Metric-Learning Encoding Models Identify Processing Profiles of Linguistic Features in BERT's Representations

• URL: http://arxiv.org/abs/2402.11608v1
• Date: Sun, 18 Feb 2024 14:57:53 GMT
• Title: Metric-Learning Encoding Models Identify Processing Profiles of Linguistic Features in BERT's Representations
• Authors: Louis Jalouzot, Robin Sobczyk, Bastien Lhopitallier, Jeanne Salle, Nur Lan, Emmanuel Chemla, Yair Lakretz
• Abstract summary: Metric-Learning Models (MLEMs) are a new approach to understand how neural systems represent the theoretical features of the objects they process. MLEMs can be extended to other domains (e.g. vision) and to other neural systems, such as the human brain.
• Score: 5.893248479095486
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce Metric-Learning Encoding Models (MLEMs) as a new approach to understand how neural systems represent the theoretical features of the objects they process. As a proof-of-concept, we apply MLEMs to neural representations extracted from BERT, and track a wide variety of linguistic features (e.g., tense, subject person, clause type, clause embedding). We find that: (1) linguistic features are ordered: they separate representations of sentences to different degrees in different layers; (2) neural representations are organized hierarchically: in some layers, we find clusters of representations nested within larger clusters, following successively important linguistic features; (3) linguistic features are disentangled in middle layers: distinct, selective units are activated by distinct linguistic features. Methodologically, MLEMs are superior (4) to multivariate decoding methods, being more robust to type-I errors, and (5) to univariate encoding methods, in being able to predict both local and distributed representations. Together, this demonstrates the utility of Metric-Learning Encoding Methods for studying how linguistic features are neurally encoded in language models and the advantage of MLEMs over traditional methods. MLEMs can be extended to other domains (e.g. vision) and to other neural systems, such as the human brain.

Related papers

• Large Language Models as Neurolinguistic Subjects: Identifying Internal Representations for Form and Meaning [49.60849499134362]
  This study investigates the linguistic understanding of Large Language Models (LLMs) regarding signifier (form) and signified (meaning) Traditional psycholinguistic evaluations often reflect statistical biases that may misrepresent LLMs' true linguistic capabilities. We introduce a neurolinguistic approach, utilizing a novel method that combines minimal pair and diagnostic probing to analyze activation patterns across model layers.
  arXiv  Detail & Related papers  (2024-11-12T04:16:44Z)
• Training Neural Networks as Recognizers of Formal Languages [87.06906286950438]
  Formal language theory pertains specifically to recognizers. It is common to instead use proxy tasks that are similar in only an informal sense. We correct this mismatch by training and evaluating neural networks directly as binary classifiers of strings.
  arXiv  Detail & Related papers  (2024-11-11T16:33:25Z)
• Brain-Like Language Processing via a Shallow Untrained Multihead Attention Network [16.317199232071232]
  Large Language Models (LLMs) have been shown to be effective models of the human language system. In this work, we investigate the key architectural components driving the surprising alignment of untrained models.
  arXiv  Detail & Related papers  (2024-06-21T12:54:03Z)
• What Makes Two Language Models Think Alike? [6.244579327420724]
  We propose a new approach, based on metric-learning encoding models (MLEMs), as a first step to answer this question. MLEMs offer a transparent comparison, by identifying the specific linguistic features responsible for similarities and differences. The approach can straightforwardly be extended to other domains, such as speech and vision, and to other neural systems, including human brains.
  arXiv  Detail & Related papers  (2024-06-18T13:45:50Z)
• Decoding Probing: Revealing Internal Linguistic Structures in Neural Language Models using Minimal Pairs [0.873811641236639]
  We introduce a novel decoding probing' method to probe internal linguistic characteristics in neural language models layer by layer. By treating the language model as the brain' and its representations as neural activations', we decode grammaticality labels of minimal pairs from the intermediate layers' representations.
  arXiv  Detail & Related papers  (2024-03-26T00:56:06Z)
• Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models [117.20416338476856]
  Large language models (LLMs) demonstrate remarkable multilingual capabilities without being pre-trained on specially curated multilingual parallel corpora. We propose a novel detection method, language activation probability entropy (LAPE), to identify language-specific neurons within LLMs. Our findings indicate that LLMs' proficiency in processing a particular language is predominantly due to a small subset of neurons.
  arXiv  Detail & Related papers  (2024-02-26T09:36:05Z)
• Investigating semantic subspaces of Transformer sentence embeddings through linear structural probing [2.5002227227256864]
  We present experiments with semantic structural probing, a method for studying sentence-level representations. We apply our method to language models from different families (encoder-only, decoder-only, encoder-decoder) and of different sizes in the context of two tasks. We find that model families differ substantially in their performance and layer dynamics, but that the results are largely model-size invariant.
  arXiv  Detail & Related papers  (2023-10-18T12:32:07Z)
• A Multi-level Supervised Contrastive Learning Framework for Low-Resource Natural Language Inference [54.678516076366506]
  Natural Language Inference (NLI) is a growingly essential task in natural language understanding. Here we propose a multi-level supervised contrastive learning framework named MultiSCL for low-resource natural language inference.
  arXiv  Detail & Related papers  (2022-05-31T05:54:18Z)
• Low-Dimensional Structure in the Space of Language Representations is Reflected in Brain Responses [62.197912623223964]
  We show a low-dimensional structure where language models and translation models smoothly interpolate between word embeddings, syntactic and semantic tasks, and future word embeddings. We find that this representation embedding can predict how well each individual feature space maps to human brain responses to natural language stimuli recorded using fMRI. This suggests that the embedding captures some part of the brain's natural language representation structure.
  arXiv  Detail & Related papers  (2021-06-09T22:59:12Z)
• What does it mean to be language-agnostic? Probing multilingual sentence encoders for typological properties [17.404220737977738]
  We propose methods for probing sentence representations from state-of-the-art multilingual encoders. Our results show interesting differences in encoding linguistic variation associated with different pretraining strategies.
  arXiv  Detail & Related papers  (2020-09-27T15:00:52Z)
• Linguistic Typology Features from Text: Inferring the Sparse Features of World Atlas of Language Structures [73.06435180872293]
  We construct a recurrent neural network predictor based on byte embeddings and convolutional layers. We show that some features from various linguistic types can be predicted reliably.
  arXiv  Detail & Related papers  (2020-04-30T21:00:53Z)

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.