English
Related papers

Related papers: Lexicosyntactic Inference in Neural Models

200 papers

Extensive research has recently shown that recurrent neural language models are able to process a wide range of grammatical phenomena. How these models are able to perform these remarkable feats so well, however, is still an open question.…

Computation and Language · Computer Science 2019-09-20 Jaap Jumelet , Willem Zuidema , Dieuwke Hupkes

We study causal inference in a multi-environment setting, in which the functional relations for producing the variables from their direct causes remain the same across environments, while the distribution of exogenous noises may vary. We…

Machine Learning · Computer Science 2017-05-29 AmirEmad Ghassami , Saber Salehkaleybar , Negar Kiyavash , Kun Zhang

An important challenge for human-like AI is compositional semantics. Recent research has attempted to address this by using deep neural networks to learn vector space embeddings of sentences, which then serve as input to other tasks. We…

Computation and Language · Computer Science 2018-05-21 Ishita Dasgupta , Demi Guo , Andreas Stuhlmüller , Samuel J. Gershman , Noah D. Goodman

Capturing the semantic relations of words in a vector space contributes to many natural language processing tasks. One promising approach exploits lexico-syntactic patterns as features of word pairs. In this paper, we propose a novel model…

Computation and Language · Computer Science 2018-09-11 Koki Washio , Tsuneaki Kato

Neural language models exhibit impressive performance on a variety of tasks, but their internal reasoning may be difficult to understand. Prior art aims to uncover meaningful properties within model representations via probes, but it is…

Computation and Language · Computer Science 2021-09-21 Mycal Tucker , Peng Qian , Roger Levy

Sequential neural networks models are powerful tools in a variety of Natural Language Processing (NLP) tasks. The sequential nature of these models raises the questions: to what extent can these models implicitly learn hierarchical…

Computation and Language · Computer Science 2018-11-27 Shauli Ravfogel , Francis M. Tyers , Yoav Goldberg

Structural probing work has found evidence for latent syntactic information in pre-trained language models. However, much of this analysis has focused on monolingual models, and analyses of multilingual models have employed correlational…

Computation and Language · Computer Science 2022-10-27 Aaron Mueller , Yu Xia , Tal Linzen

We define a novel textual entailment task that requires inference over multiple premise sentences. We present a new dataset for this task that minimizes trivial lexical inferences, emphasizes knowledge of everyday events, and presents a…

Computation and Language · Computer Science 2017-10-10 Alice Lai , Yonatan Bisk , Julia Hockenmaier

Models trained to estimate word probabilities in context have become ubiquitous in natural language processing. How do these models use lexical cues in context to inform their word probabilities? To answer this question, we present a case…

Computation and Language · Computer Science 2021-04-23 Kanishka Misra , Allyson Ettinger , Julia Taylor Rayz

Modern deep neural networks achieve impressive performance in engineering applications that require extensive linguistic skills, such as machine translation. This success has sparked interest in probing whether these models are inducing…

Computation and Language · Computer Science 2020-04-24 Tal Linzen , Marco Baroni

What kinds of and how much data is necessary for language models to induce grammatical knowledge to judge sentence acceptability? Recent language models still have much room for improvement in their data efficiency compared to humans. This…

Computation and Language · Computer Science 2024-10-24 Miyu Oba , Yohei Oseki , Akiyo Fukatsu , Akari Haga , Hiroki Ouchi , Taro Watanabe , Saku Sugawara

We apply recent advances in deep generative modeling to the task of imitation learning from biological agents. Specifically, we apply variations of the variational recurrent neural network model to a multi-agent setting where we learn…

Machine Learning · Computer Science 2020-07-02 Michael Teng , Tuan Anh Le , Adam Scibior , Frank Wood

Large language models (LLMs) are trained on enormous amounts of data and encode knowledge in their parameters. We propose a pipeline to elicit causal relationships from LLMs. Specifically, (i) we sample many documents from LLMs on a given…

Machine Learning · Computer Science 2026-03-05 Takashi Kameyama , Masahiro Kato , Yasuko Hio , Yasushi Takano , Naoto Minakawa

Scaling large language models (LLMs) leads to an emergent capacity to learn in-context from example demonstrations. Despite progress, theoretical understanding of this phenomenon remains limited. We argue that in-context learning relies on…

Computation and Language · Computer Science 2023-03-15 Michael Hahn , Navin Goyal

Common language models typically predict the next word given the context. In this work, we propose a method that improves language modeling by learning to align the given context and the following phrase. The model does not require any…

Computation and Language · Computer Science 2019-06-06 Hongyin Luo , Lan Jiang , Yonatan Belinkov , James Glass

Prediction in language has traditionally been studied using simple designs in which neural responses to expected and unexpected words are compared in a categorical fashion. However, these designs have been contested as being `prediction…

Neurons and Cognition · Quantitative Biology 2019-09-11 Micha Heilbron , Benedikt Ehinger , Peter Hagoort , Floris P. de Lange

Language models are at the heart of numerous works, notably in the text mining and information retrieval communities. These statistical models aim at extracting word distributions, from simple unigram models to recurrent approaches with…

Computation and Language · Computer Science 2020-02-25 Edouard Delasalles , Sylvain Lamprier , Ludovic Denoyer

According to the principle of compositional generalization, the meaning of a complex expression can be understood as a function of the meaning of its parts and of how they are combined. This principle is crucial for human language…

Computation and Language · Computer Science 2024-03-19 Sungjun Han , Sebastian Padó

Language Models (LMs) have emerged as powerful sources of evidence for linguists seeking to develop theories of syntax. In this paper, we argue that causal interpretability methods, applied to LMs, can greatly enhance the value of such…

Computation and Language · Computer Science 2025-10-01 Sasha Boguraev , Christopher Potts , Kyle Mahowald

The outcomes of elections, product sales, and the structure of social connections are all determined by the choices individuals make when presented with a set of options, so understanding the factors that contribute to choice is crucial. Of…

Machine Learning · Computer Science 2020-11-09 Kiran Tomlinson , Austin R. Benson
‹ Prev 1 3 4 5 6 7 10 Next ›