Learning to Translate for Multilingual Question Answering
In multilingual question answering, either the question needs to be translated into the document language, or vice versa. In addition to direction, there are multiple methods to perform the translation, four of which we explore in this paper: word-based, 10-best, context-based, and grammar-based. We build a feature for each combination of translation direction and method, and train a model that learns optimal feature weights. On a large forum dataset consisting of posts in English, Arabic, and Chinese, our novel learn-to-translate approach was more effective than a strong baseline (p<0.05): translating all text into English, then training a classifier based only on English (original or translated) text.
Code (0)
등록된 구현이 없습니다.
Tasks
Question AnsweringTranslationSimilar Papers 제목 키워드 기반
Automatic Spanish Translation of the SQuAD Dataset for Multilingual Question Answering
Recently, multilingual question answering became a crucial research topic, and it is receiving increased interest in the NLP community. However, the unavailability of large-scale datasets makes it challenging to train mu…
Question AnsweringTARTranslationAutomatic Spanish Translation of SQuAD Dataset for Multi-lingual Question Answering
Recently, multilingual question answering became a crucial research topic, and it is receiving increased interest in the NLP community. However, the unavailability of large-scale datasets makes it challenging to train mu…
Question AnsweringTARTranslationMintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering
We introduce Mintaka, a complex, natural, and multilingual dataset designed for experimenting with end-to-end question-answering models. Mintaka is composed of 20,000 question-answer pairs collected in English, annotated…
Question AnsweringUQA: Corpus for Urdu Question Answering
This paper introduces UQA, a novel dataset for question answering and text comprehension in Urdu, a low-resource language with over 70 million native speakers. UQA is generated by translating the Stanford Question Answer…
Multilingual NLPQuestion AnsweringReading ComprehensionMultilingual Answer Sentence Reranking via Automatically Translated Data
We present a study on the design of multilingual Answer Sentence Selection (AS2) models, which are a core component of modern Question Answering (QA) systems. The main idea is to transfer data, created from one resource …
Question AnsweringRerankingSentence