paper-with-me

홈 › Papers

RNNs as psycholinguistic subjects: Syntactic state and grammatical dependency

2018-09-05 · Richard Futrell, Ethan Wilcox, Takashi Morita, Roger Levy

Recurrent neural networks (RNNs) are the state of the art in sequence modeling for natural language. However, it remains poorly understood what grammatical characteristics of natural language they implicitly learn and represent as a consequence of optimizing the language modeling objective. Here we deploy the methods of controlled psycholinguistic experimentation to shed light on to what extent RNN behavior reflects incremental syntactic state and grammatical dependency representations known to characterize human linguistic behavior. We broadly test two publicly available long short-term memory (LSTM) English sequence models, and learn and test a new Japanese LSTM. We demonstrate that these models represent and maintain incremental syntactic state, but that they do not always generalize in the same way as humans. Furthermore, none of our models learn the appropriate grammatical dependency configurations licensing reflexive pronouns or negative polarity items.

📄 PDF Abstract BibTeX arXiv:1809.01329

Code (1)

Futrell/rnn_psycholinguistic_subjects 공식 구현 pytorch

Tasks

Language ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State

2019-03-08 · NAACL 2019 6 · Richard Futrell, Ethan Wilcox, Takashi Morita, Peng Qian 외

We deploy the methods of controlled psycholinguistic experimentation to shed light on the extent to which the behavior of neural network language models reflects incremental representations of syntactic state. To do so, …

Exploring the Syntactic Abilities of RNNs with Multi-task Learning

2017-06-12 · CONLL 2017 8 · Emile Enguehard, Yoav Goldberg, Tal Linzen

Recent work has explored the syntactic abilities of RNNs using the subject-verb agreement task, which diagnoses sensitivity to sentence structure. RNNs performed this task well in common cases, but faltered in complex se…

CCG SupertaggingLanguage ModelingLanguage ModellingMulti-Task Learning+1

Distinct patterns of syntactic agreement errors in recurrent networks and humans

2018-07-18 · Tal Linzen, Brian Leonard

Determining the correct form of a verb in context requires an understanding of the syntactic structure of the sentence. Recurrent neural networks have been shown to perform this task with an error rate comparable to huma…

Sentence

A Method for Studying Semantic Construal in Grammatical Constructions with Interpretable Contextual Embedding Spaces

2023-05-29 · Gabriella Chronis, Kyle Mahowald, Katrin Erk

We study semantic construal in grammatical constructions using large language models. First, we project contextual word embeddings into three interpretable semantic spaces, each defined by a different set of psycholingui…

ObjectPositionSentenceWord Embeddings

Disaggregation Reveals Hidden Training Dynamics: The Case of Agreement Attraction

2025-10-28 · James A. Michaelov, Catherine Arnett arxiv

Language models generally produce grammatical text, but they are more likely to make errors in certain contexts. Drawing on paradigms from psycholinguistics, we carry out a fine-grained analysis of those errors in differ…