The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
본 논문에서는 주로 구문 부트스트래핑을 기반으로 한 아동 동사 학습 모델을 제시합니다. 이 모델은 대화 형식의 텍스트를 사용하여 하위 분류 프레임 및 주제별 역할을 포함한 4~5세 어린이의 동사 언어 지식을 자동으로 학습합니다. 동사의 하위 분류 프레임 획득은 XNUMX개의 동사 원형이 존재한다는 가정에 따라 진행됩니다. 이러한 동사 프로토타입은 구문 부트스트래핑 및 일부 심리언어학 연구를 기반으로 추출됩니다. 주제별 역할은 구문 부트스트래핑 및 기타 심리언어학적 가설에 의해 할당됩니다. 실험은 CHILDES 데이터베이스의 데이터에 대해 수행됩니다. 결과는 학습 모델이 동사에 대한 언어 지식을 성공적으로 획득하고 아동 동사 학습에 대한 심리언어학적 연구가 자연어 처리(NLP)에서 언어 지식 획득에 중요한 힌트를 제공할 수 있음을 시사합니다.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Tiansheng XU, Zenshiro KAWASAKI, Keiji TAKIDA, Zheng TANG, "A Child Verb Learning Model Based on Syntactic Bootstrapping" in IEICE TRANSACTIONS on Information,
vol. E85-D, no. 6, pp. 985-993, June 2002, doi: .
Abstract: This paper presents a child verb learning model mainly based on syntactic bootstrapping. The model automatically learns 4-5-year-old children's linguistic knowledge of verbs, including subcategorization frames and thematic roles, using a text in dialogue format. Subcategorization frame acquisition of verbs is guided by the assumption of the existence of nine verb prototypes. These verb prototypes are extracted based on syntactic bootstrapping and some psycholinguistic studies. Thematic roles are assigned by syntactic bootstrapping and other psycholinguistic hypotheses. The experiments are performed on the data from the CHILDES database. The results show that the learning model successfully acquires linguistic knowledge of verbs and also suggest that psycholinguistic studies of child verb learning may provide important hints for linguistic knowledge acquisition in natural language processing (NLP).
URL: https://global.ieice.org/en_transactions/information/10.1587/e85-d_6_985/_p
부
@ARTICLE{e85-d_6_985,
author={Tiansheng XU, Zenshiro KAWASAKI, Keiji TAKIDA, Zheng TANG, },
journal={IEICE TRANSACTIONS on Information},
title={A Child Verb Learning Model Based on Syntactic Bootstrapping},
year={2002},
volume={E85-D},
number={6},
pages={985-993},
abstract={This paper presents a child verb learning model mainly based on syntactic bootstrapping. The model automatically learns 4-5-year-old children's linguistic knowledge of verbs, including subcategorization frames and thematic roles, using a text in dialogue format. Subcategorization frame acquisition of verbs is guided by the assumption of the existence of nine verb prototypes. These verb prototypes are extracted based on syntactic bootstrapping and some psycholinguistic studies. Thematic roles are assigned by syntactic bootstrapping and other psycholinguistic hypotheses. The experiments are performed on the data from the CHILDES database. The results show that the learning model successfully acquires linguistic knowledge of verbs and also suggest that psycholinguistic studies of child verb learning may provide important hints for linguistic knowledge acquisition in natural language processing (NLP).},
keywords={},
doi={},
ISSN={},
month={June},}
부
TY - JOUR
TI - A Child Verb Learning Model Based on Syntactic Bootstrapping
T2 - IEICE TRANSACTIONS on Information
SP - 985
EP - 993
AU - Tiansheng XU
AU - Zenshiro KAWASAKI
AU - Keiji TAKIDA
AU - Zheng TANG
PY - 2002
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E85-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2002
AB - This paper presents a child verb learning model mainly based on syntactic bootstrapping. The model automatically learns 4-5-year-old children's linguistic knowledge of verbs, including subcategorization frames and thematic roles, using a text in dialogue format. Subcategorization frame acquisition of verbs is guided by the assumption of the existence of nine verb prototypes. These verb prototypes are extracted based on syntactic bootstrapping and some psycholinguistic studies. Thematic roles are assigned by syntactic bootstrapping and other psycholinguistic hypotheses. The experiments are performed on the data from the CHILDES database. The results show that the learning model successfully acquires linguistic knowledge of verbs and also suggest that psycholinguistic studies of child verb learning may provide important hints for linguistic knowledge acquisition in natural language processing (NLP).
ER -