Work

Does String-Based Neural MT Learn Source Syntax?

Year: 2016

Type: conference-paper

Abstract: We investigate whether a neural, encoderdecoder translation system learns syntactic information on the source side as a by-product of training.We propose two methods to detect whether the encoder has learned local and global source syntax.A fine-grained analysis of the syntactic structure learned by the encoder reveals which kinds of syntax are learned and which are missing.

Source: Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI: 10.18653/v1/d16-1159

Authors: Xing Shi, Inkit Padhi, Kevin Knight

Institution: University of Southern California

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W2563574619

FWCI: 23.69

Cites: 26

Cited by: 302

Related to: 10