What do Language Models know about word senses? Zero-Shot WSD with Language Models and Domain Inventories

• URL: http://arxiv.org/abs/2302.03353v1
• Date: Tue, 7 Feb 2023 09:55:07 GMT
• Title: What do Language Models know about word senses? Zero-Shot WSD with Language Models and Domain Inventories
• Authors: Oscar Sainz, Oier Lopez de Lacalle, Eneko Agirre and German Rigau
• Abstract summary: We aim to explore to what extent language models are capable of discerning among senses at inference time. We leverage the relation between word senses and domains, and cast Word Sense Disambiguation (WSD) as a textual entailment problem. Our results show that this approach is indeed effective, close to supervised systems.
• Score: 23.623074512572593
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Language Models are the core for almost any Natural Language Processing system nowadays. One of their particularities is their contextualized representations, a game changer feature when a disambiguation between word senses is necessary. In this paper we aim to explore to what extent language models are capable of discerning among senses at inference time. We performed this analysis by prompting commonly used Languages Models such as BERT or RoBERTa to perform the task of Word Sense Disambiguation (WSD). We leverage the relation between word senses and domains, and cast WSD as a textual entailment problem, where the different hypothesis refer to the domains of the word senses. Our results show that this approach is indeed effective, close to supervised systems.

Related papers

• Word Sense Disambiguation in Native Spanish: A Comprehensive Lexical Evaluation Resource [2.7775559369441964]
  A lexical meaning of a word in context can be determined automatically by Word Sense Disambiguation (WSD) algorithms. This study introduces a new resource for Spanish WSD. It includes a sense inventory and a lexical dataset sourced from the Diccionario de la Lengua Espanola.
  arXiv  Detail & Related papers  (2024-09-30T17:22:33Z)
• Word sense extension [8.939269057094661]
  We present a paradigm of word sense extension (WSE) that enables words to spawn new senses toward novel context. We develop a framework that simulates novel word sense extension by partitioning a polysemous word type into two pseudo-tokens that mark its different senses. Our framework combines cognitive models of chaining with a learning scheme that transforms a language model embedding space to support various types of word sense extension.
  arXiv  Detail & Related papers  (2023-06-09T00:54:21Z)
• A Linguistic Investigation of Machine Learning based Contradiction Detection Models: An Empirical Analysis and Future Perspectives [0.34998703934432673]
  We analyze two Natural Language Inference data sets with respect to their linguistic features. The goal is to identify those syntactic and semantic properties that are particularly hard to comprehend for a machine learning model.
  arXiv  Detail & Related papers  (2022-10-19T10:06:03Z)
• Transparency Helps Reveal When Language Models Learn Meaning [71.96920839263457]
  Our systematic experiments with synthetic data reveal that, with languages where all expressions have context-independent denotations, both autoregressive and masked language models learn to emulate semantic relations between expressions. Turning to natural language, our experiments with a specific phenomenon -- referential opacity -- add to the growing body of evidence that current language models do not well-represent natural language semantics.
  arXiv  Detail & Related papers  (2022-10-14T02:35:19Z)
• Multilingual Word Sense Disambiguation with Unified Sense Representation [55.3061179361177]
  We propose building knowledge and supervised-based Multilingual Word Sense Disambiguation (MWSD) systems. We build unified sense representations for multiple languages and address the annotation scarcity problem for MWSD by transferring annotations from rich-sourced languages to poorer ones. Evaluations of SemEval-13 and SemEval-15 datasets demonstrate the effectiveness of our methodology.
  arXiv  Detail & Related papers  (2022-10-14T01:24:03Z)
• BERT Has Uncommon Sense: Similarity Ranking for Word Sense BERTology [11.650381752104298]
  We investigate how well contextualized word embedding models can represent different word senses. We find that several popular CWE models all outperform a random baseline even for proportionally rare senses, without explicit sense supervision.
  arXiv  Detail & Related papers  (2021-09-20T18:15:26Z)
• Sense representations for Portuguese: experiments with sense embeddings and deep neural language models [0.0]
  Unsupervised sense representations can induce different senses of a word by analyzing its contextual semantics in a text. We present the first experiments carried out for generating sense embeddings for Portuguese.
  arXiv  Detail & Related papers  (2021-08-31T18:07:01Z)
• Towards Zero-shot Language Modeling [90.80124496312274]
  We construct a neural model that is inductively biased towards learning human languages. We infer this distribution from a sample of typologically diverse training languages. We harness additional language-specific side information as distant supervision for held-out languages.
  arXiv  Detail & Related papers  (2021-08-06T23:49:18Z)
• Moving Down the Long Tail of Word Sense Disambiguation with Gloss-Informed Biencoders [79.38278330678965]
  A major obstacle in Word Sense Disambiguation (WSD) is that word senses are not uniformly distributed. We propose a bi-encoder model that independently embeds (1) the target word with its surrounding context and (2) the dictionary definition, or gloss, of each sense.
  arXiv  Detail & Related papers  (2020-05-06T04:21:45Z)
• Semantics-Aware Inferential Network for Natural Language Understanding [79.70497178043368]
  We propose a Semantics-Aware Inferential Network (SAIN) to meet such a motivation. Taking explicit contextualized semantics as a complementary input, the inferential module of SAIN enables a series of reasoning steps over semantic clues. Our model achieves significant improvement on 11 tasks including machine reading comprehension and natural language inference.
  arXiv  Detail & Related papers  (2020-04-28T07:24:43Z)
• Word Sense Disambiguation for 158 Languages using Word Embeddings Only [80.79437083582643]
  Disambiguation of word senses in context is easy for humans, but a major challenge for automatic approaches. We present a method that takes as input a standard pre-trained word embedding model and induces a fully-fledged word sense inventory. We use this method to induce a collection of sense inventories for 158 languages on the basis of the original pre-trained fastText word embeddings.
  arXiv  Detail & Related papers  (2020-03-14T14:50:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.