Upload model
Browse files- README.md +199 -0
- config.json +26 -0
- configuration_relik.py +45 -0
- model.safetensors +3 -0
- modeling_relik.py +999 -0
README.md
ADDED
@@ -0,0 +1,199 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
tags: []
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/media/ssd/perelluis/relik_experiments/models/relik-reader-deberta-v3-large-re-wikipedia",
|
3 |
+
"activation": "gelu",
|
4 |
+
"add_entity_embedding": null,
|
5 |
+
"additional_special_symbols": 30,
|
6 |
+
"additional_special_symbols_types": 0,
|
7 |
+
"architectures": [
|
8 |
+
"RelikReaderREModel"
|
9 |
+
],
|
10 |
+
"auto_map": {
|
11 |
+
"AutoConfig": "configuration_relik.RelikReaderConfig",
|
12 |
+
"AutoModel": "modeling_relik.RelikReaderREModel"
|
13 |
+
},
|
14 |
+
"binary_end_logits": false,
|
15 |
+
"default_reader_class": null,
|
16 |
+
"entity_type_loss": null,
|
17 |
+
"linears_hidden_size": 512,
|
18 |
+
"model_type": "relik-reader",
|
19 |
+
"num_layers": null,
|
20 |
+
"threshold": 0.5,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"training": true,
|
23 |
+
"transformer_model": "microsoft/deberta-v3-small",
|
24 |
+
"transformers_version": "4.41.2",
|
25 |
+
"use_last_k_layers": 1
|
26 |
+
}
|
configuration_relik.py
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from typing import Optional
|
2 |
+
|
3 |
+
from transformers import AutoConfig
|
4 |
+
from transformers.configuration_utils import PretrainedConfig
|
5 |
+
|
6 |
+
|
7 |
+
class RelikReaderConfig(PretrainedConfig):
|
8 |
+
model_type = "relik-reader"
|
9 |
+
|
10 |
+
def __init__(
|
11 |
+
self,
|
12 |
+
transformer_model: str = "microsoft/deberta-v3-base",
|
13 |
+
additional_special_symbols: int = 101,
|
14 |
+
additional_special_symbols_types: Optional[int] = 0,
|
15 |
+
num_layers: Optional[int] = None,
|
16 |
+
activation: str = "gelu",
|
17 |
+
linears_hidden_size: Optional[int] = 512,
|
18 |
+
use_last_k_layers: int = 1,
|
19 |
+
entity_type_loss: bool = False,
|
20 |
+
add_entity_embedding: bool = None,
|
21 |
+
binary_end_logits: bool = False,
|
22 |
+
training: bool = False,
|
23 |
+
default_reader_class: Optional[str] = None,
|
24 |
+
threshold: Optional[float] = 0.5,
|
25 |
+
**kwargs
|
26 |
+
) -> None:
|
27 |
+
# TODO: add name_or_path to kwargs
|
28 |
+
self.transformer_model = transformer_model
|
29 |
+
self.additional_special_symbols = additional_special_symbols
|
30 |
+
self.additional_special_symbols_types = additional_special_symbols_types
|
31 |
+
self.num_layers = num_layers
|
32 |
+
self.activation = activation
|
33 |
+
self.linears_hidden_size = linears_hidden_size
|
34 |
+
self.use_last_k_layers = use_last_k_layers
|
35 |
+
self.entity_type_loss = entity_type_loss
|
36 |
+
self.add_entity_embedding = (
|
37 |
+
True
|
38 |
+
if add_entity_embedding is None and entity_type_loss
|
39 |
+
else add_entity_embedding
|
40 |
+
)
|
41 |
+
self.threshold = threshold
|
42 |
+
self.binary_end_logits = binary_end_logits
|
43 |
+
self.training = training
|
44 |
+
self.default_reader_class = default_reader_class
|
45 |
+
super().__init__(**kwargs)
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcaad405b58a947631c5690834dad6d3dcaf1475446a90cbfe6ec5523a44eb8e
|
3 |
+
size 585824816
|
modeling_relik.py
ADDED
@@ -0,0 +1,999 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from typing import Any, Dict, Optional
|
2 |
+
|
3 |
+
import torch
|
4 |
+
from transformers import AutoModel, PreTrainedModel
|
5 |
+
from transformers.activations import ClippedGELUActivation, GELUActivation
|
6 |
+
from transformers.configuration_utils import PretrainedConfig
|
7 |
+
from transformers.modeling_utils import PoolerEndLogits
|
8 |
+
|
9 |
+
from .configuration_relik import RelikReaderConfig
|
10 |
+
|
11 |
+
|
12 |
+
class RelikReaderSample:
|
13 |
+
def __init__(self, **kwargs):
|
14 |
+
super().__setattr__("_d", {})
|
15 |
+
self._d = kwargs
|
16 |
+
|
17 |
+
def __getattribute__(self, item):
|
18 |
+
return super(RelikReaderSample, self).__getattribute__(item)
|
19 |
+
|
20 |
+
def __getattr__(self, item):
|
21 |
+
if item.startswith("__") and item.endswith("__"):
|
22 |
+
# this is likely some python library-specific variable (such as __deepcopy__ for copy)
|
23 |
+
# better follow standard behavior here
|
24 |
+
raise AttributeError(item)
|
25 |
+
elif item in self._d:
|
26 |
+
return self._d[item]
|
27 |
+
else:
|
28 |
+
return None
|
29 |
+
|
30 |
+
def __setattr__(self, key, value):
|
31 |
+
if key in self._d:
|
32 |
+
self._d[key] = value
|
33 |
+
else:
|
34 |
+
super().__setattr__(key, value)
|
35 |
+
self._d[key] = value
|
36 |
+
|
37 |
+
|
38 |
+
activation2functions = {
|
39 |
+
"relu": torch.nn.ReLU(),
|
40 |
+
"gelu": GELUActivation(),
|
41 |
+
"gelu_10": ClippedGELUActivation(-10, 10),
|
42 |
+
}
|
43 |
+
|
44 |
+
|
45 |
+
class PoolerEndLogitsBi(PoolerEndLogits):
|
46 |
+
