Baselines and test data for cross-lingual inference

Zeljko Agic, Natalie Schluter

Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review


The recent years have seen a revival of interest in textual entailment, sparked by i) the emergence of powerful deep neural network learners for natural language processing and ii) the timely development of large-scale evaluation datasets such as SNLI. Recast as natural language inference, the problem now amounts to detecting the relation between pairs of statements: they either contradict or entail one another, or they are mutually neutral. Current research in natural language inference is effectively exclusive to English. In this paper, we propose to advance the research in SNLI-style natural language inference toward multilingual evaluation. To that end, we provide test data for four major languages: Arabic, French, Spanish, and Russian. We experiment with a set of baselines. Our systems are based on cross-lingual word embeddings and machine translation. While our best system scores an average accuracy of just over 75%, we focus largely on enabling further research in multilingual inference.
TitelProceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)
Antal sider5
ForlagEuropean Language Resources Association
Publikationsdato7 maj 2018
ISBN (Elektronisk)979-10-95546-00-9
StatusUdgivet - 7 maj 2018


Dyk ned i forskningsemnerne om 'Baselines and test data for cross-lingual inference'. Sammen danner de et unikt fingeraftryk.