Using Distributional Principles for the Semantic Study of Contextual Language Models

• URL: http://arxiv.org/abs/2111.12174v1
• Date: Tue, 23 Nov 2021 22:21:16 GMT
• Title: Using Distributional Principles for the Semantic Study of Contextual Language Models
• Authors: Olivier Ferret
• Abstract summary: We first focus on these properties for English by exploiting the distributional principle of substitution as a probing mechanism in the controlled context of SemCor and WordNet paradigmatic relations. We then propose to adapt the same method to a more open setting for characterizing the differences between static and contextual language models.
• Score: 7.284661356980247
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many studies were recently done for investigating the properties of contextual language models but surprisingly, only a few of them consider the properties of these models in terms of semantic similarity. In this article, we first focus on these properties for English by exploiting the distributional principle of substitution as a probing mechanism in the controlled context of SemCor and WordNet paradigmatic relations. Then, we propose to adapt the same method to a more open setting for characterizing the differences between static and contextual language models.

Related papers

• Cross-domain Chinese Sentence Pattern Parsing [67.1381983012038]
  Sentence Pattern Structure (SPS) parsing is a syntactic analysis method primarily employed in language teaching. Existing SPSs rely heavily on textbook corpora for training, lacking cross-domain capability. This paper proposes an innovative approach leveraging large language models (LLMs) within a self-training framework.
  arXiv  Detail & Related papers  (2024-02-26T05:30:48Z)
• How Well Do Text Embedding Models Understand Syntax? [50.440590035493074]
  The ability of text embedding models to generalize across a wide range of syntactic contexts remains under-explored. Our findings reveal that existing text embedding models have not sufficiently addressed these syntactic understanding challenges. We propose strategies to augment the generalization ability of text embedding models in diverse syntactic scenarios.
  arXiv  Detail & Related papers  (2023-11-14T08:51:00Z)
• Feature Interactions Reveal Linguistic Structure in Language Models [2.0178765779788495]
  We study feature interactions in the context of feature attribution methods for post-hoc interpretability. We work out a grey box methodology, in which we train models to perfection on a formal language classification task. We show that under specific configurations, some methods are indeed able to uncover the grammatical rules acquired by a model.
  arXiv  Detail & Related papers  (2023-06-21T11:24:41Z)
• Topics in Contextualised Attention Embeddings [7.6650522284905565]
  Recent work has demonstrated that conducting clustering on the word-level contextual representations from a language model emulates word clusters that are discovered in latent topics of words from Latent Dirichlet Allocation. The important question is how such topical word clusters are automatically formed, through clustering, in the language model when it has not been explicitly designed to model latent topics. Using BERT and DistilBERT, we find that the attention framework plays a key role in modelling such word topic clusters.
  arXiv  Detail & Related papers  (2023-01-11T07:26:19Z)
• Beyond Contrastive Learning: A Variational Generative Model for Multilingual Retrieval [109.62363167257664]
  We propose a generative model for learning multilingual text embeddings. Our model operates on parallel data in $N$ languages. We evaluate this method on a suite of tasks including semantic similarity, bitext mining, and cross-lingual question retrieval.
  arXiv  Detail & Related papers  (2022-12-21T02:41:40Z)
• 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)
• Visual Comparison of Language Model Adaptation [55.92129223662381]
  adapters are lightweight alternatives for model adaptation. In this paper, we discuss several design and alternatives for interactive, comparative visual explanation methods. We show that, for instance, an adapter trained on the language debiasing task according to context-0 embeddings introduces a new type of bias.
  arXiv  Detail & Related papers  (2022-08-17T09:25:28Z)
• Do Language Models Learn Position-Role Mappings? [1.4548651568912523]
  We test whether well-performing pertained language models (BERT, RoBERTa, and DistilBERT) exhibit knowledge of position-role mappings. In Experiment 1, we show that these neural models do indeed recognize distinctions between theme and recipient roles. In Experiment 2, we show that fine-tuning these language models on novel theme- and recipient-like tokens in one paradigm allows the models to make correct predictions about their placement in other paradigms.
  arXiv  Detail & Related papers  (2022-02-08T02:50:53Z)
• Dependency Induction Through the Lens of Visual Perception [81.91502968815746]
  We propose an unsupervised grammar induction model that leverages word concreteness and a structural vision-based to jointly learn constituency-structure and dependency-structure grammars. Our experiments show that the proposed extension outperforms the current state-of-the-art visually grounded models in constituency parsing even with a smaller grammar size.
  arXiv  Detail & Related papers  (2021-09-20T18:40:37Z)
• Analysing Lexical Semantic Change with Contextualised Word Representations [7.071298726856781]
  We propose a novel method that exploits the BERT neural language model to obtain representations of word usages. We create a new evaluation dataset and show that the model representations and the detected semantic shifts are positively correlated with human judgements.
  arXiv  Detail & Related papers  (2020-04-29T12:18:14Z)
• How Far are We from Effective Context Modeling? An Exploratory Study on Semantic Parsing in Context [59.13515950353125]
  We present a grammar-based decoding semantic parsing and adapt typical context modeling methods on top of it. We evaluate 13 context modeling methods on two large cross-domain datasets, and our best model achieves state-of-the-art performances.
  arXiv  Detail & Related papers  (2020-02-03T11:28:10Z)

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.