Add model

README.md

@@ -1,3 +1,259 @@
 ---
+
+language: en
 license: mit
+tags:
+- keyphrase-extraction
+datasets:
+- midas/semeval2017
+metrics:
+- seqeval
+widget:
+- text: "Keyphrase extraction is a technique in text analysis where you extract the important keyphrases from a document. 
+Thanks to these keyphrases humans can understand the content of a text very quickly and easily without reading 
+it completely. Keyphrase extraction was first done primarily by human annotators, who read the text in detail 
+and then wrote down the most important keyphrases. The disadvantage is that if you work with a lot of documents, 
+this process can take a lot of time. 
+
+Here is where Artificial Intelligence comes in. Currently, classical machine learning methods, that use statistical 
+and linguistic features, are widely used for the extraction process. Now with deep learning, it is possible to capture 
+the semantic meaning of a text even better than these classical methods. Classical methods look at the frequency, 
+occurrence and order of words in the text, whereas these neural approaches can capture long-term semantic dependencies 
+and context of words in a text."
+  example_title: "Example 1"
+- text: "In this work, we explore how to learn task specific language models aimed towards learning rich representation of keyphrases from text documents. We experiment with different masking strategies for pre-training transformer language models (LMs) in discriminative as well as generative settings. In the discriminative setting, we introduce a new pre-training objective - Keyphrase Boundary Infilling with Replacement (KBIR), showing large gains in performance (up to 9.26 points in F1) over SOTA, when LM pre-trained using KBIR is fine-tuned for the task of keyphrase extraction. In the generative setting, we introduce a new pre-training setup for BART - KeyBART, that reproduces the keyphrases related to the input text in the CatSeq format, instead of the denoised original input. This also led to gains in performance (up to 4.33 points inF1@M) over SOTA for keyphrase generation. Additionally, we also fine-tune the pre-trained language models on named entity recognition(NER), question answering (QA), relation extraction (RE), abstractive summarization and achieve comparable performance with that of the SOTA, showing that learning rich representation of keyphrases is indeed beneficial for many other fundamental NLP tasks."
+  example_title: "Example 2"
+model-index:
+- name: ml6team/keyphrase-extraction-kbir-semeval2017
+  results:
+  - task: 
+      type: keyphrase-extraction
+      name: Keyphrase Extraction
+    dataset:
+      type: midas/semeval2017
+      name: semeval2017
+    metrics:
+      - type: F1 (Seqeval) 
+        value: 0.000
+        name: F1 (Seqeval)
+      - type: F1@M
+        value: 0.401
+        name: F1@M        
 ---
+# 🔑 Keyphrase Extraction Model: KBIR-semeval2017
+Keyphrase extraction is a technique in text analysis where you extract the important keyphrases from a document. Thanks to these keyphrases humans can understand the content of a text very quickly and easily without reading it completely. Keyphrase extraction was first done primarily by human annotators, who read the text in detail and then wrote down the most important keyphrases. The disadvantage is that if you work with a lot of documents, this process can take a lot of time ⏳. 
+
+Here is where Artificial Intelligence 🤖 comes in. Currently, classical machine learning methods, that use statistical and linguistic features, are widely used for the extraction process. Now with deep learning, it is possible to capture the semantic meaning of a text even better than these classical methods. Classical methods look at the frequency, occurrence and order of words in the text, whereas these neural approaches can capture long-term semantic dependencies and context of words in a text.
+
+
+## 📓 Model Description
+This model uses [KBIR](https://huggingface.co/bloomberg/KBIR) as its base model and fine-tunes it on the [semeval2017 dataset](https://huggingface.co/datasets/midas/semeval2017). KBIR or Keyphrase Boundary Infilling with Replacement is a pre-trained model which utilizes a multi-task learning setup for optimizing a combined loss of Masked Language Modeling (MLM), Keyphrase Boundary Infilling (KBI) and Keyphrase Replacement Classification (KRC).
+You can find more information about the architecture in this [paper](https://arxiv.org/abs/2112.08547).
+
+Keyphrase extraction models are transformer models fine-tuned as a token classification problem where each word in the document is classified as being part of a keyphrase or not.
