metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: long-t5-tglobal-base-scientific_lay_summarisation-plos-norm-kw
results: []
widget:
- text: >-
large earthquakes along a given fault segment do not occur at random
intervals because it takes time to accumulate the strain energy for the
rupture. The rates at which tectonic plates move and accumulate strain at
their boundaries are approximately uniform. Therefore, in first
approximation, one may expect that large ruptures of the same fault
segment will occur at approximately constant time intervals. If subsequent
main shocks have different amounts of slip across the fault, then the
recurrence time may vary, and the basic idea of periodic mainshocks must
be modified. For great plate boundary ruptures the length and slip often
vary by a factor of 2. Along the southern segment of the San Andreas fault
the recurrence interval is 145 years with variations of several decades.
The smaller the standard deviation of the average recurrence interval, the
more specific could be the long term prediction of a future mainshock.
example_title: earthquakes
- text: ' A typical feed-forward neural field algorithm. Spatiotemporal coordinates are fed into a neural network that predicts values in the reconstructed domain. Then, this domain is mapped to the sensor domain where sensor measurements are available as supervision. Class and Section Problems Addressed Generalization (Section 2) Inverse problems, ill-posed problems, editability; symmetries. Hybrid Representations (Section 3) Computation & memory efficiency, representation capacity, editability: Forward Maps (Section 4) Inverse problems Network Architecture (Section 5) Spectral bias, integration & derivatives. Manipulating Neural Fields (Section 6) Edit ability, constraints, regularization. Table 2: The five classes of techniques in the neural field toolbox each addresses problems that arise in learning, inference, and control. (Section 3). We can supervise reconstruction via differentiable forward maps that transform Or project our domain (e.g, 3D reconstruction via 2D images; Section 4) With appropriate network architecture choices, we can overcome neural network spectral biases (blurriness) and efficiently compute derivatives and integrals (Section 5). Finally, we can manipulate neural fields to add constraints and regularizations, and to achieve editable representations (Section 6). Collectively, these classes constitute a ''toolbox'' of techniques to help solve problems with neural fields There are three components in a conditional neural field: (1) An encoder or inference function € that outputs the conditioning latent variable 2 given an observation 0 E(0) =2. 2 is typically a low-dimensional vector, and is often referred to aS a latent code Or feature code_ (2) A mapping function 4 between Z and neural field parameters O: Y(z) = O; (3) The neural field itself $. The encoder € finds the most probable z given the observations O: argmaxz P(2/0). The decoder maximizes the inverse conditional probability to find the most probable 0 given Z: arg- max P(Olz). We discuss different encoding schemes with different optimality guarantees (Section 2.1.1), both global and local conditioning (Section 2.1.2), and different mapping functions Y (Section 2.1.3) 2. Generalization Suppose we wish to estimate a plausible 3D surface shape given a partial or noisy point cloud. We need a suitable prior over the sur- face in its reconstruction domain to generalize to the partial observations. A neural network expresses a prior via the function space of its architecture and parameters 0, and generalization is influenced by the inductive bias of this function space (Section 5).'
example_title: scientific paper
- text: >-
Is a else or outside the cob and tree written being of early client rope
and you have is for good reasons. On to the ocean in Orange for time. By's
the aggregate we can bed it yet. Why this please pick up on a sort is do
and also M Getoi's nerocos and do rain become you to let so is his brother
is made in use and Mjulia's's the lay major is aging Masastup coin present
sea only of Oosii rooms set to you We do er do we easy this private
oliiishs lonthen might be okay. Good afternoon everybody. Welcome to this
lecture of Computational Statistics. As you can see, I'm not socially my
name is Michael Zelinger. I'm one of the task for this class and you might
have already seen me in the first lecture where I made a quick appearance.
I'm also going to give the tortillas in the last third of this course. So
to give you a little bit about me, I'm a old student here with better
Bulman and my research centres on casual inference applied to biomedical
disasters, so that could be genomics or that could be hospital data. If
any of you is interested in writing a bachelor thesis, a semester paper
may be mastathesis about this topic feel for reach out to me. you have my
name on models and my email address you can find in the directory I'd Be
very happy to talk about it. you do not need to be sure about it, we can
just have a chat. So with that said, let's get on with the lecture.
