Baselines and test data for cross-lingual inference (CROSBI ID 661577)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Agić, Željko ; Schluter, Natalie
engleski
Baselines and test data for cross-lingual inference
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.
natural language inference ; cross-lingual methods ; test data
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
3890-3894.
2018.
objavljeno
Podaci o matičnoj publikaciji
LREC 2018: Eleventh International Conference on Language Resources and Evaluation: Conference Proceedings
Calzolari, Nicoletta ... [et al.]
Miyazaki: European Language Resources Association (ELRA)
979-10-95546-00-9
Podaci o skupu
11th International Conference on Language Resources and Evaluation (LREC 2018)
poster
07.05.2018-12.05.2018
Miyazaki, Japan
Povezanost rada
Filologija, Informacijske i komunikacijske znanosti, Računarstvo