R2-D2: A Modular Baseline for Open-Domain Question Answering
This work presents a novel four-stage open-domain QA pipeline R2-D2 (Rank twice, reaD twice). The pipeline is composed of a retriever, passage reranker, extractive reader, generative reader and a mechanism that aggregates the final prediction from all system's components. We demonstrate its strength across three open-domain QA datasets: NaturalQuestions, TriviaQA and EfficientQA, surpassing state-of-the-art on the first two. Our analysis demonstrates that: (i) combining extractive and generative reader yields absolute improvements up to 5 exact match and it is at least twice as effective as the posterior averaging ensemble of the same models with different parameters, (ii) the extractive reader with fewer parameters can match the performance of the generative reader on extractive QA datasets.
Code (1)
Tasks
Open-Domain Question AnsweringPassage RetrievalQuestion AnsweringTriviaQASimilar Papers 제목 키워드 기반
Combining Open Domain Question Answering with a Task-Oriented Dialog System
We apply the modular dialog system framework to combine open-domain question answering with a task-oriented dialog system. This meta dialog system can answer questions from Wikipedia and at the same time act as a persona…
Open-Domain Question AnsweringQuestion AnsweringSF-QA: Simple and Fair Evaluation Library for Open-domain Question Answering
Although open-domain question answering (QA) draws great attention in recent years, it requires large amounts of resources for building the full system and is often difficult to reproduce previous results due to complex …
Open-Domain Question AnsweringQuestion AnsweringKatecheo: A Portable and Modular System for Multi-Topic Question Answering
We introduce a modular system that can be deployed on any Kubernetes cluster for question answering via REST API. This system, called Katecheo, includes three configurable modules that collectively enable identification …
ArticlesQuestion AnsweringReading ComprehensionA dataset and baselines for sequential open-domain question answering
Previous work on question-answering systems mainly focuses on answering individual questions, assuming they are independent and devoid of context. Instead, we investigate sequential question answering, asking multiple re…
Information RetrievalOpen-Domain Question AnsweringQuestion AnsweringReading ComprehensionAmbigQA: 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 Learning