Papers with Word Sense Induction
Topology of Word Embeddings: Singularities Reflect Polysemy (2020.starsem-1)
Copied to clipboard
| Challenge: | a new study suggests that word vectors live on a submanifold within their ambient vector space . a manifold hypothesis suggests that vectors should live on pinched manifels . |
| Approach: | They propose a topological measure of polysemy that correlates well with the actual number of meanings of a word. |
| Outcome: | The proposed method produces competitive results for a word Sense Induction & Disambiguation task. |
To Word Senses and Beyond: Inducing Concepts with Contextualized Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Word Sense Disambiguiation and Word sense Induction are considered independent problems, but they are often neglected in practice. |
| Approach: | They propose an unsupervised task of learning a soft clustering amongwords that defines a set of concepts directly from data. |
| Outcome: | The proposed approach leverages both a local and global cross-lexicon view to induce concepts and also senses in the context of the proposed task. |
A Systematic Comparison of Contextualized Word Embeddings for Lexical Semantic Change (2024.naacl-long)
Copied to clipboard
| Challenge: | Contextualized embeddings are the preferred tool for modeling Lexical Semantic Change (LSC) current evaluations focus on a specific task known as Graded Change Detection (GCD) however, performance comparisons between different approaches are often misleading due to diverse settings. |
| Approach: | They evaluate the performance of contextualized embeddings for Lexical Semantic Change (LSC) they break the problem into Word-in-Context (WiC) and Word Sense Induction (WSI) tasks . |
| Outcome: | The proposed model outperforms other models on eight available benchmarks for Lexical Semantic Change (LSC) while comparable to GPT-4. |
Word Sense Induction with Neural biLM and Symmetric Patterns (D18-1)
Copied to clipboard
| Challenge: | Existing methods for word sense induction use a language model to predict probable substitutes for target words. |
| Approach: | They propose to use a language model to predict probable substitutes for target words . they replace the ngram-based language model with a recurrent model to generate strong substitute vectors . |
| Outcome: | The proposed method surpasses the current state-of-the-art on the SemEval 2013 task by a large margin. |
Automatically Generated Definitions and their utility for Modeling Word Meaning (2024.emnlp-main)
Copied to clipboard
| Challenge: | Modern language models generate semantic representations for words based on context and context based models. |
| Approach: | They propose to use dictionary-like sense definitions to generate sentence embeddings . they evaluate the quality of the generated definitions on existing English benchmarks based on the results of their study . |
| Outcome: | The proposed model sets new state-of-the-art results on lexical semantics tasks compared to baselines . |
Multilingual Substitution-based Word Sense Induction (2024.lrec-main)
Copied to clipboard
| Challenge: | Word Sense Induction is the task of finding senses of an ambiguous word . many approaches to WSI are language-specific and are not easily adaptable to new languages. |
| Approach: | They propose to use multilingual substitution-based WSI methods that generalize to any language supported by the underlying multilingual language model with minimal to no adaptation required. |
| Outcome: | The proposed methods perform on par with monolingual approaches on popular English datasets while being language-specific. |