← Back to papers
2021 EACL EACL 2021

Calculating the optimal step of arc-eager parsing for non-projective trees

Abstract

AbstractIt is shown that the optimal next step of an arc-eager parser relative to a non-projective dependency structure can be calculated in cubic time, solving an open problem in parsing theory. Applications are in training of parsers by means of a ‘dynamic oracle’.

🧭 Keyword Pioneer — non-projective tree
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Security & Privacy, Speech & Audio

Authors

Mark-Jan Nederhof

Topics

Mathematics & Optimization > Mathematics > Discrete Mathematics Mathematics & Optimization > Optimization > Combinatorial Optimization

Keywords

dependency parsing dynamic oracle non-projective tree arc-eager parsing cubic time algorithm parsing theory
Download PDF

Related papers

Joint Coreference Resolution and Character Linking for Multiparty Conversation 2021
Progressively Pretrained Dense Corpus Index for Open-Domain Question Answering 2021
Crisscrossed Captions: Extended Intramodal and Intermodal Semantic Similarity Judgments for MS-COCO 2021
Representations for Question Answering from Documents with Tables and Text 2021
Gender and Racial Fairness in Depression Research using Social Media 2021