def __init__(self, config: PretrainedConfig):
|
47 |
+
super().__init__(config)
|
48 |
+
self.dense_1 = torch.nn.Linear(config.hidden_size, 2)
|
49 |
+
|
50 |
+
def forward(
|
51 |
+
self,
|
52 |
+
hidden_states: torch.FloatTensor,
|
53 |
+
start_states: Optional[torch.FloatTensor] = None,
|
54 |
+
start_positions: Optional[torch.LongTensor] = None,
|
55 |
+
p_mask: Optional[torch.FloatTensor] = None,
|
56 |
+
) -> torch.FloatTensor:
|
57 |
+
if p_mask is not None:
|
58 |
+
p_mask = p_mask.unsqueeze(-1)
|
59 |
+
logits = super().forward(
|
60 |
+
hidden_states,
|
61 |
+
start_states,
|
62 |
+
start_positions,
|
63 |
+
p_mask,
|
64 |
+
)
|
65 |
+
return logits
|
66 |
+
|
67 |
+
|
68 |
+
class RelikReaderSpanModel(PreTrainedModel):
|
69 |
+
config_class = RelikReaderConfig
|
70 |
+
|
71 |
+
def __init__(self, config: RelikReaderConfig, *args, **kwargs):
|
72 |
+
super().__init__(config)
|
73 |
+
# Transformer model declaration
|
74 |
+
self.config = config
|
75 |
+
self.transformer_model = (
|
76 |
+
AutoModel.from_pretrained(self.config.transformer_model)
|
77 |
+
if self.config.num_layers is None
|
78 |
+
else AutoModel.from_pretrained(
|
79 |
+
self.config.transformer_model, num_hidden_layers=self.config.num_layers
|
80 |
+
)
|
81 |
+
)
|
82 |
+
self.transformer_model.resize_token_embeddings(
|
83 |
+
self.transformer_model.config.vocab_size
|
84 |
+
+ self.config.additional_special_symbols
|
85 |
+
)
|
86 |
+
|
87 |
+
self.activation = self.config.activation
|
88 |
+
self.linears_hidden_size = self.config.linears_hidden_size
|
89 |
+
self.use_last_k_layers = self.config.use_last_k_layers
|
90 |
+
|
91 |
+
# named entity detection layers
|
92 |
+
self.ned_start_classifier = self._get_projection_layer(
|
93 |
+
self.activation, last_hidden=2, layer_norm=False
|
94 |
+
)
|
95 |
+
if self.config.binary_end_logits:
|
96 |
+
self.ned_end_classifier = PoolerEndLogitsBi(self.transformer_model.config)
|
97 |
+
else:
|
98 |
+
self.ned_end_classifier = PoolerEndLogits(self.transformer_model.config)
|
99 |
+
|
100 |
+
# END entity disambiguation layer
|
101 |
+
self.ed_start_projector = self._get_projection_layer(self.activation)
|
102 |
+
self.ed_end_projector = self._get_projection_layer(self.activation)
|
103 |
+
|
104 |
+
self.training = self.config.training
|
105 |
+
|
106 |
+
# criterion
|
107 |
+
self.criterion = torch.nn.CrossEntropyLoss()
|
108 |
+
|
109 |
+
def _get_projection_layer(
|
110 |
+
self,
|
111 |
+
activation: str,
|
112 |
+
last_hidden: Optional[int] = None,
|
113 |
+
input_hidden=None,
|
114 |
+
layer_norm: bool = True,
|
115 |
+
) -> torch.nn.Sequential:
|
116 |
+
head_components = [
|
117 |
+
torch.nn.Dropout(0.1),
|
118 |
+
torch.nn.Linear(
|
119 |
+
(
|
120 |
+
self.transformer_model.config.hidden_size * self.use_last_k_layers
|
121 |
+
if input_hidden is None
|
122 |
+
else input_hidden
|
123 |
+
),
|
124 |
+
self.linears_hidden_size,
|
125 |
+
),
|
126 |
+
activation2functions[activation],
|
127 |
+
torch.nn.Dropout(0.1),
|
128 |
+
torch.nn.Linear(
|
129 |
+
self.linears_hidden_size,
|
130 |
+
self.linears_hidden_size if last_hidden is None else last_hidden,
|
131 |
+
),
|
132 |
+
]
|
133 |
+
|
134 |
+
if layer_norm:
|
135 |
+
head_components.append(
|
136 |
+
torch.nn.LayerNorm(
|
137 |
+
self.linears_hidden_size if last_hidden is None else last_hidden,
|
138 |
+
self.transformer_model.config.layer_norm_eps,
|
139 |
+
)
|
140 |
+
)
|
141 |
+
|
142 |
+
return torch.nn.Sequential(*head_components)
|
143 |
+
|
144 |
+
def _mask_logits(self, logits: torch.Tensor, mask: torch.Tensor) -> torch.Tensor:
|
145 |
+
mask = mask.unsqueeze(-1)
|
146 |
+
if next(self.parameters()).dtype == torch.float16:
|
147 |
+
logits = logits * (1 - mask) - 65500 * mask
|
148 |
+
else:
|
149 |
+
logits = logits * (1 - mask) - 1e30 * mask
|
150 |
+
return logits
|
151 |
+
|
152 |
+
def _get_model_features(
|
153 |
+
self,
|
154 |
+
input_ids: torch.Tensor,
|
155 |
+
attention_mask: torch.Tensor,
|
156 |
+
token_type_ids: Optional[torch.Tensor],
|
157 |
+
):
|
158 |
+
model_input = {
|
159 |
+
"input_ids": input_ids,
|
160 |
+
"attention_mask": attention_mask,
|
161 |
+
"output_hidden_states": self.use_last_k_layers > 1,
|
162 |
+
}
|
163 |
+
|
164 |
+
if token_type_ids is not None:
|
165 |
+
model_input["token_type_ids"] = token_type_ids
|
166 |
+
|
167 |
+
model_output = self.transformer_model(**model_input)
|
168 |
+
|
169 |
+
if self.use_last_k_layers > 1:
|
170 |
+
model_features = torch.cat(
|
171 |
+
model_output[1][-self.use_last_k_layers :], dim=-1
|
172 |
+
)
|
173 |
+
else:
|
174 |
+
model_features = model_output[0]
|
175 |
+
|
176 |
+
return model_features
|
177 |
+
|
178 |
+
def compute_ned_end_logits(
|
179 |
+
self,
|
180 |
+
start_predictions,
|
181 |
+
start_labels,
|
182 |
+
model_features,
|
183 |
+
prediction_mask,
|
184 |
+
batch_size,
|
185 |
+
) -> Optional[torch.Tensor]:
