Events Calendar

EMNLP PRACTICE TALK: UNDERSTANDING NEURAL MACHINE TRANSLATION: LENGTH CONTROL AND SYNTACTIC STRUCTURE

Speaker: Xing Shi, USC/ISI

Talk Title: EMNLP PRACTICE TALK: UNDERSTANDING NEURAL MACHINE TRANSLATION: LENGTH CONTROL AND SYNTACTIC STRUCTURE

Series: Natural Language Seminar

Abstract: Neural Machine Translation is powerful but we know little about the black box. We conduct the following two investigations to gain a better understanding: First, we investigate how neural, encoder-decoder translation systems output target strings of appropriate lengths, finding that a collection of hidden units learns to explicitly implement this functionality. Second, 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.





Biography: Xing Shi is a PhD student at ISI working with Prof. Kevin Knight.

Host: Kevin Knight

More Info: http://nlg.isi.edu/nl-seminar/

Location: Information Science Institute (ISI) - 6th Floor -CR # 689; ISI-Marina del Rey

Audiences: Everyone Is Invited

Contact: Peter Zamar

Event Link: http://nlg.isi.edu/nl-seminar/