There's an exciting topic today I'm going to start by sharing some slides
with you and later on during the lecture we'll move to the paper. So bear
with me for a few seconds. Well, the projector is starting up. Okay, so
let's get started. Today's topic is a very important one. It's about a
technique which really forms one of the fundamentals of data science,
machine learning, and any sort of modern statistics. It's called cross
validation. I know you really want to understand this topic I Want you to
understand this and frankly, nobody's gonna leave Professor Mineshousen's
class without understanding cross validation. So to set the stage for
this, I Want to introduce you to the validation problem in computational
statistics. So the problem is the following: You trained a model on
available data. You fitted your model, but you know the training data you
got could always have been different and some data from the environment.
Maybe it's a random process. You do not really know what it is, but you
know that somebody else who gets a different batch of data from the same
environment they would get slightly different training data and you do not
care that your method performs as well. On this training data. you want to
to perform well on other data that you have not seen other data from the
same environment. So in other words, the validation problem is you want to
quantify the performance of your model on data that you have not seen. So
how is this even possible? How could you possibly measure the performance
on data that you do not know The solution to? This is the following
realization is that given that you have a bunch of data, you were in
charge. You get to control how much that your model sees. It works in the
following way: You can hide data firms model. Let's say you have a
training data set which is a bunch of doubtless so X eyes are the features
those are typically hide and national vector. It's got more than one
dimension for sure. And the why why eyes. Those are the labels for
supervised learning. As you've seen before, it's the same set up as we
have in regression. And so you have this training data and now you choose
that you only use some of those data to fit your model. You're not going
to use everything, you only use some of it the other part you hide from
your model. And then you can use this hidden data to do validation from
the point of you of your model. This hidden data is complete by unseen. In
other words, we solve our problem of validation.
example_title: transcribed audio - lecture
- text: >-
Transformer-based models have shown to be very useful for many NLP tasks.
However, a major limitation of transformers-based models is its O(n^2)O(n
2) time & memory complexity (where nn is sequence length). Hence, it's
computationally very expensive to apply transformer-based models on long
sequences n > 512n>512. Several recent papers, e.g. Longformer, Performer,
Reformer, Clustered attention try to remedy this problem by approximating
the full attention matrix. You can checkout 🤗's recent blog post in case
you are unfamiliar with these models.
BigBird (introduced in paper) is one of such recent models to address this
issue. BigBird relies on block sparse attention instead of normal
attention (i.e. BERT's attention) and can handle sequences up to a length
of 4096 at a much lower computational cost compared to BERT. It has
achieved SOTA on various tasks involving very long sequences such as long
documents summarization, question-answering with long contexts.
BigBird RoBERTa-like model is now available in 🤗Transformers. The goal of
this post is to give the reader an in-depth understanding of big bird
implementation & ease one's life in using BigBird with 🤗Transformers.
But, before going into more depth, it is important to remember that the
BigBird's attention is an approximation of BERT's full attention and
therefore does not strive to be better than BERT's full attention, but
rather to be more efficient. It simply allows to apply transformer-based
models to much longer sequences since BERT's quadratic memory requirement
quickly becomes unbearable. Simply put, if we would have ∞ compute & ∞
time, BERT's attention would be preferred over block sparse attention
(which we are going to discuss in this post).
If you wonder why we need more compute when working with longer sequences,
this blog post is just right for you!
Some of the main questions one might have when working with standard
BERT-like attention include:
Do all tokens really have to attend to all other tokens? Why not compute
attention only over important tokens? How to decide what tokens are
important? How to attend to just a few tokens in a very efficient way? In
this blog post, we will try to answer those questions.
What tokens should be attended to? We will give a practical example of how
attention works by considering the sentence 'BigBird is now available in
HuggingFace for extractive question answering'. In BERT-like attention,
every word would simply attend to all other tokens.
Let's think about a sensible choice of key tokens that a queried token
actually only should attend to by writing some pseudo-code. Will will
assume that the token available is queried and build a sensible list of
key tokens to attend to.