|
186 |
+
# todo: maybe when constraining on the spans,
|
187 |
+
# we should not use a prediction_mask for the end tokens.
|
188 |
+
# at least we should not during training imo
|
189 |
+
start_positions = start_labels if self.training else start_predictions
|
190 |
+
start_positions_indices = (
|
191 |
+
torch.arange(start_positions.size(1), device=start_positions.device)
|
192 |
+
.unsqueeze(0)
|
193 |
+
.expand(batch_size, -1)[start_positions > 0]
|
194 |
+
).to(start_positions.device)
|
195 |
+
|
196 |
+
if len(start_positions_indices) > 0:
|
197 |
+
expanded_features = model_features.repeat_interleave(
|
198 |
+
torch.sum(start_positions > 0, dim=-1), dim=0
|
199 |
+
)
|
200 |
+
expanded_prediction_mask = prediction_mask.repeat_interleave(
|
201 |
+
torch.sum(start_positions > 0, dim=-1), dim=0
|
202 |
+
)
|
203 |
+
end_logits = self.ned_end_classifier(
|
204 |
+
hidden_states=expanded_features,
|
205 |
+
start_positions=start_positions_indices,
|
206 |
+
p_mask=expanded_prediction_mask,
|
207 |
+
)
|
208 |
+
|
209 |
+
return end_logits
|
210 |
+
|
211 |
+
return None
|
212 |
+
|
213 |
+
def compute_classification_logits(
|
214 |
+
self,
|
215 |
+
model_features_start,
|
216 |
+
model_features_end,
|
217 |
+
special_symbols_features,
|
218 |
+
) -> torch.Tensor:
|
219 |
+
model_start_features = self.ed_start_projector(model_features_start)
|
220 |
+
model_end_features = self.ed_end_projector(model_features_end)
|
221 |
+
model_start_features_symbols = self.ed_start_projector(special_symbols_features)
|
222 |
+
model_end_features_symbols = self.ed_end_projector(special_symbols_features)
|
223 |
+
|
224 |
+
model_ed_features = torch.cat(
|
225 |
+
[model_start_features, model_end_features], dim=-1
|
226 |
+
)
|
227 |
+
special_symbols_representation = torch.cat(
|
228 |
+
[model_start_features_symbols, model_end_features_symbols], dim=-1
|
229 |
+
)
|
230 |
+
|
231 |
+
logits = torch.bmm(
|
232 |
+
model_ed_features,
|
233 |
+
torch.permute(special_symbols_representation, (0, 2, 1)),
|
234 |
+
)
|
235 |
+
|
236 |
+
logits = self._mask_logits(
|
237 |
+
logits, (model_features_start == -100).all(2).long()
|
238 |
+
)
|
239 |
+
return logits
|
240 |
+
|
241 |
+
def forward(
|
242 |
+
self,
|
243 |
+
input_ids: torch.Tensor,
|
244 |
+
attention_mask: torch.Tensor,
|
245 |
+
token_type_ids: Optional[torch.Tensor] = None,
|
246 |
+
prediction_mask: Optional[torch.Tensor] = None,
|
247 |
+
special_symbols_mask: Optional[torch.Tensor] = None,
|
248 |
+
start_labels: Optional[torch.Tensor] = None,
|
249 |
+
end_labels: Optional[torch.Tensor] = None,
|
250 |
+
use_predefined_spans: bool = False,
|
251 |
+
*args,
|
252 |
+
**kwargs,
|
253 |
+
) -> Dict[str, Any]:
|
254 |
+
batch_size, seq_len = input_ids.shape
|
255 |
+
|
256 |
+
model_features = self._get_model_features(
|
257 |
+
input_ids, attention_mask, token_type_ids
|
258 |
+
)
|
259 |
+
|
260 |
+
ned_start_labels = None
|
261 |
+
|
262 |
+
# named entity detection if required
|
263 |
+
if use_predefined_spans: # no need to compute spans
|
264 |
+
ned_start_logits, ned_start_probabilities, ned_start_predictions = (
|
265 |
+
None,
|
266 |
+
None,
|
267 |
+
(
|
268 |
+
torch.clone(start_labels)
|
269 |
+
if start_labels is not None
|
270 |
+
else torch.zeros_like(input_ids)
|
271 |
+
),
|
272 |
+
)
|
273 |
+
ned_end_logits, ned_end_probabilities, ned_end_predictions = (
|
274 |
+
None,
|
275 |
+
None,
|
276 |
+
(
|
277 |
+
torch.clone(end_labels)
|
278 |
+
if end_labels is not None
|
279 |
+
else torch.zeros_like(input_ids)
|
280 |
+
),
|
281 |
+
)
|
282 |
+
ned_start_predictions[ned_start_predictions > 0] = 1
|
283 |
+
ned_end_predictions[end_labels > 0] = 1
|
284 |
+
ned_end_predictions = ned_end_predictions[~(end_labels == -100).all(2)]
|
285 |
+
|
286 |
+
else: # compute spans
|
287 |
+
# start boundary prediction
|
288 |
+
ned_start_logits = self.ned_start_classifier(model_features)
|
289 |
+
ned_start_logits = self._mask_logits(ned_start_logits, prediction_mask)
|
290 |
+
ned_start_probabilities = torch.softmax(ned_start_logits, dim=-1)
|
291 |
+
ned_start_predictions = ned_start_probabilities.argmax(dim=-1)
|
292 |
+
|
293 |
+
# end boundary prediction
|
294 |
+
ned_start_labels = (
|
295 |
+
torch.zeros_like(start_labels) if start_labels is not None else None
|
296 |
+
)
|
297 |
+
|
298 |
+
if ned_start_labels is not None:
|
299 |
+
ned_start_labels[start_labels == -100] = -100
|
300 |
+
ned_start_labels[start_labels > 0] = 1
|
301 |
+
|
302 |
+
ned_end_logits = self.compute_ned_end_logits(
|
303 |
+
ned_start_predictions,
|
304 |
+
ned_start_labels,
|
305 |
+
model_features,
|
306 |
+
prediction_mask,
|
307 |
+
batch_size,
|
308 |
+
)
|
309 |
+
|
310 |
+
if ned_end_logits is not None:
|
311 |
+
ned_end_probabilities = torch.softmax(ned_end_logits, dim=-1)
|
312 |
+
if not self.config.binary_end_logits:
|
313 |
+
ned_end_predictions = torch.argmax(ned_end_probabilities, dim=-1, keepdim=True)
|
314 |
+
ned_end_predictions = torch.zeros_like(ned_end_probabilities).scatter_(1, ned_end_predictions, 1)
|
315 |
+
else:
|
316 |
+
ned_end_predictions = torch.argmax(ned_end_probabilities, dim=-1)
|
317 |
+
else:
|
318 |
+
ned_end_logits, ned_end_probabilities = None, None
|
319 |
+
ned_end_predictions = ned_start_predictions.new_zeros(batch_size, seq_len)
|
320 |
+
|
321 |
+
if not self.training:
