Predicting Target Language CCG Supertags Improves Neural Machine Translation

02/03/2017
by   Maria Nădejde, et al.
0

Neural machine translation (NMT) models are able to partially learn syntactic information from sequential lexical information. Still, some complex syntactic phenomena such as prepositional phrase attachment are poorly modeled. This work aims to answer two questions: 1) Does explicitly modeling target language syntax help NMT? 2) Is tight integration of words and syntax better than multitask training? We introduce syntactic information in the form of CCG supertags in the decoder, by interleaving the target supertags with the word sequence. Our results on WMT data show that explicitly modeling target-syntax improves machine translation quality for German->English, a high-resource pair, and for Romanian->English, a low-resource pair and also several syntactic phenomena including prepositional phrase attachment. Furthermore, a tight coupling of words and syntax improves translation quality more than multitask training. By combining target-syntax with adding source-side dependency labels in the embedding layer, we obtain a total improvement of 0.9 BLEU for German->English and 1.2 BLEU for Romanian->English.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/16/2017

Towards String-to-Tree Neural Machine Translation

We present a simple method to incorporate syntactic information about th...
research
12/28/2021

A Preordered RNN Layer Boosts Neural Machine Translation in Low Resource Settings

Neural Machine Translation (NMT) models are strong enough to convey sema...
research
05/17/2020

Encodings of Source Syntax: Similarities in NMT Representations Across Target Languages

We train neural machine translation (NMT) models from English to six tar...
research
08/30/2018

Multi-Source Syntactic Neural Machine Translation

We introduce a novel multi-source technique for incorporating source syn...
research
08/16/2016

Neural versus Phrase-Based Machine Translation Quality: a Case Study

Within the field of Statistical Machine Translation (SMT), the neural ap...
research
09/11/2015

Verbs Taking Clausal and Non-Finite Arguments as Signals of Modality - Revisiting the Issue of Meaning Grounded in Syntax

We revisit Levin's theory about the correspondence of verb meaning and s...
research
05/02/2017

Modeling Source Syntax for Neural Machine Translation

Even though a linguistics-free sequence to sequence model in neural mach...

Please sign up or login with your details

Forgot password? Click here to reset