Adaptive document retrieval for deep question answering
Bernhard Kratzwald,Stefan Feuerriegel +1 more
- pp 576-581
TLDR
This paper proposed an adaptive document retrieval model, which learns the optimal candidate number for document retrieval, conditional on the size of the corpus and the query, and reported extensive experimental results showing that their adaptive approach outperforms state-of-the-art methods on multiple benchmark datasets, as well as in the context of corpora with variable sizes.Abstract:
State-of-the-art systems in deep question answering proceed as follows: (1)an initial document retrieval selects relevant documents, which (2) are then processed by a neural network in order to extract the final answer. Yet the exact interplay between both components is poorly understood, especially concerning the number of candidate documents that should be retrieved. We show that choosing a static number of documents - as used in prior research - suffers from a noise-information trade-off and yields suboptimal results. As a remedy, we propose an adaptive document retrieval model. This learns the optimal candidate number for document retrieval, conditional on the size of the corpus and the query. We report extensive experimental results showing that our adaptive approach outperforms state-of-the-art methods on multiple benchmark datasets, as well as in the context of corpora with variable sizes.read more
Citations
More filters
Proceedings ArticleDOI
Latent Retrieval for Weakly Supervised Open Domain Question Answering
Abstract: Recent work on open domain question answering (QA) assumes strong supervision of the supporting evidence and/or assumes a blackbox information retrieval (IR) system to retrieve evidence candidates. We argue that both are suboptimal, since gold evidence is not always available, and QA is fundamentally different from IR. We show for the first time that it is possible to jointly learn the retriever and reader from question-answer string pairs and without any IR system. In this setting, evidence retrieval from all of Wikipedia is treated as a latent variable. Since this is impractical to learn from scratch, we pre-train the retriever with an Inverse Cloze Task. We evaluate on open versions of five QA datasets. On datasets where the questioner already knows the answer, a traditional IR system such as BM25 is sufficient. On datasets where a user is genuinely seeking an answer, we show that learned retrieval is crucial, outperforming BM25 by up to 19 points in exact match.
Proceedings ArticleDOI
End-to-End Open-Domain Question Answering with BERTserini
TL;DR: In this paper, an end-to-end question answering system that integrates BERT with the open-source Anserini information retrieval toolkit is presented, which integrates best practices from IR with a BERT-based reader to identify answers from a large corpus of Wikipedia articles.
Proceedings Article
Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering
TL;DR: A new graph-based recurrent retrieval approach that learns to retrieve reasoning paths over the Wikipedia graph to answer multi-hop open-domain questions and achieves significant improvement in HotpotQA, outperforming the previous best model by more than 14 points.
Journal ArticleDOI
Combining Fact Extraction and Verification with Neural Semantic Matching Networks
TL;DR: Li et al. as mentioned in this paper presented a connected system consisting of three homogeneous neural semantic matching models that conduct document retrieval, sentence selection, and claim verification jointly for fact extraction and verification.
Posted Content
Latent Retrieval for Weakly Supervised Open Domain Question Answering
TL;DR: It is shown for the first time that it is possible to jointly learn the retriever and reader from question-answer string pairs and without any IR system, and outperforming BM25 by up to 19 points in exact match.
References
More filters
Posted Content
SQuAD: 100,000+ Questions for Machine Comprehension of Text
TL;DR: The Stanford Question Answering Dataset (SQuAD) as mentioned in this paper is a reading comprehension dataset consisting of 100,000+ questions posed by crowdworkers on a set of Wikipedia articles, where the answer to each question is a segment of text from the corresponding reading passage.
Proceedings ArticleDOI
SQuAD: 100,000+ Questions for Machine Comprehension of Text
TL;DR: The Stanford Question Answering Dataset (SQuAD) as mentioned in this paper is a reading comprehension dataset consisting of 100,000+ questions posed by crowdworkers on a set of Wikipedia articles, where the answer to each question is a segment of text from the corresponding reading passage.
Proceedings Article
Teaching machines to read and comprehend
Karl Moritz Hermann,Tomáš Kočiský,Edward Grefenstette,Lasse Espeholt,Will Kay,Mustafa Suleyman,Phil Blunsom +6 more
TL;DR: A new methodology is defined that resolves this bottleneck and provides large scale supervised reading comprehension data that allows a class of attention based deep neural networks that learn to read real documents and answer complex questions with minimal prior knowledge of language structure to be developed.
Proceedings Article
Semantic Parsing on Freebase from Question-Answer Pairs
TL;DR: This paper trains a semantic parser that scales up to Freebase and outperforms their state-of-the-art parser on the dataset of Cai and Yates (2013), despite not having annotated logical forms.
Proceedings Article
Bidirectional Attention Flow for Machine Comprehension
TL;DR: The BIDAF network is introduced, a multi-stage hierarchical process that represents the context at different levels of granularity and uses bi-directional attention flow mechanism to obtain a query-aware context representation without early summarization.