|
322 |
+
# if len(ned_end_predictions.shape) < 2:
|
323 |
+
# print(ned_end_predictions)
|
324 |
+
end_preds_count = ned_end_predictions.sum(1)
|
325 |
+
# If there are no end predictions for a start prediction, remove the start prediction
|
326 |
+
if (end_preds_count == 0).any() and (ned_start_predictions > 0).any():
|
327 |
+
ned_start_predictions[ned_start_predictions == 1] = (
|
328 |
+
end_preds_count != 0
|
329 |
+
).long()
|
330 |
+
ned_end_predictions = ned_end_predictions[end_preds_count != 0]
|
331 |
+
|
332 |
+
if end_labels is not None:
|
333 |
+
end_labels = end_labels[~(end_labels == -100).all(2)]
|
334 |
+
|
335 |
+
start_position, end_position = (
|
336 |
+
(start_labels, end_labels)
|
337 |
+
if self.training
|
338 |
+
else (ned_start_predictions, ned_end_predictions)
|
339 |
+
)
|
340 |
+
start_counts = (start_position > 0).sum(1)
|
341 |
+
if (start_counts > 0).any():
|
342 |
+
ned_end_predictions = ned_end_predictions.split(start_counts.tolist())
|
343 |
+
# Entity disambiguation
|
344 |
+
if (end_position > 0).sum() > 0:
|
345 |
+
ends_count = (end_position > 0).sum(1)
|
346 |
+
model_entity_start = torch.repeat_interleave(
|
347 |
+
model_features[start_position > 0], ends_count, dim=0
|
348 |
+
)
|
349 |
+
model_entity_end = torch.repeat_interleave(
|
350 |
+
model_features, start_counts, dim=0)[
|
351 |
+
end_position > 0
|
352 |
+
]
|
353 |
+
ents_count = torch.nn.utils.rnn.pad_sequence(
|
354 |
+
torch.split(ends_count, start_counts.tolist()),
|
355 |
+
batch_first=True,
|
356 |
+
padding_value=0,
|
357 |
+
).sum(1)
|
358 |
+
|
359 |
+
model_entity_start = torch.nn.utils.rnn.pad_sequence(
|
360 |
+
torch.split(model_entity_start, ents_count.tolist()),
|
361 |
+
batch_first=True,
|
362 |
+
padding_value=-100,
|
363 |
+
)
|
364 |
+
|
365 |
+
model_entity_end = torch.nn.utils.rnn.pad_sequence(
|
366 |
+
torch.split(model_entity_end, ents_count.tolist()),
|
367 |
+
batch_first=True,
|
368 |
+
padding_value=-100,
|
369 |
+
)
|
370 |
+
|
371 |
+
ed_logits = self.compute_classification_logits(
|
372 |
+
model_entity_start,
|
373 |
+
model_entity_end,
|
374 |
+
model_features[special_symbols_mask].view(
|
375 |
+
batch_size, -1, model_features.shape[-1]
|
376 |
+
),
|
377 |
+
)
|
378 |
+
ed_probabilities = torch.softmax(ed_logits, dim=-1)
|
379 |
+
ed_predictions = torch.argmax(ed_probabilities, dim=-1)
|
380 |
+
else:
|
381 |
+
ed_logits, ed_probabilities, ed_predictions = (
|
382 |
+
None,
|
383 |
+
ned_start_predictions.new_zeros(batch_size, seq_len),
|
384 |
+
ned_start_predictions.new_zeros(batch_size),
|
385 |
+
)
|
386 |
+
# output build
|
387 |
+
output_dict = dict(
|
388 |
+
batch_size=batch_size,
|
389 |
+
ned_start_logits=ned_start_logits,
|
390 |
+
ned_start_probabilities=ned_start_probabilities,
|
391 |
+
ned_start_predictions=ned_start_predictions,
|
392 |
+
ned_end_logits=ned_end_logits,
|
393 |
+
ned_end_probabilities=ned_end_probabilities,
|
394 |
+
ned_end_predictions=ned_end_predictions,
|
395 |
+
ed_logits=ed_logits,
|
396 |
+
ed_probabilities=ed_probabilities,
|
397 |
+
ed_predictions=ed_predictions,
|
398 |
+
)
|
399 |
+
|
400 |
+
# compute loss if labels
|
401 |
+
if start_labels is not None and end_labels is not None and self.training:
|
402 |
+
# named entity detection loss
|
403 |
+
|
404 |
+
# start
|
405 |
+
if ned_start_logits is not None:
|
406 |
+
ned_start_loss = self.criterion(
|
407 |
+
ned_start_logits.view(-1, ned_start_logits.shape[-1]),
|
408 |
+
ned_start_labels.view(-1),
|
409 |
+
)
|
410 |
+
else:
|
411 |
+
ned_start_loss = 0
|
412 |
+
|
413 |
+
# end
|
414 |
+
# use ents_count to assign the labels to the correct positions i.e. using end_labels -> [[0,0,4,0], [0,0,0,2]] -> [4,2] (this is just an element, for batch we need to mask it with ents_count), ie -> [[4,2,-100,-100], [3,1,2,-100], [1,3,2,5]]
|
415 |
+
|
416 |
+
if ned_end_logits is not None:
|
417 |
+
ed_labels = end_labels.clone()
|
418 |
+
ed_labels = torch.nn.utils.rnn.pad_sequence(
|
419 |
+
torch.split(ed_labels[ed_labels > 0], ents_count.tolist()),
|
420 |
+
batch_first=True,
|
421 |
+
padding_value=-100,
|
422 |
+
)
|
423 |
+
end_labels[end_labels > 0] = 1
|
424 |
+
if not self.config.binary_end_logits:
|
425 |
+
# transform label to position in the sequence
|
426 |
+
end_labels = end_labels.argmax(dim=-1)
|
427 |
+
ned_end_loss = self.criterion(
|
428 |
+
ned_end_logits.view(-1, ned_end_logits.shape[-1]),
|
429 |
+
end_labels.view(-1),
|
430 |
+
)
|
431 |
+
else:
|
432 |
+
ned_end_loss = self.criterion(ned_end_logits.reshape(-1, ned_end_logits.shape[-1]), end_labels.reshape(-1).long())
|
433 |
+
|
434 |
+
# entity disambiguation loss
|
435 |
+
ed_loss = self.criterion(
|
436 |
+
ed_logits.view(-1, ed_logits.shape[-1]),
|
437 |
+
ed_labels.view(-1).long(),
|
438 |
+
)
|
439 |
+
|
440 |
+
else:
|
441 |
+
ned_end_loss = 0
|
442 |
+
ed_loss = 0
|
443 |
+
|
444 |
+
output_dict["ned_start_loss"] = ned_start_loss
|
445 |
+
output_dict["ned_end_loss"] = ned_end_loss
|
446 |
+
output_dict["ed_loss"] = ed_loss
|
447 |
+
|
448 |
+
output_dict["loss"] = ned_start_loss + ned_end_loss + ed_loss
|
449 |
+
|
450 |
+
return output_dict
|
451 |
+
|
452 |
+
|
453 |
+
class RelikReaderREModel(PreTrainedModel):
|
454 |
+
config_class = RelikReaderConfig
|
455 |
+
|
456 |
+
def __init__(self, config, *args, **kwargs):
|
457 |
+
