MIX : a Multi-task Learning Approach to Solve Open-Domain Question Answering
In this paper, we introduce MIX : a multi-task deep learning approach to solve Open-Domain Question Answering. First, we design our system as a multi-stage pipeline made of 3 building blocks : a BM25-based Retriever, to reduce the search space; RoBERTa based Scorer and Extractor, to rank retrieved paragraphs and extract relevant spans of text respectively. Eventually, we further improve computational efficiency of our system to deal with the scalability challenge : thanks to multi-task learning, we parallelize the close tasks solved by the Scorer and the Extractor. Our system is on par with state-of-the-art performances on the squad-open benchmark while being simpler conceptually.
Code (0)
등록된 구현이 없습니다.
Tasks
Computational EfficiencyMulti-Task LearningOpen-Domain Question AnsweringQuestion AnsweringMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
AmbigQA: Answering Ambiguous Open-domain Questions
Ambiguity is inherent to open-domain question answering; especially when exploring new topics, it can be difficult to ask questions that have a single, unambiguous answer. In this paper, we introduce AmbigQA, a new open-…
Open-Domain Question AnsweringQuestion AnsweringWeakly-supervised LearningAsk To The Point: Open-Domain Entity-Centric Question Generation
We introduce a new task called *entity-centric question generation* (ECQG), motivated by real-world applications such as topic-specific learning, assisted reading, and fact-checking. The task aims to generate questions f…
Fact CheckingQuestion GenerationQuestion-GenerationAnswering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction
In open-domain question answering, questions are highly likely to be ambiguous because users may not know the scope of relevant topics when formulating them. Therefore, a system needs to find possible interpretations of …
Open-Domain Question AnsweringQuestion AnsweringTriviaQAOpenBioRQ: Unsolved Biomedical Research Questions for Agents
A working citation looks like proof -- but the fact that a link resolves does not mean the cited paper supports the claim. I find that current agentic models rarely fabricate citations (over $99\%$ resolve), yet roughly …
Simple yet Effective Bridge Reasoning for Open-Domain Multi-Hop Question Answering
A key challenge of multi-hop question answering (QA) in the open-domain setting is to accurately retrieve the supporting passages from a large corpus. Existing work on open-domain QA typically relies on off-the-shelf inf…
Information RetrievalMulti-hop Question AnsweringQuestion AnsweringReading Comprehension+1