+
+| Label | Description                     |
+| ----- | ------------------------------- |
+| B-KEY | At the beginning of a keyphrase |
+| I-KEY | Inside a keyphrase              |
+| O     | Outside a keyphrase             |
+
+## ✋ Intended Uses & Limitations
+### 🛑 Limitations
+* This keyphrase extraction model is very domain-specific and will perform very well on abstracts of scientific articles. It's not recommended to use this model for other domains, but you are free to test it out.
+* Limited amount of predicted keyphrases.
+* Only works for English documents.
+* For a custom model, please consult the [training notebook]() for more information.
+
+### ❓ How To Use
+```python
+from transformers import (
+    TokenClassificationPipeline,
+    AutoModelForTokenClassification,
+    AutoTokenizer,
+)
+from transformers.pipelines import AggregationStrategy
+import numpy as np
+
+# Define keyphrase extraction pipeline
+class KeyphraseExtractionPipeline(TokenClassificationPipeline):
+    def __init__(self, model, *args, **kwargs):
+        super().__init__(
+            model=AutoModelForTokenClassification.from_pretrained(model),
+            tokenizer=AutoTokenizer.from_pretrained(model),
+            *args,
+            **kwargs
+        )
+
+    def postprocess(self, model_outputs):
+        results = super().postprocess(
+            model_outputs=model_outputs,
+            aggregation_strategy=AggregationStrategy.SIMPLE,
+        )
+        return np.unique([result.get("word").strip() for result in results])
+
+```
+
+```python
+# Load pipeline
+model_name = "ml6team/keyphrase-extraction-kbir-semeval2017"
+extractor = KeyphraseExtractionPipeline(model=model_name)
+```
+```python
+# Inference
+text = """
+Keyphrase extraction is a technique in text analysis where you extract the
+important keyphrases from a document. Thanks to these keyphrases humans can
+understand the content of a text very quickly and easily without reading it
+completely. Keyphrase extraction was first done primarily by human annotators,
+who read the text in detail and then wrote down the most important keyphrases.
+The disadvantage is that if you work with a lot of documents, this process
+can take a lot of time. 
+
+Here is where Artificial Intelligence comes in. Currently, classical machine
+learning methods, that use statistical and linguistic features, are widely used
+for the extraction process. Now with deep learning, it is possible to capture
+the semantic meaning of a text even better than these classical methods.
+Classical methods look at the frequency, occurrence and order of words
+in the text, whereas these neural approaches can capture long-term
+semantic dependencies and context of words in a text.
+""".replace("\n", " ")
+
+keyphrases = extractor(text)
+
+print(keyphrases)
+
+```
+
+```
+# Output
+['artificial intelligence']
+```
+
+## 📚 Training Dataset
+[Semeval2017](https://huggingface.co/datasets/midas/semeval2017) is a keyphrase extraction/generation dataset consisting of 500 English scientific paper abstracts from the ScienceDirect open access publications.  from NY Times and 10K from JPTimes and annotated by professional indexers or editors. The selected articles were evenly distributed among the domains of Computer Science, Material Sciences and Physics. Each paper has a set of keyphrases annotated by student volunteers. Each paper was double-annotated, where the second annotation was done by an expert annotator.
+
+You can find more information in the [paper](https://arxiv.org/abs/1704.02853).
+
+## 👷‍♂️ Training procedure
+For more in detail information, you can take a look at the [training notebook]().
+
+### Training parameters
+
+| Parameter | Value |
+| --------- | ------|
+| Learning Rate | 1e-4 |
+| Epochs | 50 |
+| Early Stopping Patience | 3 |
+
+### Preprocessing
+The documents in the dataset are already preprocessed into list of words with the corresponding labels. The only thing that must be done is tokenization and the realignment of the labels so that they correspond with the right subword tokens.
