article thumbnail

Selective Classification Can Magnify Disparities Across Groups

The Stanford AI Lab Blog

In Association for Computational Linguistics (ACL), pp. In World Wide Web (WWW), pp. 491–500, 2019. ↩ Adina Williams, Nikita Nangia, and Samuel Bowman. A broad-coverage challenge corpus for sentence understanding through inference. 1112–1122, 2018. ↩ Yonatan Giefman and Ran El-Yaniv.

article thumbnail

Multi-domain Multilingual Question Answering

Sebastian Ruder

2008 ; Lin & Kuo, 2010 ; Shima & Mitamura, 2010 ). Most prior work on multilingual QA uses the translate-test setting, which translates all data into English—typically using an online MT system as a black box—and then applies a QA model trained on English to it ( Hartrumpf et al.,

BERT 52
article thumbnail

Lexical Inference

Probably Approximately a Scientific Blog

Proceedings of the 14th conference on Computational linguistics-Volume 2. Association for Computational Linguistics, 1992. Association for Computational Linguistics, 2003. Proceedings of the Nineteenth Conference on Computational Natural Language Learning. Association for Computational Linguistics.