Linguistic Structure from a Bottleneck on Sequential Information Processing

• URL: http://arxiv.org/abs/2405.12109v2
• Date: Wed, 09 Oct 2024 15:25:25 GMT
• Title: Linguistic Structure from a Bottleneck on Sequential Information Processing
• Authors: Richard Futrell, Michael Hahn,
• Abstract summary: We show that natural-language-like systematicity arises in codes that are constrained by predictive information. We show that human languages are structured to have low predictive information at the levels of phonology, morphology, syntax, and semantics.
• Score: 5.850665541267672
• License:
• Abstract: Human language is a unique form of communication in the natural world, distinguished by its structured nature. Most fundamentally, it is systematic, meaning that signals can be broken down into component parts that are individually meaningful -- roughly, words -- which are combined in a regular way to form sentences. Furthermore, the way in which these parts are combined maintains a kind of locality: words are usually concatenated together, and they form contiguous phrases, keeping related parts of sentences close to each other. We address the challenge of understanding how these basic properties of language arise from broader principles of efficient communication under information processing constraints. Here we show that natural-language-like systematicity arises in codes that are constrained by predictive information, a measure of the amount of information that must be extracted from the past of a sequence in order to predict its future. In simulations, we show that such codes approximately factorize their source distributions, and then express the resulting factors systematically and locally. Next, in a series of cross-linguistic corpus studies, we show that human languages are structured to have low predictive information at the levels of phonology, morphology, syntax, and semantics. Our result suggests that human language performs a sequential, discrete form of Independent Components Analysis on the statistical distribution over meanings that need to be expressed. It establishes a link between the statistical and algebraic structure of human language, and reinforces the idea that the structure of human language is shaped by communication under cognitive constraints.

Related papers

• Finding Structure in Language Models [3.882018118763685]
  This thesis is about whether language models possess a deep understanding of grammatical structure similar to that of humans. We will develop novel interpretability techniques that enhance our understanding of the complex nature of large-scale language models.
  arXiv  Detail & Related papers  (2024-11-25T14:37:24Z)
• Analyzing The Language of Visual Tokens [48.62180485759458]
  We take a natural-language-centric approach to analyzing discrete visual languages. We show that higher token innovation drives greater entropy and lower compression, with tokens predominantly representing object parts. We also show that visual languages lack cohesive grammatical structures, leading to higher perplexity and weaker hierarchical organization compared to natural languages.
  arXiv  Detail & Related papers  (2024-11-07T18:59:28Z)
• A Linguistic Investigation of Machine Learning based Contradiction Detection Models: An Empirical Analysis and Future Perspectives [0.34998703934432673]
  We analyze two Natural Language Inference data sets with respect to their linguistic features. The goal is to identify those syntactic and semantic properties that are particularly hard to comprehend for a machine learning model.
  arXiv  Detail & Related papers  (2022-10-19T10:06:03Z)
• 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)
• Crosslinguistic word order variation reflects evolutionary pressures of dependency and information locality [4.869029215261254]
  About 40% of the world's languages have subject-verb-object order, and about 40% have subject-object-verb order. We show that variation in word order reflects different ways of balancing competing pressures of dependency locality and information locality. Our findings suggest that syntactic structure and usage across languages co-adapt to support efficient communication under limited cognitive resources.
  arXiv  Detail & Related papers  (2022-06-09T02:56:53Z)
• Linking Emergent and Natural Languages via Corpus Transfer [98.98724497178247]
  We propose a novel way to establish a link by corpus transfer between emergent languages and natural languages. Our approach showcases non-trivial transfer benefits for two different tasks -- language modeling and image captioning. We also introduce a novel metric to predict the transferability of an emergent language by translating emergent messages to natural language captions grounded on the same images.
  arXiv  Detail & Related papers  (2022-03-24T21:24:54Z)
• Generalized Optimal Linear Orders [9.010643838773477]
  The sequential structure of language, and the order of words in a sentence specifically, plays a central role in human language processing. In designing computational models of language, the de facto approach is to present sentences to machines with the words ordered in the same order as in the original human-authored sentence. The very essence of this work is to question the implicit assumption that this is desirable and inject theoretical soundness into the consideration of word order in natural language processing.
  arXiv  Detail & Related papers  (2021-08-13T13:10:15Z)
• 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)
• Compositional Processing Emerges in Neural Networks Solving Math Problems [100.80518350845668]
  Recent progress in artificial neural networks has shown that when large models are trained on enough linguistic data, grammatical structure emerges in their representations. We extend this work to the domain of mathematical reasoning, where it is possible to formulate precise hypotheses about how meanings should be composed. Our work shows that neural networks are not only able to infer something about the structured relationships implicit in their training data, but can also deploy this knowledge to guide the composition of individual meanings into composite wholes.
  arXiv  Detail & Related papers  (2021-05-19T07:24:42Z)
• 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)
• Learning Music Helps You Read: Using Transfer to Study Linguistic Structure in Language Models [27.91397366776451]
  Training LSTMs on latent structure (MIDI music or Java code) improves test performance on natural language. Experiments on transfer between natural languages controlling for vocabulary overlap show that zero-shot performance on a test language is highly correlated with typological similarity to the training language.
  arXiv  Detail & Related papers  (2020-04-30T06:24:03Z)

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.