Open AccessPosted Content
Dissecting Contextual Word Embeddings: Architecture and Representation
TLDR
This article showed that the choice of neural architecture (e.g., LSTM, CNN, or self attention) influences both end task accuracy and qualitative properties of the representations that are learned.Abstract:
Contextual word representations derived from pre-trained bidirectional language models (biLMs) have recently been shown to provide significant improvements to the state of the art for a wide range of NLP tasks. However, many questions remain as to how and why these models are so effective. In this paper, we present a detailed empirical study of how the choice of neural architecture (e.g. LSTM, CNN, or self attention) influences both end task accuracy and qualitative properties of the representations that are learned. We show there is a tradeoff between speed and accuracy, but all architectures learn high quality contextual representations that outperform word embeddings for four challenging NLP tasks. Additionally, all architectures learn representations that vary with network depth, from exclusively morphological based at the word embedding layer through local syntax based in the lower contextual layers to longer range semantics such coreference at the upper layers. Together, these results suggest that unsupervised biLMs, independent of architecture, are learning much more about the structure of language than previously appreciated.read more
Citations
More filters
Proceedings Article
Language Models are Few-Shot Learners
Tom B. Brown,Benjamin Mann,Nick Ryder,Melanie Subbiah,Jared Kaplan,Prafulla Dhariwal,Arvind Neelakantan,Pranav Shyam,Girish Sastry,Amanda Askell,Sandhini Agarwal,Ariel Herbert-Voss,Gretchen Krueger,Thomas Henighan,Rewon Child,Aditya Ramesh,Daniel M. Ziegler,Jeffrey Wu,Clemens Winter,Christopher Hesse,Mark Chen,Eric Sigler,Mateusz Litwin,Scott Gray,Benjamin Chess,Jack Clark,Christopher Berner,Samuel McCandlish,Alec Radford,Ilya Sutskever,Dario Amodei +30 more
TL;DR: GPT-3 achieves strong performance on many NLP datasets, including translation, question-answering, and cloze tasks, as well as several tasks that require on-the-fly reasoning or domain adaptation, such as unscrambling words, using a novel word in a sentence, or performing 3-digit arithmetic.
Proceedings ArticleDOI
BERT Rediscovers the Classical NLP Pipeline
TL;DR: This work finds that the model represents the steps of the traditional NLP pipeline in an interpretable and localizable way, and that the regions responsible for each step appear in the expected sequence: POS tagging, parsing, NER, semantic roles, then coreference.
Proceedings ArticleDOI
What does BERT learn about the structure of language
TL;DR: This work provides novel support for the possibility that BERT networks capture structural information about language by performing a series of experiments to unpack the elements of English language structure learned by BERT.
Proceedings ArticleDOI
A Structural Probe for Finding Syntax in Word Representations
TL;DR: A structural probe is proposed, which evaluates whether syntax trees are embedded in a linear transformation of a neural network’s word representation space, and shows that such transformations exist for both ELMo and BERT but not in baselines, providing evidence that entire syntax Trees are embedded implicitly in deep models’ vector geometry.
Proceedings ArticleDOI
How multilingual is Multilingual BERT
TL;DR: This article showed that M-BERT is surprisingly good at zero-shot cross-lingual model transfer, in which task-specific annotations in one language are used to fine-tune the model for evaluation in another language.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings ArticleDOI
Glove: Global Vectors for Word Representation
TL;DR: A new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods and produces a vector space with meaningful substructure.
Journal Article
Visualizing Data using t-SNE
TL;DR: A new technique called t-SNE that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map, a variation of Stochastic Neighbor Embedding that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map.
Posted Content
Efficient Estimation of Word Representations in Vector Space
TL;DR: This paper proposed two novel model architectures for computing continuous vector representations of words from very large data sets, and the quality of these representations is measured in a word similarity task and the results are compared to the previously best performing techniques based on different types of neural networks.
Proceedings Article
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
TL;DR: This work presents iterative parameter estimation algorithms for conditional random fields and compares the performance of the resulting models to HMMs and MEMMs on synthetic and natural-language data.