+
+```python
+from datasets import load_dataset
+from transformers import AutoTokenizer
+
+# Labels
+label_list = ["B", "I", "O"]
+lbl2idx = {"B": 0, "I": 1, "O": 2}
+idx2label = {0: "B", 1: "I", 2: "O"}
+
+# Tokenizer
+tokenizer = AutoTokenizer.from_pretrained("bloomberg/KBIR")
+max_length = 512
+
+# Dataset parameters
+dataset_full_name = "midas/semeval2017"
+dataset_subset = "raw"
+dataset_document_column = "document"
+dataset_biotags_column = "doc_bio_tags"
+
+def preprocess_fuction(all_samples_per_split):
+    tokenized_samples = tokenizer.batch_encode_plus(
+        all_samples_per_split[dataset_document_column],
+        padding="max_length",
+        truncation=True,
+        is_split_into_words=True,
+        max_length=max_length,
+    )
+    total_adjusted_labels = []
+    for k in range(0, len(tokenized_samples["input_ids"])):
+        prev_wid = -1
+        word_ids_list = tokenized_samples.word_ids(batch_index=k)
+        existing_label_ids = all_samples_per_split[dataset_biotags_column][k]
+        i = -1
+        adjusted_label_ids = []
+
+        for wid in word_ids_list:
+            if wid is None:
+                adjusted_label_ids.append(lbl2idx["O"])
+            elif wid != prev_wid:
+                i = i + 1
+                adjusted_label_ids.append(lbl2idx[existing_label_ids[i]])
+                prev_wid = wid
+            else:
+                adjusted_label_ids.append(
+                    lbl2idx[
+                        f"{'I' if existing_label_ids[i] == 'B' else existing_label_ids[i]}"
+                    ]
+                )
+
+        total_adjusted_labels.append(adjusted_label_ids)
+    tokenized_samples["labels"] = total_adjusted_labels
+    return tokenized_samples
+
+# Load dataset
+dataset = load_dataset(dataset_full_name, dataset_subset)
+
+# Preprocess dataset
+tokenized_dataset = dataset.map(preprocess_fuction, batched=True)
+    
+```
+
+### Postprocessing (Without Pipeline Function)
+If you do not use the pipeline function, you must filter out the B and I labeled tokens. Each B and I will then be merged into a keyphrase. Finally, you need to strip the keyphrases to make sure all unnecessary spaces have been removed.
+```python
+# Define post_process functions
+def concat_tokens_by_tag(keyphrases):
+    keyphrase_tokens = []
+    for id, label in keyphrases:
+        if label == "B":
+            keyphrase_tokens.append([id])
+        elif label == "I":
+            if len(keyphrase_tokens) > 0:
+                keyphrase_tokens[len(keyphrase_tokens) - 1].append(id)
+    return keyphrase_tokens
+
+
+def extract_keyphrases(example, predictions, tokenizer, index=0):
+    keyphrases_list = [
+        (id, idx2label[label])
+        for id, label in zip(
+            np.array(example["input_ids"]).squeeze().tolist(), predictions[index]
+        )
+        if idx2label[label] in ["B", "I"]
+    ]
+
+    processed_keyphrases = concat_tokens_by_tag(keyphrases_list)
+    extracted_kps = tokenizer.batch_decode(
+        processed_keyphrases,
+        skip_special_tokens=True,
+        clean_up_tokenization_spaces=True,
+    )
+    return np.unique([kp.strip() for kp in extracted_kps])
+
+```
+
+## 📝 Evaluation Results
+
+Traditional evaluation methods are the precision, recall and F1-score @k,m where k is the number that stands for the first k predicted keyphrases and m for the average amount of predicted keyphrases.
+The model achieves the following results on the Semeval2017 test set:
+
+| Dataset               | P@5  | R@5  | F1@5 | P@10 | R@10 | F1@10 | P@M  | R@M  | F1@M |
+|:---------------------:|:----:|:----:|:----:|:----:|:----:|:-----:|:----:|:----:|:----:|
+| Semeval2017 Test Set  | 0.41 | 0.20 | 0.25 | 0.37 | 0.34 | 0.34  | 0.36 | 0.50 | 0.40 |
+
+For more information on the evaluation process, you can take a look at the keyphrase extraction [evaluation notebook]().
+
+## 🚨 Issues
+Please feel free to start discussions in the Community Tab.

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "bloomberg/KBIR",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "B-KEY",
+    "1": "I-KEY",
+    "2": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-KEY": 0,
+    "I-KEY": 1,
+    "O": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a1b44206d2c0596246fe574d2a33ea5eb7c5ea0512b5f27e3cee15a1baf4c4b
+size 1417389425

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": true, "trim_offsets": true, "use_fast": true, "max_length": 512, "special_tokens_map_file": null, "name_or_path": "bloomberg/KBIR", "tokenizer_class": "RobertaTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acfbe5d9b9acbbe59f5955fcd403ef2957a5406d4042431a93ebe335775e8e3d
+size 3119