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.

Similar Papers

Quantifying the Contextualization of Word Representations with Semantic Class Probing (2020.findings-emnlp)

Copied to clipboard

Challenge: Pretrained language models are effective in solving NLP tasks, but there are still questions about how and why they work so well.
Approach: They use BERT to quantify contextualization by studying the extent of inference . they show that top layer representations support highly accurate inference of semantic classes .
Outcome: The proposed model is highly accurate, but weak in the lower layers . it is more task-specific after finetuning while lower layers are more transferable .
Spying on Your Neighbors: Fine-grained Probing of Contextual Embeddings for Information about Surrounding Words (2020.acl-main)

Copied to clipboard

Challenge: a suite of probing tasks test contextual embeddings for encoding of information about surrounding words . authors: little is known about what information embeddables encode about the context words encode . a recent study shows that contextual embeds can be powerful for many tasks .
Approach: They propose probing tasks that enable fine-grained testing of contextual embeddings . they examine popular contextual encoders and find that each encodes contextual information across tokens a little different .
Outcome: The proposed probing tasks show that word embeddings encode information about words . the tests show that the encoded information is encoded across tokens with near-perfect recoverability .
What Does This Word Mean? Explaining Contextualized Embeddings with Natural Language Definition (D19-1)

Copied to clipboard

Challenge: Contextualized word embeddings have boosted many NLP tasks compared with static word embeds.
Approach: They propose a framework that can explain word meanings given contextualized word embeddings for better interpretation.
Outcome: The proposed framework can explain word meanings given contextualized word embeddings for better interpretation.
Contextual Embeddings: When Are They Worth It? (2020.acl-main)

Copied to clipboard

Challenge: In recent years, rich contextual embeddings have enabled rapid progress on benchmarks like GLUE, but require significant computational resources during pretraining and during downstream task training and inference.
Approach: They empirically compare contextual embeddings with classic pretrained embedders and a random word embeddable with a simple baseline.
Outcome: The proposed models perform within 5 to 10% accuracy on industry-scale data.
Interpreting Pretrained Contextualized Representations via Reductions to Static Embeddings (2020.acl-main)

Copied to clipboard

Challenge: Contextualized representations have become the default for downstream NLP applications.
Approach: They propose a method for converting from contextualized representations to static lookup-table embeddings and apply it to 5 popular pretrained models and 9 sets of pretrained weights.
Outcome: The proposed methods show that pooling over many contexts significantly improves representational quality under intrinsic evaluation.
Linguistic Knowledge and Transferability of Contextual Representations (N19-1)

Copied to clipboard

Challenge: Recent work has explored contextual word representations, which assign each word a vector that is a function of the entire input sequence.
Approach: They compare pretrained word representations with 16 diverse probing tasks to examine their transferability.
Outcome: The pretrained representations are successful across a diverse set of NLP tasks . the models are competitive with state-of-the-art models but fail on fine-grained tasks requiring fine-granular knowledge, the study finds .
Using Paraphrases to Study Properties of Contextual Embeddings (2022.naacl-main)

Copied to clipboard

Challenge: Previously, paraphrases have been used to probe whether compositionality is accurately captured by BERT, but we believe they can be used to explore many other questions.
Approach: They propose to use paraphrases as a unique source of data to analyze contextualized embeddings, with a particular focus on BERT.
Outcome: The proposed analysis of paraphrases and paraphrase representations using the Paraphrase Database shows that BERT handles polysemous words, but different representations in many cases.
Embeddings in Natural Language Processing (2020.coling-tutorials)

Copied to clipboard

Challenge: Embeddings have been a key topic of interest in NLP for the past decade . a quick warm-up introduction to NLP and why it is important to have a semantic comprehension of texts .
Approach: This tutorial will provide a high-level synthesis of the main embedding techniques in NLP . it will start with word embedds and then move to other types of embeddable vectors .
Outcome: This tutorial will provide a high-level synthesis of the main embedding techniques in NLP . it will start with word embedds and move to other types of embeddable representations .
Picking BERT’s Brain: Probing for Linguistic Dependencies in Contextualized Embeddings Using Representational Similarity Analysis (2020.coling-main)

Copied to clipboard

Challenge: Contextualized word embeddings can incorporate contextual information, whereas other embeddables cannot.
Approach: They propose an approach to address this question using Representational Similarity Analysis (RSA) they investigate whether verb embeddings encode verb’s subject, pronoun embedds antecedent and full-sentence representations encode sentence’s head word .
Outcome: The proposed approach can adjudicate between hypotheses about which aspects of context are encoded in representations of language.
Dissecting Contextual Word Embeddings: Architecture and Representation (D18-1)

Copied to clipboard

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations