Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models

• URL: http://arxiv.org/abs/2106.06087v1
• Date: Thu, 10 Jun 2021 23:50:51 GMT
• Title: Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models
• Authors: Matthew Finlayson, Aaron Mueller, Stuart Shieber, Sebastian Gehrmann, Tal Linzen, Yonatan Belinkov
• Abstract summary: This study applies causal mediation analysis to pre-trained neural language models. We investigate the magnitude of models' preferences for grammatical inflections. We observe two distinct mechanisms for producing subject-verb agreement depending on the syntactic structure.
• Score: 40.83377935276978
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Targeted syntactic evaluations have demonstrated the ability of language models to perform subject-verb agreement given difficult contexts. To elucidate the mechanisms by which the models accomplish this behavior, this study applies causal mediation analysis to pre-trained neural language models. We investigate the magnitude of models' preferences for grammatical inflections, as well as whether neurons process subject-verb agreement similarly across sentences with different syntactic structures. We uncover similarities and differences across architectures and model sizes -- notably, that larger models do not necessarily learn stronger preferences. We also observe two distinct mechanisms for producing subject-verb agreement depending on the syntactic structure of the input sentence. Finally, we find that language models rely on similar sets of neurons when given sentences with similar syntactic structure.

Related papers

• Agentivit\`a e telicit\`a in GilBERTo: implicazioni cognitive [77.71680953280436]
  The goal of this study is to investigate whether a Transformer-based neural language model infers lexical semantics. The semantic properties considered are telicity (also combined with definiteness) and agentivity.
  arXiv  Detail & Related papers  (2023-07-06T10:52:22Z)
• Model Criticism for Long-Form Text Generation [113.13900836015122]
  We apply a statistical tool, model criticism in latent space, to evaluate the high-level structure of generated text. We perform experiments on three representative aspects of high-level discourse -- coherence, coreference, and topicality. We find that transformer-based language models are able to capture topical structures but have a harder time maintaining structural coherence or modeling coreference.
  arXiv  Detail & Related papers  (2022-10-16T04:35:58Z)
• Interpreting Language Models with Contrastive Explanations [99.7035899290924]
  Language models must consider various features to predict a token, such as its part of speech, number, tense, or semantics. Existing explanation methods conflate evidence for all these features into a single explanation, which is less interpretable for human understanding. We show that contrastive explanations are quantifiably better than non-contrastive explanations in verifying major grammatical phenomena.
  arXiv  Detail & Related papers  (2022-02-21T18:32:24Z)
• Oracle Linguistic Graphs Complement a Pretrained Transformer Language Model: A Cross-formalism Comparison [13.31232311913236]
  We examine the extent to which, in principle, linguistic graph representations can complement and improve neural language modeling. We find that, overall, semantic constituency structures are most useful to language modeling performance.
  arXiv  Detail & Related papers  (2021-12-15T04:29:02Z)
• Syntactic Persistence in Language Models: Priming as a Window into Abstract Language Representations [0.38498574327875945]
  We investigate the extent to which modern, neural language models are susceptible to syntactic priming. We introduce a novel metric and release Prime-LM, a large corpus where we control for various linguistic factors which interact with priming strength. We report surprisingly strong priming effects when priming with multiple sentences, each with different words and meaning but with identical syntactic structure.
  arXiv  Detail & Related papers  (2021-09-30T10:38:38Z)
• Is Incoherence Surprising? Targeted Evaluation of Coherence Prediction from Language Models [7.5413579967970605]
  We design an extendable set of test suites addressing different aspects of discourse and dialogue coherence. Unlike most previous coherence evaluation studies, we address specific linguistic devices beyond sentence order perturbations. We show that this paradigm is equally suited to evaluate linguistic qualities that contribute to the notion of coherence.
  arXiv  Detail & Related papers  (2021-05-07T20:28:33Z)
• Mechanisms for Handling Nested Dependencies in Neural-Network Language Models and Humans [75.15855405318855]
  We studied whether a modern artificial neural network trained with "deep learning" methods mimics a central aspect of human sentence processing. Although the network was solely trained to predict the next word in a large corpus, analysis showed the emergence of specialized units that successfully handled local and long-distance syntactic agreement. We tested the model's predictions in a behavioral experiment where humans detected violations in number agreement in sentences with systematic variations in the singular/plural status of multiple nouns.
  arXiv  Detail & Related papers  (2020-06-19T12:00:05Z)
• Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach [78.77265671634454]
  We make use of a multi-task objective, i.e., the models simultaneously predict words as well as ground truth parse trees in a form called "syntactic distances" Experimental results on the Penn Treebank and Chinese Treebank datasets show that when ground truth parse trees are provided as additional training signals, the model is able to achieve lower perplexity and induce trees with better quality.
  arXiv  Detail & Related papers  (2020-05-12T15:35:00Z)
• Do Neural Language Models Show Preferences for Syntactic Formalisms? [14.388237635684737]
  We study the extent to which the semblance of syntactic structure captured by language models adheres to a surface-syntactic or deep syntactic style of analysis. We apply a probe for extracting directed dependency trees to BERT and ELMo models trained on 13 different languages. We find that both models exhibit a preference for UD over SUD - with interesting variations across languages and layers.
  arXiv  Detail & Related papers  (2020-04-29T11:37:53Z)
• Overestimation of Syntactic Representationin Neural Language Models [16.765097098482286]
  One popular method for determining a model's ability to induce syntactic structure trains a model on strings generated according to a template then tests the model's ability to distinguish such strings from superficially similar ones with different syntax. We illustrate a fundamental problem with this approach by reproducing positive results from a recent paper with two non-syntactic baseline language models.
  arXiv  Detail & Related papers  (2020-04-10T15:13:03Z)

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.