Multilingual Semantic Networks for Data-driven Interlingua Seq2Seq Systems

Cristina España-Bonet; Josef van Genabith
In: Jinhua Du; Mihael Arcan; Qun Liu; Hitoshi Isahara (Hrsg.). Proceedings of the LREC 2018 Workshop “MLP-MomenT”. International Conference on Language Resources and Evaluation (LREC-2018), located at 20th, May 7-12, Miyazaki, Japan, Pages 8-13, ISBN 979-10-95546-15-3, 2018.


Neural machine translation systems are state-of-the-art for most language pairs despite the fact that they are relatively recent and that because of this there is likely room for even further improvements. Here, we explore whether, and if so, to what extent, semantic networks can help improve NMT. In particular, we (i) study the contribution of the nodes of the semantic network, synsets, as factors in multilingual neural translation engines. We show that they improve a state-of-the-art baseline and that they facilitate the translation from languages that have not been seen at all in training (beyond zero-shot translation). Taking this idea to an extreme, we (ii) use synsets as the basic unit to encode the input and turn the source language into a data-driven interlingual language. This transformation boosts the performance of the neural system for unseen languages achieving an improvement of 4.9/6.3 and 8.2/8.7 points of BLEU/METEOR for fr2en and es2en respectively when neither corpora in fr or es has been used. In (i), the enhancement comes about because cross-language synsets help to cluster words by semantics irrespective of their language and to map the unknown words of a new language into the multilingual clusters. In (ii), because with the data-driven interlingua there is no unknown language if it is covered by the semantic network. However, non-content words are not represented in the semantic network, and a higher level of abstraction is still needed in order to go a step further and train these systems with only monolingual corpora for example.



Weitere Links