In this post, the paper "SuperNMT: Neural Machine Translation with Semantic Supersenses and
Syntactic Supertags"is summarized.
Link to paper: http://aclweb.org/anthology/P18-3010?fbclid=IwAR2078q3nTRhoguSu36IHBxYRRmLmoNbZfC50Ruz3_2Ah3Id335n-FE2-Qw
Eva Vanmassenhove, Andy Way, SuperNMT: Neural Machine Translation with Semantic Supersenses and
Syntactic Supertags, Proceedings of ACL 2018, Student Research Workshop, pages 67–73
Melbourne, Australia, July 15 - 20, 2018. Association for Computational Linguistics
Summary:
Neural Machine Translation (NMT) learn by generalizing patterns based on the raw, sentences providing semantic supersensetags and syntactic
supertag together make NMT
system learn multi-word expressions.
This
exclusive research enhances word-embeddings
in NMT systems by providing a combination
of semantic supersenses like (CCG supertags)
and syntactic supertag like (SST).
CCG tags every word in a sentence with its
correct role (verb/noun/auxiliary) and therefore resolve ambiguity
in terms of prepositional attachment.
SST,
in the other hand, classifies words independently into their
part-of-speech (Modal/ Adverb/ noun)
These
2 new embedding vectors are then concatenated into the classical embedding vector and used in the model.
Adding explicitly this
level of semantics provides the translation system with a higher level of abstraction beneficial to learn more complex constructions.
3 NMT systems are trained
and tested on 1M sentences of the Europarl
corpus for EN–FR and EN–DE:
One based on supersenses
(SST), one on syntactic supertag (CCG), and one on both (SST–CCG).
Results
for the EN–DE system shows
that SST system converges
faster, as hypothesized. The learning curve
is also more consistent.
But
if we focus on later stages of the learning process,
CCG-SST model outperforms the best model: translations are 5% better comparing to the 2 other systems.
The results
for the EN–DE
system and EN–FR system are very similar and lead to the same conclusion: combining semantic and syntactic features is beneficial for generalization which lead to a better
translation.
Aucun commentaire:
Enregistrer un commentaire