Work

English Multiword Expression-aware Dependency Parsing Including Named Entities

Year: 2017

Type: conference-paper

Abstract: Because syntactic structures and spans of multiword expressions (MWEs) are independently annotated in many English syntactic corpora, they are generally inconsistent with respect to one another, which is harmful to the implementation of an aggregate system.In this work, we construct a corpus that ensures consistency between dependency structures and MWEs, including named entities.Further, we explore models that predict both MWEspans and an MWE-aware dependency structure.Experimental results show that our joint model using additional MWEspan features achieves an MWE recognition improvement of 1.35 points over a pipeline model.

Source: Annual Meeting of the Association for Computational Linguistics (ACL)

DOI: 10.18653/v1/p17-2068

Authors: Akihiko Kato, Hiroyuki Shindo, Yuji Matsumoto

Institution: Nara Institute of Science and Technology

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: Nara Institute of Science and Technology, Japan Society for the Promotion of Science, Core Research for Evolutional Science and Technology

Awards: Research on syntactic parsing with multiword expressions, G1935184735, G6718509927