Shades of meaning: Uncovering the geometry of ambiguous word representations through contextualised language models

• URL: http://arxiv.org/abs/2304.13597v1
• Date: Wed, 26 Apr 2023 14:47:38 GMT
• Title: Shades of meaning: Uncovering the geometry of ambiguous word representations through contextualised language models
• Authors: Benedetta Cevoli, Chris Watkins, Yang Gao and Kathleen Rastle
• Abstract summary: Lexical ambiguity presents a profound and enduring challenge to the language sciences. Our work offers new insight into psychological understanding of lexical ambiguity through a series of simulations.
• Score: 6.760960482418417
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Lexical ambiguity presents a profound and enduring challenge to the language sciences. Researchers for decades have grappled with the problem of how language users learn, represent and process words with more than one meaning. Our work offers new insight into psychological understanding of lexical ambiguity through a series of simulations that capitalise on recent advances in contextual language models. These models have no grounded understanding of the meanings of words at all; they simply learn to predict words based on the surrounding context provided by other words. Yet, our analyses show that their representations capture fine-grained meaningful distinctions between unambiguous, homonymous, and polysemous words that align with lexicographic classifications and psychological theorising. These findings provide quantitative support for modern psychological conceptualisations of lexical ambiguity and raise new challenges for understanding of the way that contextual information shapes the meanings of words across different timescales.

Related papers

• Pixel Sentence Representation Learning [67.4775296225521]
  In this work, we conceptualize the learning of sentence-level textual semantics as a visual representation learning process. We employ visually-grounded text perturbation methods like typos and word order shuffling, resonating with human cognitive patterns, and enabling perturbation to be perceived as continuous. Our approach is further bolstered by large-scale unsupervised topical alignment training and natural language inference supervision.
  arXiv  Detail & Related papers  (2024-02-13T02:46:45Z)
• LMs stand their Ground: Investigating the Effect of Embodiment in Figurative Language Interpretation by Language Models [0.0]
  Figurative language is a challenge for language models since its interpretation deviates from their conventional order and meaning. Yet, humans can easily understand and interpret metaphors as they can be derived from embodied metaphors. This study shows how larger language models perform better at interpreting metaphoric sentences when the action of the metaphorical sentence is more embodied.
  arXiv  Detail & Related papers  (2023-05-05T11:44:12Z)
• 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)
• Contextualized language models for semantic change detection: lessons learned [4.436724861363513]
  We present a qualitative analysis of the outputs of contextualized embedding-based methods for detecting diachronic semantic change. Our findings show that contextualized methods can often predict high change scores for words which are not undergoing any real diachronic semantic shift. Our conclusion is that pre-trained contextualized language models are prone to confound changes in lexicographic senses and changes in contextual variance.
  arXiv  Detail & Related papers  (2022-08-31T23:35:24Z)
• What Drives the Use of Metaphorical Language? Negative Insights from Abstractness, Affect, Discourse Coherence and Contextualized Word Representations [13.622570558506265]
  Given a specific discourse, which discourse properties trigger the use of metaphorical language, rather than using literal alternatives? Many NLP approaches to metaphorical language rely on cognitive and (psycho-)linguistic insights and have successfully defined models of discourse coherence, abstractness and affect. In this work, we build five simple models relying on established cognitive and linguistic properties to predict the use of a metaphorical vs. synonymous literal expression in context.
  arXiv  Detail & Related papers  (2022-05-23T08:08:53Z)
• Testing the Ability of Language Models to Interpret Figurative Language [69.59943454934799]
  Figurative and metaphorical language are commonplace in discourse. It remains an open question to what extent modern language models can interpret nonliteral phrases. We introduce Fig-QA, a Winograd-style nonliteral language understanding task.
  arXiv  Detail & Related papers  (2022-04-26T23:42:22Z)
• It's not Rocket Science : Interpreting Figurative Language in Narratives [48.84507467131819]
  We study the interpretation of two non-compositional figurative languages (idioms and similes) Our experiments show that models based solely on pre-trained language models perform substantially worse than humans on these tasks. We additionally propose knowledge-enhanced models, adopting human strategies for interpreting figurative language.
  arXiv  Detail & Related papers  (2021-08-31T21:46:35Z)
• Exploring the Representation of Word Meanings in Context: A Case Study on Homonymy and Synonymy [0.0]
  We assess the ability of both static and contextualized models to adequately represent different lexical-semantic relations. Experiments are performed in Galician, Portuguese, English, and Spanish.
  arXiv  Detail & Related papers  (2021-06-25T10:54:23Z)
• Low Anisotropy Sense Retrofitting (LASeR) : Towards Isotropic and Sense Enriched Representations [0.0]
  We analyze the representation geometry and find that most layers of deep pretrained language models create highly anisotropic representations. We propose LASeR, a 'Low Anisotropy Sense Retrofitting' approach that renders off-the-shelf representations isotropic and semantically more meaningful.
  arXiv  Detail & Related papers  (2021-04-22T02:44:49Z)
• Lexical semantic change for Ancient Greek and Latin [61.69697586178796]
  Associating a word's correct meaning in its historical context is a central challenge in diachronic research. We build on a recent computational approach to semantic change based on a dynamic Bayesian mixture model. We provide a systematic comparison of dynamic Bayesian mixture models for semantic change with state-of-the-art embedding-based models.
  arXiv  Detail & Related papers  (2021-01-22T12:04:08Z)
• Where New Words Are Born: Distributional Semantic Analysis of Neologisms and Their Semantic Neighborhoods [51.34667808471513]
  We investigate the importance of two factors, semantic sparsity and frequency growth rates of semantic neighbors, formalized in the distributional semantics paradigm. We show that both factors are predictive word emergence although we find more support for the latter hypothesis.
  arXiv  Detail & Related papers  (2020-01-21T19:09:49Z)

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.