super().__init__(config)
|
458 |
+
# Transformer model declaration
|
459 |
+
# self.transformer_model_name = transformer_model
|
460 |
+
self.config = config
|
461 |
+
self.transformer_model = (
|
462 |
+
AutoModel.from_pretrained(config.transformer_model)
|
463 |
+
if config.num_layers is None
|
464 |
+
else AutoModel.from_pretrained(
|
465 |
+
config.transformer_model, num_hidden_layers=config.num_layers
|
466 |
+
)
|
467 |
+
)
|
468 |
+
self.transformer_model.resize_token_embeddings(
|
469 |
+
self.transformer_model.config.vocab_size
|
470 |
+
+ config.additional_special_symbols
|
471 |
+
+ config.additional_special_symbols_types,
|
472 |
+
)
|
473 |
+
|
474 |
+
# named entity detection layers
|
475 |
+
self.ned_start_classifier = self._get_projection_layer(
|
476 |
+
config.activation, last_hidden=2, layer_norm=False
|
477 |
+
)
|
478 |
+
|
479 |
+
self.ned_end_classifier = PoolerEndLogitsBi(self.transformer_model.config)
|
480 |
+
|
481 |
+
self.relation_disambiguation_loss = (
|
482 |
+
config.relation_disambiguation_loss
|
483 |
+
if hasattr(config, "relation_disambiguation_loss")
|
484 |
+
else False
|
485 |
+
)
|
486 |
+
|
487 |
+
if self.config.entity_type_loss and self.config.add_entity_embedding:
|
488 |
+
input_hidden_ents = 3
|
489 |
+
else:
|
490 |
+
input_hidden_ents = 2
|
491 |
+
|
492 |
+
self.re_projector = self._get_projection_layer(
|
493 |
+
config.activation,
|
494 |
+
input_hidden=input_hidden_ents * self.transformer_model.config.hidden_size,
|
495 |
+
hidden=input_hidden_ents * self.config.linears_hidden_size,
|
496 |
+
last_hidden=2 * self.config.linears_hidden_size,
|
497 |
+
)
|
498 |
+
|
499 |
+
self.re_relation_projector = self._get_projection_layer(
|
500 |
+
config.activation,
|
501 |
+
input_hidden=self.transformer_model.config.hidden_size,
|
502 |
+
)
|
503 |
+
|
504 |
+
if self.config.entity_type_loss or self.relation_disambiguation_loss:
|
505 |
+
self.re_entities_projector = self._get_projection_layer(
|
506 |
+
config.activation,
|
507 |
+
input_hidden=2 * self.transformer_model.config.hidden_size,
|
508 |
+
)
|
509 |
+
self.re_definition_projector = self._get_projection_layer(
|
510 |
+
config.activation,
|
511 |
+
)
|
512 |
+
|
513 |
+
self.re_classifier = self._get_projection_layer(
|
514 |
+
config.activation,
|
515 |
+
input_hidden=config.linears_hidden_size,
|
516 |
+
last_hidden=2,
|
517 |
+
layer_norm=False,
|
518 |
+
)
|
519 |
+
|
520 |
+
self.training = config.training
|
521 |
+
|
522 |
+
# criterion
|
523 |
+
self.criterion = torch.nn.CrossEntropyLoss()
|
524 |
+
self.criterion_type = torch.nn.BCEWithLogitsLoss()
|
525 |
+
|
526 |
+
def _get_projection_layer(
|
527 |
+
self,
|
528 |
+
activation: str,
|
529 |
+
last_hidden: Optional[int] = None,
|
530 |
+
hidden: Optional[int] = None,
|
531 |
+
input_hidden=None,
|
532 |
+
layer_norm: bool = True,
|
533 |
+
) -> torch.nn.Sequential:
|
534 |
+
head_components = [
|
535 |
+
torch.nn.Dropout(0.1),
|
536 |
+
torch.nn.Linear(
|
537 |
+
(
|
538 |
+
self.transformer_model.config.hidden_size
|
539 |
+
* self.config.use_last_k_layers
|
540 |
+
if input_hidden is None
|
541 |
+
else input_hidden
|
542 |
+
),
|
543 |
+
self.config.linears_hidden_size if hidden is None else hidden,
|
544 |
+
),
|
545 |
+
activation2functions[activation],
|
546 |
+
torch.nn.Dropout(0.1),
|
547 |
+
torch.nn.Linear(
|
548 |
+
self.config.linears_hidden_size if hidden is None else hidden,
|
549 |
+
self.config.linears_hidden_size if last_hidden is None else last_hidden,
|
550 |
+
),
|
551 |
+
]
|
552 |
+
|
553 |
+
if layer_norm:
|
554 |
+
head_components.append(
|
555 |
+
torch.nn.LayerNorm(
|
556 |
+
(
|
557 |
+
self.config.linears_hidden_size
|
558 |
+
if last_hidden is None
|
559 |
+
else last_hidden
|
560 |
+
),
|
561 |
+
self.transformer_model.config.layer_norm_eps,
|
562 |
+
)
|
563 |
+
)
|
564 |
+
|
565 |
+
return torch.nn.Sequential(*head_components)
|
566 |
+
|
567 |
+
def _mask_logits(self, logits: torch.Tensor, mask: torch.Tensor) -> torch.Tensor:
|
568 |
+
mask = mask.unsqueeze(-1)
|
569 |
+
if next(self.parameters()).dtype == torch.float16:
|
570 |
+
logits = logits * (1 - mask) - 65500 * mask
|
571 |
+
else:
|
572 |
+
logits = logits * (1 - mask) - 1e30 * mask
|
573 |
+
return logits
|
574 |
+
|
575 |
+
def _get_model_features(
|
576 |
+
self,
|
577 |
+
input_ids: torch.Tensor,
|
578 |
+
attention_mask: torch.Tensor,
|
579 |
+
token_type_ids: Optional[torch.Tensor],
|
580 |
+
):
|
581 |
+
model_input = {
|
582 |
+
"input_ids": input_ids,
|
583 |
+
"attention_mask": attention_mask,
|
584 |
+
"output_hidden_states": self.config.use_last_k_layers > 1,
|
585 |
+
}
|
586 |
+
|
587 |
+
if token_type_ids is not None:
|
588 |
+
model_input["token_type_ids"] = token_type_ids
|
589 |
+
|
590 |
+
model_output = self.transformer_model(**model_input)
|
591 |
+
|
592 |
+
if self.config.use_last_k_layers > 1:
|
593 |
+
model_features = torch.cat(
|
594 |
+
model_output[1][-self.config.use_last_k_layers :], dim=-1
|
595 |
+
)
|
596 |
+
else:
|
597 |
+
model_features = model_output[0]
|
598 |
+
|
599 |
+
return model_features
|
600 |
+
|
601 |
+
def compute_ned_end_logits(
|
602 |
+
self,
|
603 |
+
start_predictions,
|
604 |
+
start_labels,
|
605 |
+
model_features,
|
606 |
+
prediction_mask,
|
607 |
+
batch_size,
|
608 |
+
mask_preceding: bool = False,
|
609 |
+
) -> Optional[torch.Tensor]:
