지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
초록· 키워드
오류제보하기
This study compared the syntactic capabilities of several neural language models(LMs) including Transformers (BERT / ALBERT) and LSTM and investigated whether they exhibit human-like syntactic representations through a targeted evaluation approach, a method to evaluate the syntactic processing ability of LMs using sentences designed for psycholinguistic experiments. By employing gardenpath structures with several linguistic manipulations, whether LMs detect temporary ungrammaticality and use a linguistic cue such as plausibility, transitivity, and morphology is assessed. The results showed that both Transformers and LSTM exploited several linguistic cues for incremental syntactic processing, comparable to human syntactic processing. They differed, however, in terms of whether and how they use each linguistic cue. Overall, Transformers had a more human-like syntactic representation than LSTM, given their higher sensitivity to plausibility and ability to retain information from previous words. Meanwhile, the number of parameters does not seem to undermine the performance of LMs, contrary to what was predicted in previous studies. Through these findings, this research sought to contribute to a greater understanding of the syntactic processing of neural language models as well as human language processing.
목차
ABSTRACT
1. Introduction
2. Method
3. Results
4. General Discussion and Conclusion
References
참고문헌 (0)
참고문헌 신청함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
Psycholinguistic approaches to computational language models
담화·인지언어학회 학술대회 발표논문집
2021 .11
-
An Experimental Investigation of Discourse Expectations in Neural Language Models
영어학
2022 .01
-
Students’ Perceptions about the Role of Psycholinguistics in Developing Pre/in-Service Teachers’ Second Language Teaching Expertise: A Case Study of Virtual University of Pakistan
Journal of Asia TEFL
2021 .01
-
Decoding BERT’s Internal Processing of Garden-Path Structures through Attention Maps
영어학
2023 .01
-
사전학습 언어모델의 기술 분석 연구
인문언어
2020 .01
-
A Psycholinguistic Measurement of Language Dominance in Bilinguals
언어과학
2017 .01
-
Psycholinguistic Approaches to Code Switching: A Proposal for Multi-dimensional Comparisons across Typologically-different Languages
영어영문학
2020 .02
-
제2 언어 머릿속 사전에 관한 심리언어학적 탐색
언어학
2016 .04
-
Neural Network Language Models as Psycholinguistic Subjects: Focusing on Reflexive Dependency
언어학
2022 .12
-
말을 두고 말해본다
중국조선어문
2017 .03
-
영어 보충어 강요 문장 처리 연구: 전산 심리언어학 관점에서
영어영문학연구
2022 .03
-
Empty Garden
제3시대
2019 .08
-
일본어의 복수 표지 ‘-たち’의 사용 범위 확대에 대한 고찰 ―트랜스 동아시아적 예비 분석도 겸하여―
일본문화학보
2023 .02
-
Investigating Syntactic Interference Effects in Neural Language Models for Second Language Acquisition
영어학연구
2024 .02
-
Evaluation of BERT-Based Models’ Ability to Linguistically Distinguish Between Human-Authored and Machine-Generated Texts
언어
2024 .12
-
Sociocultural Perspective in Terms of Three Aspects
언어학연구
2016 .01
-
The Effects of Language Difference on L2 Learners’ Language Performance
미래영어영문학회 학술대회 자료집
2017 .12
-
Lexicalization Patterns of Motion Events in Korean Revisited : With a Focus on Path Realization
언어과학연구
2018 .12
-
중국인 학습자의 한국어 억양 발달 과정에서 나타난 언어 보편성과 모국어 전이-억양의 문법적 기능을 중심으로-
이중언어학
2019 .01
-
국어교육에서의 언어정체성과 문법 교육의 역할
국어교육연구
2016 .06
이 논문의 저자 정보
이 논문과 함께 이용한 논문
최근 본 자료
댓글(0)
0