Normal view MARC view ISBD view

K-Best Spanning Tree Dependency Parsing With Verb Valency Lexicon Reranking / Agić, Željko.

By: Agić, Željko.
Material type: materialTypeLabelArticleDescription: 1-12.Other title: K-Best Spanning Tree Dependency Parsing With Verb Valency Lexicon Reranking [Naslov na engleskom:].Subject(s): 5.04 | 6.03 | dependency parsing, k-best spanning trees, verb valency lexicon hrv | dependency parsing, k-best spanning trees, verb valency lexicon engOnline resources: Click here to access online | Click here to access online In: 24th International Conference on Computational Linguistics (COLING 2012) (8-15.12.2012. ; Mumbai, Indija) Proceedings of COLING 2012: Posters str. 1-12Kay, Martin ; Boitet, ChristianSummary: A novel method for hybrid graph-based dependency parsing of natural language text is proposed. It is based on k-best maximum spanning tree dependency parsing and evaluation of the spanning trees by using a verb valency lexicon for a given language as a reranking knowledge base. The approach is compared with existing state-of-the- art transition-based and graph-based approaches to dependency parsing. As the proposed generic method was developed specifically for improving the accuracy of Croatian dependency parsing, Croatian Dependency Treebank and CROVALLEX verb valency lexicon are used in the experiment. The suggested approach scored approximately 77.21% LAS, outperforming the tested state-of-the-art approaches by at least 2.68% LAS.
Tags from this library: No tags from this library for this title. Log in to add tags.
No physical items for this record

A novel method for hybrid graph-based dependency parsing of natural language text is proposed. It is based on k-best maximum spanning tree dependency parsing and evaluation of the spanning trees by using a verb valency lexicon for a given language as a reranking knowledge base. The approach is compared with existing state-of-the- art transition-based and graph-based approaches to dependency parsing. As the proposed generic method was developed specifically for improving the accuracy of Croatian dependency parsing, Croatian Dependency Treebank and CROVALLEX verb valency lexicon are used in the experiment. The suggested approach scored approximately 77.21% LAS, outperforming the tested state-of-the-art approaches by at least 2.68% LAS.

Projekt MZOS 130-1300646-0645

Projekt MZOS 130-1300646-1776

ENG

There are no comments for this item.

Log in to your account to post a comment.

Powered by Koha