Modeling Human Sentence Processing with Left-Corner Recurrent Neural Network Grammars

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yoshida, Ryo, Noji, Hiroshi, Oseki, Yohei
Format: Preprint
Published: 2021
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915450420461568
author Yoshida, Ryo
Noji, Hiroshi
Oseki, Yohei
author_facet Yoshida, Ryo
Noji, Hiroshi
Oseki, Yohei
contents In computational linguistics, it has been shown that hierarchical structures make language models (LMs) more human-like. However, the previous literature has been agnostic about a parsing strategy of the hierarchical models. In this paper, we investigated whether hierarchical structures make LMs more human-like, and if so, which parsing strategy is most cognitively plausible. In order to address this question, we evaluated three LMs against human reading times in Japanese with head-final left-branching structures: Long Short-Term Memory (LSTM) as a sequential model and Recurrent Neural Network Grammars (RNNGs) with top-down and left-corner parsing strategies as hierarchical models. Our computational modeling demonstrated that left-corner RNNGs outperformed top-down RNNGs and LSTM, suggesting that hierarchical and left-corner architectures are more cognitively plausible than top-down or sequential architectures. In addition, the relationships between the cognitive plausibility and (i) perplexity, (ii) parsing, and (iii) beam size will also be discussed.
format Preprint
id arxiv_https___arxiv_org_abs_2109_04939
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Modeling Human Sentence Processing with Left-Corner Recurrent Neural Network Grammars
Yoshida, Ryo
Noji, Hiroshi
Oseki, Yohei
Computation and Language
In computational linguistics, it has been shown that hierarchical structures make language models (LMs) more human-like. However, the previous literature has been agnostic about a parsing strategy of the hierarchical models. In this paper, we investigated whether hierarchical structures make LMs more human-like, and if so, which parsing strategy is most cognitively plausible. In order to address this question, we evaluated three LMs against human reading times in Japanese with head-final left-branching structures: Long Short-Term Memory (LSTM) as a sequential model and Recurrent Neural Network Grammars (RNNGs) with top-down and left-corner parsing strategies as hierarchical models. Our computational modeling demonstrated that left-corner RNNGs outperformed top-down RNNGs and LSTM, suggesting that hierarchical and left-corner architectures are more cognitively plausible than top-down or sequential architectures. In addition, the relationships between the cognitive plausibility and (i) perplexity, (ii) parsing, and (iii) beam size will also be discussed.
title Modeling Human Sentence Processing with Left-Corner Recurrent Neural Network Grammars
topic Computation and Language
url https://arxiv.org/abs/2109.04939