Eric Lind


2022

pdf bib
Cross-Lingual Open-Domain Question Answering with Answer Sentence Generation
Benjamin Muller | Luca Soldaini | Rik Koncel-Kedziorski | Eric Lind | Alessandro Moschitti
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Open-Domain Generative Question Answering has achieved impressive performance in English by combining document-level retrieval with answer generation. These approaches, which we refer to as GenQA, can generate complete sentences, effectively answering both factoid and non-factoid questions. In this paper, we extend to the multilingual and cross-lingual settings. For this purpose, we first introduce GenTyDiQA, an extension of the TyDiQA dataset with well-formed and complete answers for Arabic, Bengali, English, Japanese, and Russian. Based on GenTyDiQA, we design a cross-lingual generative model that produces full-sentence answers by exploiting passages written in multiple languages, including languages different from the question. Our cross-lingual generative system outperforms answer sentence selection baselines for all 5 languages and monolingual generative pipelines for three out of five languages studied.

2021

pdf bib
Answer Generation for Retrieval-based Question Answering Systems
Chao-Chun Hsu | Eric Lind | Luca Soldaini | Alessandro Moschitti
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021