What are the limits of cross-lingual dense passage retrieval for low-resource languages?
In this paper, we analyze the capabilities of the multi-lingual Dense Passage Retriever (mDPR) for extremely low-resource languages. In the Cross-lingual Open-Retrieval Answer Generation (CORA) pipeline, mDPR achieves success on multilingual open QA benchmarks across 26 languages, of which 9 were unseen during training. These results are promising for Question Answering (QA) for low-resource languages. We focus on two extremely low-resource languages for which mDPR performs poorly: Amharic and Khmer. We collect and curate datasets to train mDPR models using Translation Language Modeling (TLM) and question--passage alignment. We also investigate the effect of our extension on the language distribution in the retrieval results. Our results on the MKQA and AmQA datasets show that language alignment brings improvements to mDPR for the low-resource languages, but the improvements are modest and the results remain low. We conclude that fulfilling CORA's promise to enable multilingual open QA in extremely low-resource settings is challenging because the model, the data, and the evaluation approach are intertwined. Hence, all three need attention in follow-up work. We release our code for reproducibility and future work: https://anonymous.4open.science/r/Question-Answering-for-Low-Resource-Languages-B13C/
Code (0)
등록된 구현이 없습니다.
Tasks
Answer GenerationLanguage ModelingLanguage ModellingPassage RetrievalQuestion AnsweringRetrievalMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Augmenting Passage Representations with Query Generation for Enhanced Cross-Lingual Dense Retrieval
Effective cross-lingual dense retrieval methods that rely on multilingual pre-trained language models (PLMs) need to be trained to encompass both the relevance matching task and the cross-language alignment task. However…
Cross-Lingual Information RetrievalInformation RetrievalRetrievalMIA 2022 Shared Task Submission: Leveraging Entity Representations, Dense-Sparse Hybrids, and Fusion-in-Decoder for Cross-Lingual Question Answering
We describe our two-stage system for the Multilingual Information Access (MIA) 2022 Shared Task on Cross-Lingual Open-Retrieval Question Answering. The first stage consists of multilingual passage retrieval with a hybrid…
Cross-Lingual Question AnsweringDecoderLanguage ModelingLanguage Modelling+3One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval
We present Cross-lingual Open-Retrieval Answer Generation (CORA), the first unified many-to-many question answering (QA) model that can answer questions across many languages, even for ones without language-specific anno…
Answer GenerationPassage RetrievalQuestion AnsweringRetrieval+1Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative Training
Keyphrase generation is the task of automatically predicting keyphrases given a piece of long text. Despite its recent flourishing, keyphrase generation on non-English languages haven't been vastly investigated. In this …
Keyphrase GenerationPassage RetrievalRetrievalLexicon-Enhanced Self-Supervised Training for Multilingual Dense Retrieval
Recent multilingual pre-trained models have shown better performance in various multilingual tasks. However, these models perform poorly on multilingual retrieval tasks due to lacking multilingual training data. In this …
Retrieval