Work

Improving a Strong Neural Parser with Conjunction-Specific Features

Year: 2017

Type: conference-paper

Abstract: While dependency parsers reach very high overall accuracy, some dependency relations are much harder than others.In particular, dependency parsers perform poorly in coordination construction (i.e., correctly attaching the conj relation).We extend a state-of-the-art dependency parser with conjunction-specific features, focusing on the similarity between the conjuncts head words.Training the extended parser yields an improvement in conj attachment as well as in overall dependency parsing accuracy on the Stanford dependency conversion of the Penn TreeBank.

Source: Conference of the European Chapter of the Association for Computational Linguistics

DOI: 10.18653/v1/e17-2055

Authors: Jessica Ficler, Yoav Goldberg

Institution: Bar-Ilan University

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: Deutsche Forschungsgemeinschaft

Award: G7805275943