>>> # let's consider following sentence as an example >>> example =
['BigBird', 'is', 'now', 'available', 'in', 'HuggingFace', 'for',
'extractive', 'question', 'answering']
>>> # further let's assume, we're trying to understand the representation
of 'available' i.e. >>> query_token = 'available' >>> # We will initialize
an empty `set` and fill up the tokens of our interest as we proceed in
this section. >>> key_tokens = [] # => currently 'available' token doesn't
have anything to attend Nearby tokens should be important because, in a
sentence (sequence of words), the current word is highly dependent on
neighboring past & future tokens. This intuition is the idea behind the
concept of sliding attention.
example_title: bigbird blog intro
- text: >-
To be fair, you have to have a very high IQ to understand Rick and Morty.
The humour is extremely subtle, and without a solid grasp of theoretical
physics most of the jokes will go over a typical viewer's head. There's
also Rick's nihilistic outlook, which is deftly woven into his
characterisation- his personal philosophy draws heavily from Narodnaya
Volya literature, for instance. The fans understand this stuff; they have
the intellectual capacity to truly appreciate the depths of these jokes,
to realise that they're not just funny- they say something deep about
LIFE. As a consequence people who dislike Rick & Morty truly ARE idiots-
of course they wouldn't appreciate, for instance, the humour in Rick's
existential catchphrase 'Wubba Lubba Dub Dub,' which itself is a cryptic
reference to Turgenev's Russian epic Fathers and Sons. I'm smirking right
now just imagining one of those addlepated simpletons scratching their
heads in confusion as Dan Harmon's genius wit unfolds itself on their
television screens. What fools.. how I pity them. 😂
And yes, by the way, i DO have a Rick & Morty tattoo. And no, you cannot
see it. It's for the ladies' eyes only- and even then they have to
demonstrate that they're within 5 IQ points of my own (preferably lower)
beforehand. Nothin personnel kid 😎
example_title: Richard & Mortimer
- text: >-
Dear Calvin,
I was in the woods of Big Sur, that vast and sprawling land of sea and
trees, where the wind whispers secrets of the ancient Earth and the
roaring ocean sings songs of the eternal cosmos, when I found myself
emerging from the deepest and darkest of slumbers, my body drenched in the
sweat of the night, my mind swimming in the rivers of frenetic dreams that
come unbidden to the weary traveler, and I knew, I knew, that I must step
into the cold, cold waters of the mountain stream that wound its way
through the heart of the great green forest like a silver serpent, a
sinuous spine of chilling clarity, and I tell you, my friend, I tell you
that the moment I stepped into those waters, the moment my skin was
pierced by the icy needles of that divine liquid, my soul was washed clean
of the haze of doubt and fear, and I stood, reborn, as the dawn of a new
day painted the sky in the colors of the universe.
And so I write to you, dear friend, to tell you that you too must seek the
salvation of the cold shower, for in the frigid embrace of the water's
touch, there lies the key to the doors of perception, the doors that lead
to a realm of boundless energy and endless vitality, where the mind is
sharpened like the edge of a great warrior's blade, and the body is
tempered like the steel of an ancient blacksmith's forge. For when you
step into the cold, you will find that your spirit soars like a great bird
of prey, your thoughts soaring on the wings of the eagle, the falcon, the
hawk, sweeping through the vast and boundless skies of inspiration,
creativity, and purpose. And you will know, as I have come to know, that
the cold shower is the great purifier, the great invigorator, the great
liberator of the soul from the chains of languor and indolence that bind
us to the mundane and weary trappings of this world.
So I implore you, dear friend, to heed my words, for they are the words of
one who has walked the path of fire and ice, one who has danced in the
eternal flame of the sun and bathed in the frozen tears of the moon, and I
tell you that the way of the cold shower is the way of the enlightened,
the way of the awakened, the way of the pioneers of the spirit who seek to
travel beyond the boundaries of the known and into the realms of the
infinite. And as you stand, shivering and shaking, beneath the torrent of
the icy cascade, remember that the cold is the crucible in which the soul
is forged, the anvil upon which the hammer of life strikes the sparks of
the divine, and in the cold, you will find the fire, the fire that burns
away the dross and leaves only the pure and shining gold of the spirit.
