Challenge: Using English lexical stimuli, we find that BERT models show "priming" predicting a word with greater probability when the context includes a related word versus an unrelated one.
Approach: They analyze a pre-trained BERT model with tests informed by semantic priming . they find that BERT too shows "priming" predicting a word with greater probability when context includes a related word versus an unrelated one.
Outcome: The proposed model shows a tendency to be distracted by related prime words as context becomes more informative, and lower probability of related words.

Similar Papers

Measuring Context-Word Biases in Lexical Semantic Datasets (2022.emnlp-main)

Copied to clipboard

Challenge: Existing pretrained contextualized models have been used to evaluate word-in-context representations in many lexical semantic tasks.
Approach: They propose to quantify the degree of context or word biases in existing datasets by probing masked input.
Outcome: The proposed model performs better when both word and context are available than with masked input.
What BERT Is Not: Lessons from a New Suite of Psycholinguistic Diagnostics for Language Models (2020.tacl-1)

Copied to clipboard

Challenge: Pretraining by language modeling has become popular but we have yet to understand what language models learn during that process.
Approach: They propose diagnostics that ask questions about information used by language models for generating predictions in context.
Outcome: The proposed diagnostics can be used to study the popular BERT model . they show that the model can distinguish good from bad completions, but struggles with inference and role-based event prediction.
Speakers Fill Lexical Semantic Gaps with Context (2020.emnlp-main)

Copied to clipboard

Challenge: Lexical ambiguity is widespread in language, allowing for the reuse of economical word forms and thus making language more efficient.
Approach: They propose two ways to estimate lexical ambiguity as the entropy of meanings a word can take . they validate this hypothesis by using WordNet and BERT .
Outcome: The proposed method shows that on six high-resource languages, there are significant correlations between the estimate and the number of synonyms a word has in WordNet.
Probe-Less Probing of BERT’s Layer-Wise Linguistic Knowledge with Masked Word Prediction (2022.naacl-srw)

Copied to clipboard

Challenge: Among studies on localization of linguistic knowledge, it is unclear what information is encoded in each layer.
Approach: They analyze BERT’s layer-wise masked word prediction on an English corpus and find syntactic and semantic information is encoded at different layers for words of different syntaktic categories.
Outcome: The proposed model outperforms state-of-the-art models in many downstream tasks.
Context versus Prior Knowledge in Language Models (2024.acl-long)

Copied to clipboard

Challenge: Existing studies have investigated how often a model will rely on prior knowledge over conflicting contextual information in answering questions.
Approach: They propose two mutual information-based metrics to measure a model’s dependency on a context and on its prior about an entity.
Outcome: The proposed metrics show that language models can integrate prior knowledge and new information in a predictable way across different questions and contexts.
Explaining Contextualization in Language Models using Visual Analytics (2021.acl-long)

Copied to clipboard

Challenge: Contextualized language models (LMs) have learned highly transferable and task-agnostic properties of language, even to a degree of imitating the classical NLP pipeline.
Approach: They propose to use an existing similarity-based score to measure contextualization and integrate it into a visual analytics technique that combines the model's layers simultaneously and highlighting intra-layer properties and inter-layer differences.
Outcome: The proposed approach combines linguistically-informed insights with scoring and visual analytics to show that contextualization is neither driven by polysemy nor by pure context variation.
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.
Do Language Models Exhibit Human-like Structural Priming Effects? (2024.findings-acl)

Copied to clipboard

Challenge: a recent exposure to a structure facilitates processing of the same structure, a study finds . structural priming is well attested in humans, for both language production and comprehension .
Approach: They use the structural priming paradigm to investigate where priming effects manifest . they find that rarer elements within a prime increase priming effect .
Outcome: The findings provide an important piece in the puzzle of understanding how properties within their context affect structural prediction in language models.
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 .
Improving Contextual Representation with Gloss Regularized Pre-training (2022.findings-naacl)

Copied to clipboard

Challenge: Experimental results show that the gloss regularizer module enhances word semantic similarity in pre-training.
Approach: They propose an auxiliary gloss regularizer module to BERT pre-training to enhance word semantic similarity.
Outcome: The proposed model improves word similarity in word-level and sentence-level representation.

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