|
610 |
+
# todo: maybe when constraining on the spans,
|
611 |
+
# we should not use a prediction_mask for the end tokens.
|
612 |
+
# at least we should not during training imo
|
613 |
+
start_positions = start_labels if self.training else start_predictions
|
614 |
+
start_positions_indices = (
|
615 |
+
torch.arange(start_positions.size(1), device=start_positions.device)
|
616 |
+
.unsqueeze(0)
|
617 |
+
.expand(batch_size, -1)[start_positions > 0]
|
618 |
+
).to(start_positions.device)
|
619 |
+
|
620 |
+
if len(start_positions_indices) > 0:
|
621 |
+
expanded_features = model_features.repeat_interleave(
|
622 |
+
torch.sum(start_positions > 0, dim=-1), dim=0
|
623 |
+
)
|
624 |
+
expanded_prediction_mask = prediction_mask.repeat_interleave(
|
625 |
+
torch.sum(start_positions > 0, dim=-1), dim=0
|
626 |
+
)
|
627 |
+
if mask_preceding:
|
628 |
+
expanded_prediction_mask[
|
629 |
+
torch.arange(
|
630 |
+
expanded_prediction_mask.shape[1],
|
631 |
+
device=expanded_prediction_mask.device,
|
632 |
+
)
|
633 |
+
< start_positions_indices.unsqueeze(1)
|
634 |
+
] = 1
|
635 |
+
end_logits = self.ned_end_classifier(
|
636 |
+
hidden_states=expanded_features,
|
637 |
+
start_positions=start_positions_indices,
|
638 |
+
p_mask=expanded_prediction_mask,
|
639 |
+
)
|
640 |
+
|
641 |
+
return end_logits
|
642 |
+
|
643 |
+
return None
|
644 |
+
|
645 |
+
def compute_relation_logits(
|
646 |
+
self,
|
647 |
+
model_entity_features,
|
648 |
+
special_symbols_features,
|
649 |
+
) -> torch.Tensor:
|
650 |
+
model_subject_object_features = self.re_projector(model_entity_features)
|
651 |
+
model_subject_features = model_subject_object_features[
|
652 |
+
:, :, : model_subject_object_features.shape[-1] // 2
|
653 |
+
]
|
654 |
+
model_object_features = model_subject_object_features[
|
655 |
+
:, :, model_subject_object_features.shape[-1] // 2 :
|
656 |
+
]
|
657 |
+
special_symbols_start_representation = self.re_relation_projector(
|
658 |
+
special_symbols_features
|
659 |
+
)
|
660 |
+
re_logits = torch.einsum(
|
661 |
+
"bse,bde,bfe->bsdfe",
|
662 |
+
model_subject_features,
|
663 |
+
model_object_features,
|
664 |
+
special_symbols_start_representation,
|
665 |
+
)
|
666 |
+
re_logits = self.re_classifier(re_logits)
|
667 |
+
|
668 |
+
return re_logits
|
669 |
+
|
670 |
+
def compute_entity_logits(
|
671 |
+
self,
|
672 |
+
model_entity_features,
|
673 |
+
special_symbols_features,
|
674 |
+
) -> torch.Tensor:
|
675 |
+
model_ed_features = self.re_entities_projector(model_entity_features)
|
676 |
+
special_symbols_ed_representation = self.re_definition_projector(
|
677 |
+
special_symbols_features
|
678 |
+
)
|
679 |
+
|
680 |
+
logits = torch.bmm(
|
681 |
+
model_ed_features,
|
682 |
+
torch.permute(special_symbols_ed_representation, (0, 2, 1)),
|
683 |
+
)
|
684 |
+
logits = self._mask_logits(
|
685 |
+
logits, (model_entity_features == -100).all(2).long()
|
686 |
+
)
|
687 |
+
return logits
|
688 |
+
|
689 |
+
def compute_loss(self, logits, labels, mask=None):
|
690 |
+
logits = logits.reshape(-1, logits.shape[-1])
|
691 |
+
labels = labels.reshape(-1).long()
|
692 |
+
if mask is not None:
|
693 |
+
return self.criterion(logits[mask], labels[mask])
|
694 |
+
return self.criterion(logits, labels)
|
695 |
+
|
696 |
+
def compute_ned_type_loss(
|
697 |
+
self,
|
698 |
+
disambiguation_labels,
|
699 |
+
re_ned_entities_logits,
|
700 |
+
ned_type_logits,
|
701 |
+
re_entities_logits,
|
702 |
+
entity_types,
|
703 |
+
mask,
|
704 |
+
):
|
705 |
+
if self.config.entity_type_loss and self.relation_disambiguation_loss:
|
706 |
+
return self.criterion_type(
|
707 |
+
re_ned_entities_logits[disambiguation_labels != -100],
|
708 |
+
disambiguation_labels[disambiguation_labels != -100],
|
709 |
+
)
|
710 |
+
if self.config.entity_type_loss:
|
711 |
+
return self.criterion_type(
|
712 |
+
ned_type_logits[mask],
|
713 |
+
disambiguation_labels[:, :, :entity_types][mask],
|
714 |
+
)
|
715 |
+
|
716 |
+
if self.relation_disambiguation_loss:
|
717 |
+
return self.criterion_type(
|
718 |
+
re_entities_logits[disambiguation_labels != -100],
|
719 |
+
disambiguation_labels[disambiguation_labels != -100],
|
720 |
+
)
|
721 |
+
return 0
|
722 |
+
|
723 |
+
def compute_relation_loss(self, relation_labels, re_logits):
|
724 |
+
return self.compute_loss(
|
725 |
+
re_logits, relation_labels, relation_labels.view(-1) != -100
|
726 |
+
)
|
727 |
+
|
728 |
+
def forward(
|
729 |
+
self,
|
730 |
+
input_ids: torch.Tensor,
|
731 |
+
attention_mask: torch.Tensor,
|
732 |
+
token_type_ids: torch.Tensor,
|
733 |
+
prediction_mask: Optional[torch.Tensor] = None,
|
734 |
+
special_symbols_mask: Optional[torch.Tensor] = None,
|
735 |
+
special_symbols_mask_entities: Optional[torch.Tensor] = None,
|
736 |
+
start_labels: Optional[torch.Tensor] = None,
|
737 |
+
end_labels: Optional[torch.Tensor] = None,
|
738 |
+
disambiguation_labels: Optional[torch.Tensor] = None,
|
739 |
+
relation_labels: Optional[torch.Tensor] = None,
|
740 |
+
relation_threshold: float = None,
|
741 |
+
is_validation: bool = False,
|
742 |
+
is_prediction: bool = False,
|
743 |
+
use_predefined_spans: bool = False,
|
744 |
+
*args,
|
745 |
+
**kwargs,
|
746 |
+
) -> Dict[str, Any]:
|
747 |
+
relation_threshold = (
|
748 |
+
self.config.threshold if relation_threshold is None else relation_threshold
|
749 |
+
)
|
750 |
+
|
751 |
+
batch_size = input_ids.shape[0]
|
752 |
+
|
753 |
+
model_features = self._get_model_features(
|
754 |
+
input_ids, attention_mask, token_type_ids
|
755 |
+
)
|
756 |
+
|
757 |
+
# named entity detection
|
758 |
+
if use_predefined_spans:
|
759 |
+
ned_start_logits, ned_start_probabilities, ned_start_predictions = (
|
760 |
+
None,
|
761 |
+
None,
|
762 |
+
torch.zeros_like(start_labels),
|
763 |
+
)
|
764 |
+
ned_end_logits, ned_end_probabilities, ned_end_predictions = (
|
765 |
+
None,
|
766 |
+
None,
|
767 |
+
torch.zeros_like(end_labels),
|
768 |
+
)
|
769 |
+
|
770 |
+
ned_start_predictions[start_labels > 0] = 1
|
771 |
+
ned_end_predictions[end_labels > 0] = 1
|
772 |
+
ned_end_predictions = ned_end_predictions[~(end_labels == -100).all(2)]
|
773 |
+
ned_start_labels = start_labels
|
774 |
+
ned_start_labels[start_labels > 0] = 1
|
775 |
+
else:
|
776 |
+
# start boundary prediction
|
777 |
+
ned_start_logits = self.ned_start_classifier(model_features)
|
778 |
+
if is_validation or is_prediction:
|
779 |
+
ned_start_logits = self._mask_logits(
|
780 |
+
ned_start_logits, prediction_mask
|
781 |
+
) # why?
