| Challenge: | Existing work on learning contextual representations has used LSTM-based biLMs, but there is no reason to believe this is effective. |
| Approach: | They propose to use pre-trained bidirectional language models to learn contextual word embeddings for four NLP tasks and to use them to study the effects of architecture on endtask accuracy. |
| Outcome: | The proposed models outperform word embeddings for four NLP tasks and all learn representations that vary with network depth. |
Similar Papers
Deep Contextualized Word Representations (N18-1)
Copied to clipboard
Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, Luke Zettlemoyer
| Challenge: | a new type of deep contextualized word representation is proposed for language understanding problems . word vectors are learned functions of the internal states of a deep bidirectional language model . |
| Approach: | They propose a new type of deep contextualized word representation that models complex features of word use and how they vary across linguistic contexts. |
| Outcome: | The proposed representations improve the state of the art across six challenging NLP problems. |
Similarity Analysis of Contextual Word Representation Models (2020.acl-main)
Copied to clipboard
| Challenge: | Existing and novel similarity measures are used to analyze contextual word representations . different architectures have rather similar representations, but different individual neurons. |
| Approach: | They propose a method to analyze contextual word representation models using similarity analysis. |
| Outcome: | The proposed approach can be used to analyze model similarity without external annotations. |
Contextualized Word Representations for Reading Comprehension (N18-2)
Copied to clipboard
| Challenge: | Reading comprehension (RC) is a high-level task in natural language understanding that requires reading a document and answering questions about its content. |
| Approach: | They propose to provide a standard neural network for reading a document and answering a question about its content. |
| Outcome: | The proposed model improves on the competitive SQuAD dataset by providing rich contextualized word representations and allowing it to choose between context-dependent and context-independent representations. |
How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings (D19-1)
Copied to clipboard
| Challenge: | Existing word embeddings were static, requiring all senses of a polysemous word to share the same representation. |
| Approach: | They found that the contextualized representations of all words are not isotropic in any layer of the contextualizing model. |
| Outcome: | The results show that the representations of all words are not isotropic in any layer of the contextualizing model. |
Language Modelling Makes Sense: Propagating Representations through WordNet for Full-Coverage Word Sense Disambiguation (P19-1)
Copied to clipboard
| Challenge: | Contextual embeddings address the problem of meaning conflation hampering word embeddables. |
| Approach: | They propose a method that creates sense-level embeddings with full-coverage of WordNet without recourse to explicit sense distributions or task-specific modelling. |
| Outcome: | The proposed method surpasses previous systems using powerful models and is robust when ignoring part-of-speech and lemma features. |
Putting Words in Context: LSTM Language Models and Lexical Ambiguity (P19-1)
Copied to clipboard
| Challenge: | In language, a word can contribute a very different meaning depending on the context . lexical ambiguity involves both morphosyntactic and semantic aspects . |
| Approach: | They propose a method to probe hidden representations for lexical and contextual information about words. |
| Outcome: | The proposed method shows that both types of information are represented to a large extent, but there is room for improvement for contextual information. |
Learning Better Internal Structure of Words for Sequence Labeling (D18-1)
Copied to clipboard
| Challenge: | a gap exists between methods for learning representations of sentences and words . authors propose a convolutional neural architecture with no down-sampling for learning words based on character embeddings . |
| Approach: | They propose a funnel-shaped wide convolutional neural architecture with no down-sampling for learning words' internal structure. |
| Outcome: | The proposed model outperforms other character embedding models on six sequence labeling datasets. |
How to represent a word and predict it, too: Improving tied architectures for language modelling (D18-1)
Copied to clipboard
| Challenge: | Recent state-of-the-art models use word embeddings as input and output mappings instead of tied models. |
| Approach: | They propose to decouple hidden state from word embedding prediction . they extend their proposed modification to word2vec models . |
| Outcome: | The proposed architectures achieve comparable or better results compared to previous models without tying . the proposed architecture reduces parameters, enabling more compact models and faster learning. |
Rethinking Complex Neural Network Architectures for Document Classification (N19-1)
Copied to clipboard
| Challenge: | Neural network models for many NLP tasks have grown increasingly complex in recent years . authors of recent papers question the necessity of such architectures and find them quite effective . |
| Approach: | They propose to use regularization techniques borrowed from language modeling to improve model accuracy . they find that a simple biLSTM architecture with appropriate regularization yields competitive results . |
| Outcome: | a simple biLSTM model outperforms the state-of-the-art on four benchmark datasets . authors say that improvements are not real, but are attributed to mundane reasons . |
Improved Word Sense Disambiguation Using Pre-Trained Contextualized Word Representations (D19-1)
Copied to clipboard
| Challenge: | Contextualized word representations are effective in downstream tasks such as question answering, named entity recognition, and sentiment analysis. |
| Approach: | They propose to integrate pre-trained contextualized word representations into a neural network that captures the whole sentence and the word representation in the sentence. |
| Outcome: | The proposed approach outperforms the state-of-the-art approach that makes use of non-contextualized word embeddings on multiple benchmark WSD datasets. |