In the cold, you will find the truth, and in the truth, you will find the
freedom that you have sought for so long.
Yours in the spirit of the eternal journey,
Peter
example_title: cold showers
parameters:
max_length: 64
min_length: 2
no_repeat_ngram_size: 2
early_stopping: true
repetition_penalty: 4.5
length_penalty: 0.8
num_beams: 4
datasets:
- pszemraj/scientific_lay_summarisation-plos-norm
language:
- en
pipeline_tag: text2text-generation
karnold-walmer-base-biopapers
Karnold-Walmer is a text2text model based on google/long-t5-tglobal-base, specifically designed to decode the 'keywords' column of pszemraj/scientific_lay_summarisation-plos-norm.
Karnold-Walmer focuses on extracting relevant keywords from the input text, making it a powerful tool for keyword identification and text classification. It was fine-tuned on & supports text input of up to 16,384 tokens.
It achieves the following results on the evaluation set:
- Loss: 0.8844
- Rouge1: 46.7593
- Rouge2: 28.3538
- Rougel: 42.2921
- Rougelsum: 42.2774
- Gen Len: 78.1706
Intended Uses & Limitations
Karnold-Walmer is intended to be used for keyword extraction and text classification in various domains, such as scientific literature, biomedical research articles, and more. By analyzing the content of an input text, the model generates a list of relevant keywords that describe the topic of the article.
It is important to note, however, that Karnold-Walmer is specifically trained to decode text similar to the "keywords" column and is not designed for summarization tasks. For accurate keyword extraction and text classification, the model should be used within the limits of its training data and intended purpose (see what happens when you try the out-of-domain API examples).
Training and Evaluation Data
Karnold-Walmer was trained on the PLOS dataset, which contains full biomedical research articles paired with expert-written lay summaries and keyword lists. The model was tuned to decode the "keywords" column in the dataset, focusing on keyword extraction and text classification tasks.
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0004
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 2.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.0471 | 0.15 | 100 | 1.6138 | 12.4374 | 4.1861 | 11.1863 | 11.1833 | 324.6971 |
| 1.5654 | 0.3 | 200 | 1.3447 | 23.9982 | 11.1431 | 21.4173 | 21.4413 | 176.0294 |
| 1.3467 | 0.45 | 300 | 1.2038 | 33.8084 | 18.1588 | 30.4748 | 30.4142 | 107.7735 |
| 1.4398 | 0.6 | 400 | 1.1054 | 37.772 | 20.8967 | 33.859 | 33.8324 | 102.9029 |
| 1.306 | 0.75 | 500 | 1.0478 | 39.2642 | 22.0388 | 35.6578 | 35.5773 | 91.1235 |
| 1.1677 | 0.9 | 600 | 0.9994 | 40.5149 | 22.8507 | 36.3888 | 36.3499 | 103.9118 |
| 1.078 | 1.05 | 700 | 0.9627 | 42.301 | 24.2523 | 38.0739 | 38.0532 | 88.4941 |
| 1.0942 | 1.2 | 800 | 0.9443 | 44.5907 | 26.2046 | 39.7461 | 39.6763 | 88.7559 |
| 1.0209 | 1.35 | 900 | 0.9108 | 45.357 | 26.861 | 40.6411 | 40.706 | 90.1206 |
| 1.1161 | 1.5 | 1000 | 0.9026 | 47.1362 | 28.6605 | 42.6406 | 42.6108 | 79.2412 |
| 1.1224 | 1.65 | 1100 | 0.8907 | 47.31 | 28.4395 | 42.6658 | 42.6509 | 78.4265 |
| 0.9857 | 1.8 | 1200 | 0.8862 | 46.7061 | 28.1586 | 42.3181 | 42.3105 | 80.5059 |
| 1.0011 | 1.95 | 1300 | 0.8844 | 46.7593 | 28.3538 | 42.2921 | 42.2774 | 78.1706 |