|
782 |
+
ned_start_probabilities = torch.softmax(ned_start_logits, dim=-1)
|
783 |
+
ned_start_predictions = ned_start_probabilities.argmax(dim=-1)
|
784 |
+
|
785 |
+
# end boundary prediction
|
786 |
+
ned_start_labels = (
|
787 |
+
torch.zeros_like(start_labels) if start_labels is not None else None
|
788 |
+
)
|
789 |
+
|
790 |
+
# start_labels contain entity id at their position, we just need 1 for start of entity
|
791 |
+
if ned_start_labels is not None:
|
792 |
+
ned_start_labels[start_labels == -100] = -100
|
793 |
+
ned_start_labels[start_labels > 0] = 1
|
794 |
+
|
795 |
+
# compute end logits only if there are any start predictions.
|
796 |
+
# For each start prediction, n end predictions are made
|
797 |
+
ned_end_logits = self.compute_ned_end_logits(
|
798 |
+
ned_start_predictions,
|
799 |
+
ned_start_labels,
|
800 |
+
model_features,
|
801 |
+
prediction_mask,
|
802 |
+
batch_size,
|
803 |
+
True,
|
804 |
+
)
|
805 |
+
|
806 |
+
if ned_end_logits is not None:
|
807 |
+
# For each start prediction, n end predictions are made based on
|
808 |
+
# binary classification ie. argmax at each position.
|
809 |
+
ned_end_probabilities = torch.softmax(ned_end_logits, dim=-1)
|
810 |
+
ned_end_predictions = ned_end_probabilities.argmax(dim=-1)
|
811 |
+
else:
|
812 |
+
ned_end_logits, ned_end_probabilities = None, None
|
813 |
+
ned_end_predictions = torch.zeros_like(ned_start_predictions)
|
814 |
+
|
815 |
+
if is_prediction or is_validation:
|
816 |
+
end_preds_count = ned_end_predictions.sum(1)
|
817 |
+
# If there are no end predictions for a start prediction, remove the start prediction
|
818 |
+
if (end_preds_count == 0).any() and (ned_start_predictions > 0).any():
|
819 |
+
ned_start_predictions[ned_start_predictions == 1] = (
|
820 |
+
end_preds_count != 0
|
821 |
+
).long()
|
822 |
+
ned_end_predictions = ned_end_predictions[end_preds_count != 0]
|
823 |
+
|
824 |
+
if end_labels is not None:
|
825 |
+
end_labels = end_labels[~(end_labels == -100).all(2)]
|
826 |
+
|
827 |
+
start_position, end_position = (
|
828 |
+
(start_labels, end_labels)
|
829 |
+
if (not is_prediction and not is_validation)
|
830 |
+
else (ned_start_predictions, ned_end_predictions)
|
831 |
+
)
|
832 |
+
|
833 |
+
start_counts = (start_position > 0).sum(1)
|
834 |
+
if (start_counts > 0).any():
|
835 |
+
ned_end_predictions = ned_end_predictions.split(start_counts.tolist())
|
836 |
+
# limit to 30 predictions per document using start_counts, by setting all po after sum is 30 to 0
|
837 |
+
# if is_validation or is_prediction:
|
838 |
+
# ned_start_predictions[ned_start_predictions == 1] = start_counts
|
839 |
+
# We can only predict relations if we have start and end predictions
|
840 |
+
if (end_position > 0).sum() > 0:
|
841 |
+
ends_count = (end_position > 0).sum(1)
|
842 |
+
model_subject_features = torch.cat(
|
843 |
+
[
|
844 |
+
torch.repeat_interleave(
|
845 |
+
model_features[start_position > 0], ends_count, dim=0
|
846 |
+
), # start position features
|
847 |
+
torch.repeat_interleave(model_features, start_counts, dim=0)[
|
848 |
+
end_position > 0
|
849 |
+
], # end position features
|
850 |
+
],
|
851 |
+
dim=-1,
|
852 |
+
)
|
853 |
+
ents_count = torch.nn.utils.rnn.pad_sequence(
|
854 |
+
torch.split(ends_count, start_counts.tolist()),
|
855 |
+
batch_first=True,
|
856 |
+
padding_value=0,
|
857 |
+
).sum(1)
|
858 |
+
model_subject_features = torch.nn.utils.rnn.pad_sequence(
|
859 |
+
torch.split(model_subject_features, ents_count.tolist()),
|
860 |
+
batch_first=True,
|
861 |
+
padding_value=-100,
|
862 |
+
)
