Are Representations Built from the Ground Up? An Empirical Examination of Local Composition in Language Models

• URL: http://arxiv.org/abs/2210.03575v1
• Date: Fri, 7 Oct 2022 14:21:30 GMT
• Title: Are Representations Built from the Ground Up? An Empirical Examination of Local Composition in Language Models
• Authors: Emmy Liu and Graham Neubig
• Abstract summary: Representing compositional and non-compositional phrases is critical for language understanding. We first formulate a problem of predicting the LM-internal representations of longer phrases given those of their constituents. While we would expect the predictive accuracy to correlate with human judgments of semantic compositionality, we find this is largely not the case.
• Score: 91.3755431537592
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Compositionality, the phenomenon where the meaning of a phrase can be derived from its constituent parts, is a hallmark of human language. At the same time, many phrases are non-compositional, carrying a meaning beyond that of each part in isolation. Representing both of these types of phrases is critical for language understanding, but it is an open question whether modern language models (LMs) learn to do so; in this work we examine this question. We first formulate a problem of predicting the LM-internal representations of longer phrases given those of their constituents. We find that the representation of a parent phrase can be predicted with some accuracy given an affine transformation of its children. While we would expect the predictive accuracy to correlate with human judgments of semantic compositionality, we find this is largely not the case, indicating that LMs may not accurately distinguish between compositional and non-compositional phrases. We perform a variety of analyses, shedding light on when different varieties of LMs do and do not generate compositional representations, and discuss implications for future modeling work.

Related papers

• Investigating Idiomaticity in Word Representations [9.208145117062339]
  We focus on noun compounds of varying levels of idiomaticity in two languages (English and Portuguese) We present a dataset of minimal pairs containing human idiomaticity judgments for each noun compound at both type and token levels. We define a set of fine-grained metrics of Affinity and Scaled Similarity to determine how sensitive the models are to perturbations that may lead to changes in idiomaticity.
  arXiv  Detail & Related papers  (2024-11-04T21:05:01Z)
• Do Pre-Trained Language Models Detect and Understand Semantic Underspecification? Ask the DUST! [4.1970767174840455]
  We study whether pre-trained language models (LMs) correctly identify and interpret underspecified sentences. Our experiments show that when interpreting underspecified sentences, LMs exhibit little uncertainty, contrary to what theoretical accounts of underspecification would predict.
  arXiv  Detail & Related papers  (2024-02-19T19:49:29Z)
• "You Are An Expert Linguistic Annotator": Limits of LLMs as Analyzers of Abstract Meaning Representation [60.863629647985526]
  We examine the successes and limitations of the GPT-3, ChatGPT, and GPT-4 models in analysis of sentence meaning structure. We find that models can reliably reproduce the basic format of AMR, and can often capture core event, argument, and modifier structure. Overall, our findings indicate that these models out-of-the-box can capture aspects of semantic structure, but there remain key limitations in their ability to support fully accurate semantic analyses or parses.
  arXiv  Detail & Related papers  (2023-10-26T21:47:59Z)
• Natural Language Decompositions of Implicit Content Enable Better Text Representations [56.85319224208865]
  We introduce a method for the analysis of text that takes implicitly communicated content explicitly into account. We use a large language model to produce sets of propositions that are inferentially related to the text that has been observed. Our results suggest that modeling the meanings behind observed language, rather than the literal text alone, is a valuable direction for NLP.
  arXiv  Detail & Related papers  (2023-05-23T23:45:20Z)
• 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)
• A Latent-Variable Model for Intrinsic Probing [93.62808331764072]
  We propose a novel latent-variable formulation for constructing intrinsic probes. We find empirical evidence that pre-trained representations develop a cross-lingually entangled notion of morphosyntax.
  arXiv  Detail & Related papers  (2022-01-20T15:01:12Z)
• The Language Model Understood the Prompt was Ambiguous: Probing Syntactic Uncertainty Through Generation [23.711953448400514]
  We inspect to which extent neural language models (LMs) exhibit uncertainty over such analyses. We find that LMs can track multiple analyses simultaneously. As a response to disambiguating cues, the LMs often select the correct interpretation, but occasional errors point to potential areas of improvement.
  arXiv  Detail & Related papers  (2021-09-16T10:27:05Z)
• Provable Limitations of Acquiring Meaning from Ungrounded Form: What will Future Language Models Understand? [87.20342701232869]
  We investigate the abilities of ungrounded systems to acquire meaning. We study whether assertions enable a system to emulate representations preserving semantic relations like equivalence. We find that assertions enable semantic emulation if all expressions in the language are referentially transparent. However, if the language uses non-transparent patterns like variable binding, we show that emulation can become an uncomputable problem.
  arXiv  Detail & Related papers  (2021-04-22T01:00:17Z)
• Discourse structure interacts with reference but not syntax in neural language models [17.995905582226463]
  We study the ability of language models (LMs) to learn interactions between different linguistic representations. We find that, contrary to humans, implicit causality only influences LM behavior for reference, not syntax. Our results suggest that LM behavior can contradict not only learned representations of discourse but also syntactic agreement.
  arXiv  Detail & Related papers  (2020-10-10T03:14:00Z)
• Assessing Phrasal Representation and Composition in Transformers [13.460125148455143]
  Deep transformer models have pushed performance on NLP tasks to new limits. We present systematic analysis of phrasal representations in state-of-the-art pre-trained transformers. We find that phrase representation in these models relies heavily on word content, with little evidence of nuanced composition.
  arXiv  Detail & Related papers  (2020-10-08T04:59:39Z)

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.