Measuring Semantic Abstraction of Multilingual NMT with Paraphrase Recognition and Generation Tasks

Forskningsoutput: Kapitel i bok/rapport/konferenshandlingKonferensbidragVetenskapligPeer review

Sammanfattning

In this paper, we investigate whether multilingual neural translation models learn stronger semantic abstractions of sentences than bilingual ones. We test this hypotheses by measuring the perplexity of such models when applied to paraphrases of the source language. The intuition is that an encoder produces better representations if a decoder is capable of recognizing synonymous sentences in the same language even though the model is never trained for that task. In our setup, we add 16 different auxiliary languages to a bidirectional bilingual baseline model (English-French) and test it with in-domain and out-of-domain paraphrases in English. The results show that the perplexity is significantly reduced in each of the cases, indicating that meaning can be grounded in translation. This is further supported by a study on paraphrase generation that we also include at the end of the paper.
Originalspråkengelska
Titel på gästpublikationProceedings of the 3rd Workshop on Evaluating Vector Space Representations for NLP
RedaktörerAnna Rogers, Aleksandr Drozd, Anna Rumshisky, Yoav Goldberg
Antal sidor8
UtgivningsortStroudsburg
FörlagThe Association for Computational Linguistics
Utgivningsdatum1 jun 2019
Sidor35-42
ISBN (elektroniskt)978-1-950737-05-5
StatusPublicerad - 1 jun 2019
MoE-publikationstypA4 Artikel i en konferenspublikation
Evenemang Workshop on Evaluating Vector Space Representations for NLP - Minneapolis, Förenta Staterna (USA)
Varaktighet: 6 jun 20196 jun 2019
Konferensnummer: 3

Vetenskapsgrenar

  • 113 Data- och informationsvetenskap
  • 6121 Språkvetenskaper

Citera det här