|
863 |
+
|
864 |
+
# if is_validation or is_prediction:
|
865 |
+
# model_subject_features = model_subject_features[:, :30, :]
|
866 |
+
|
867 |
+
# entity disambiguation. Here relation_disambiguation_loss would only be useful to
|
868 |
+
# reduce the number of candidate relations for the next step, but currently unused.
|
869 |
+
if self.config.entity_type_loss or self.relation_disambiguation_loss:
|
870 |
+
(re_ned_entities_logits) = self.compute_entity_logits(
|
871 |
+
model_subject_features,
|
872 |
+
model_features[
|
873 |
+
special_symbols_mask | special_symbols_mask_entities
|
874 |
+
].view(batch_size, -1, model_features.shape[-1]),
|
875 |
+
)
|
876 |
+
entity_types = torch.sum(special_symbols_mask_entities, dim=1)[0].item()
|
877 |
+
ned_type_logits = re_ned_entities_logits[:, :, :entity_types]
|
878 |
+
re_entities_logits = re_ned_entities_logits[:, :, entity_types:]
|
879 |
+
|
880 |
+
if self.config.entity_type_loss:
|
881 |
+
ned_type_probabilities = torch.sigmoid(ned_type_logits)
|
882 |
+
ned_type_predictions = ned_type_probabilities.argmax(dim=-1)
|
883 |
+
|
884 |
+
if self.config.add_entity_embedding:
|
885 |
+
special_symbols_representation = model_features[
|
886 |
+
special_symbols_mask_entities
|
887 |
+
].view(batch_size, entity_types, -1)
|
888 |
+
|
889 |
+
entities_representation = torch.einsum(
|
890 |
+
"bsp,bpe->bse",
|
891 |
+
ned_type_probabilities,
|
892 |
+
special_symbols_representation,
|
893 |
+
)
|
894 |
+
model_subject_features = torch.cat(
|
895 |
+
[model_subject_features, entities_representation], dim=-1
|
896 |
+
)
|
897 |
+
re_entities_probabilities = torch.sigmoid(re_entities_logits)
|
898 |
+
re_entities_predictions = re_entities_probabilities.round()
|
899 |
+
else:
|
900 |
+
(
|
901 |
+
ned_type_logits,
|
902 |
+
ned_type_probabilities,
|
903 |
+
re_entities_logits,
|
904 |
+
re_entities_probabilities,
|
905 |
+
) = (None, None, None, None)
|
906 |
+
ned_type_predictions, re_entities_predictions = (
|
907 |
+
torch.zeros([batch_size, 1], dtype=torch.long).to(input_ids.device),
|
908 |
+
torch.zeros([batch_size, 1], dtype=torch.long).to(input_ids.device),
|
909 |
+
)
|
910 |
+
|
911 |
+
# Compute relation logits
|
912 |
+
re_logits = self.compute_relation_logits(
|
913 |
+
model_subject_features,
|
914 |
+
model_features[special_symbols_mask].view(
|
915 |
+
batch_size, -1, model_features.shape[-1]
|
916 |
+
),
|
917 |
+
)
|
918 |
+
|
919 |
+
re_probabilities = torch.softmax(re_logits, dim=-1)
|
920 |
+
# we set a thresshold instead of argmax in cause it needs to be tweaked
|
921 |
+
re_predictions = re_probabilities[:, :, :, :, 1] > relation_threshold
|
922 |
+
re_probabilities = re_probabilities[:, :, :, :, 1]
|
923 |
+
else:
|
924 |
+
(
|
925 |
+
ned_type_logits,
|
926 |
+
ned_type_probabilities,
|
927 |
+
re_entities_logits,
|
928 |
+
re_entities_probabilities,
|
929 |
+
) = (None, None, None, None)
|
930 |
+
ned_type_predictions, re_entities_predictions = (
|
931 |
+
torch.zeros([batch_size, 1], dtype=torch.long).to(input_ids.device),
|
932 |
+
torch.zeros([batch_size, 1], dtype=torch.long).to(input_ids.device),
|
933 |
+
)
|
934 |
+
re_logits, re_probabilities, re_predictions = (
|
935 |
+
torch.zeros(
|
936 |
+
[batch_size, 1, 1, special_symbols_mask.sum(1)[0]], dtype=torch.long
|
937 |
+
).to(input_ids.device),
|
938 |
+
torch.zeros(
|
939 |
+
[batch_size, 1, 1, special_symbols_mask.sum(1)[0]], dtype=torch.long
|
940 |
+
).to(input_ids.device),
|
941 |
+
torch.zeros(
|
942 |
+
[batch_size, 1, 1, special_symbols_mask.sum(1)[0]], dtype=torch.long
|
943 |
+
).to(input_ids.device),
|
944 |
+
)
|
945 |
+
|
946 |
+
# output build
|
947 |
+
output_dict = dict(
|
948 |
+
batch_size=batch_size,
|
949 |
+
ned_start_logits=ned_start_logits,
|
950 |
+
ned_start_probabilities=ned_start_probabilities,
|
951 |
+
ned_start_predictions=ned_start_predictions,
|
952 |
+
ned_end_logits=ned_end_logits,
|
953 |
+
ned_end_probabilities=ned_end_probabilities,
|
954 |
+
ned_end_predictions=ned_end_predictions,
|
955 |
+
ned_type_logits=ned_type_logits,
|
956 |
+
ned_type_probabilities=ned_type_probabilities,
|
957 |
+
ned_type_predictions=ned_type_predictions,
|
958 |
+
re_entities_logits=re_entities_logits,
|
959 |
+
re_entities_probabilities=re_entities_probabilities,
|
960 |
+
re_entities_predictions=re_entities_predictions,
|
961 |
+
re_logits=re_logits,
|
962 |
+
re_probabilities=re_probabilities,
|
963 |
+
re_predictions=re_predictions,
|
964 |
+
)
|
965 |
+
|
966 |
+
if (
|
967 |
+
start_labels is not None
|
968 |
+
and end_labels is not None
|
969 |
+
and relation_labels is not None
|
970 |
+
and is_prediction is False
|
971 |
+
):
|
972 |
+
ned_start_loss = self.compute_loss(ned_start_logits, ned_start_labels)
|
973 |
+
end_labels[end_labels > 0] = 1
|
974 |
+
ned_end_loss = self.compute_loss(ned_end_logits, end_labels)
|
975 |
+
if self.config.entity_type_loss or self.relation_disambiguation_loss:
|
976 |
+
ned_type_loss = self.compute_ned_type_loss(
|
977 |
+
disambiguation_labels,
|
978 |
+
re_ned_entities_logits,
|
979 |
+
ned_type_logits,
|
980 |
+
re_entities_logits,
|
981 |
+
entity_types,
|
982 |
+
(model_subject_features != -100).all(2),
|
983 |
+
)
|
984 |
+
relation_loss = self.compute_relation_loss(relation_labels, re_logits)
|
985 |
+
# compute loss. We can skip the relation loss if we are in the first epochs (optional)
|
986 |
+
if self.config.entity_type_loss or self.relation_disambiguation_loss:
|
987 |
+
output_dict["loss"] = (
|
988 |
+
ned_start_loss + ned_end_loss + relation_loss + ned_type_loss
|
989 |
+
) / 4
|
990 |
+
output_dict["ned_type_loss"] = ned_type_loss
|
991 |
+
else:
|
992 |
+
output_dict["loss"] = ((1 / 20) * (ned_start_loss + ned_end_loss)) + (
|
993 |
+
(9 / 10) * relation_loss
|
994 |
+
)
|
995 |
+
output_dict["ned_start_loss"] = ned_start_loss
|
996 |
+
output_dict["ned_end_loss"] = ned_end_loss
|
997 |
+
output_dict["re_loss"] = relation_loss
|
998 |
+
|
999 |
+
return output_dict
|