Reading Wikipedia to Answer Open-Domain Questions
By Danqi Chen, Adam Fisch, Jason Aaron Edward Weston, Antoine Bordes. 2017
2,232 citations recorded by the source corpus.
This paper proposes to tackle open-domain question answering using Wikipedia as the unique knowledge source: the answer to any factoid question is a text span in a Wikipedia article. This task of machine reading at scale combines the challenges of document retrieval (finding the relevant articles) with that of machine comprehension of text (identifying the answer spans from those articles). Our approach combines a search component based on bigram hashing and TF-IDF matching with a multi-layer recurrent neural network model trained to detect answers in Wikipedia paragraphs. Our experiments on multiple existing QA datasets indicate that (1) both modules are highly competitive with respect to existing counterparts and (2) multitask learning using distant supervision on their combination is an effective complete system on this challenging task.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Retrieval & Search, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Mohit Bansal
- Jianfeng Gao
- Luke S. Zettlemoyer
- Percy Liang
- Yejin Choi
- Hannaneh Hajishirzi
- Graham Neubig
- Caiming Xiong
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Mohit Bansal
- Trevor Darrell
- Jianfeng Gao
- Xiaogang Wang
- Ming-Hsuan Yang
- Jitendra Malik
In Information Retrieval & Search
- Jimmy J. Lin
- Hannaneh Hajishirzi
- Wen-tau Yih
- Jamie Callan
- Sebastian Riedel
- Danqi Chen
- Luyu Gao
- Gautier Izacard
In Natural Language Processing
- Mohit Bansal
- Luke S. Zettlemoyer
- Jianfeng Gao
- Yejin Choi
- Percy Liang
- Hannaneh Hajishirzi
- Graham Neubig
- Caiming Xiong
Citations in the corpus
- Multi-Granularity Hierarchical Attention Fusion Networks for Reading Comprehension and Question Answering (2018, methodology): “…representation: As for question side, since it is generally shorter in length and could be adequately represented with less information, we follow the question encoding method used in (Chen et al., 2017a) and adopt a linear transformation to encode the question representation to a single vector.”
- U-Net: Machine Reading Comprehension with Unanswerable Questions (2018, methodology): “Previous work Levy et al.; Clark and Gardner (2017; 2017) has attempted to normalize a no-answer score depending on the probability of all answer spans and still detect boundaries at the same time.”
- QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension (2018, background): “To measure the speedup of our model against the RNN models, we also test the corresponding model architecture with each encoder block replaced with a stack of bidirectional Published 12 LeaderBoard 13 Single Model EM / F1 EM / F1 LR Baseline (Rajpurkar et al., 2016) 40.4 / 51.0 40.4 / 51.0 Dynamic C”
- Simple and Effective Multi-Paragraph Reading Comprehension (2017, methodology): “Open question answering with neural models was considered by Chen et al. (2017), where researchers trained a model on SQuAD and combined it with a retrieval engine for Wikipedia articles.”
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (2020, methodology): “As a demonstration, we build an index using the DrQA Wikipedia dump [5], (dated December 21st, 2016) and compare generations from RAG using this index to the newer index used in our main results (December 20th, 2018).”
- Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering (2020, methodology): “While being a longstanding problem in natural language processing (Voorhees et al., 1999), this task has recently regained interest following the work by Chen et al. (2017).”
- REALM: Retrieval-Augmented Language Model Pre-Training (2020, methodology): “Numerous prior works have demonstrated the benefit of adding a discrete retrieval step to neural networks (Miller et al., 2016; Chen et al., 2017), but did not apply the framework to language model pre-training and employed nonlearned retrievers to handle large-scale document collections.”
- Few-shot Learning with Retrieval Augmented Language Models (2022, methodology): “For open-domain question answering (Voorhees et al., 1999), documents are often retrieved from Wikipedia (Chen et al., 2017).”
- How Much Knowledge Can You Pack into the Parameters of a Language Model? (2020, background): “, 2019)) or allows the model to retrieve information from an external knowledge source (Berant et al., 2013; Chen et al., 2017).”
- Adversarial NLI: A New Benchmark for Natural Language Understanding (2019, methodology): “Contexts are either ground-truth contexts from that dataset, or they are Wikipedia passages retrieved using TF-IDF (Chen et al., 2017) based on a HotpotQA question.”
- Technical report on Conversational Question Answering (2019, methodology): “Many MRC models have been proposed to tackle single-turn QA, such as BiDAF(Seo et al., 2016), DrQA(Chen et al., 2017), R-Net(Wang et al., 2017) and QANet(Yu et al., 2018) in SQuAD dataset.”
- Natural Questions: A Benchmark for Question Answering Research (2019, methodology): “Short answer selection Given a long answer, the Document Reader model (Chen et al., 2017), abbreviated DocReader, is used to extract short answers.”
- Defending Against Neural Fake News (2019, background): “An open question is to scale progress in this task towards entire news articles, and without paired evidence (similar to open-domain QA; Chen et al., 2017).”
- CoQA: A Conversational Question Answering Challenge (2018, methodology): “The state-of-the-art reading comprehension models for extractive question answering focus on finding a span in the passage that matches the question best (Seo et al., 2016; Chen et al., 2017; Yu et al., 2018).”
- Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering (2018, methodology): “For Question Match and ESIM we also experiment with ELMo (Peters et al., 2018) which improved their score on Test with 0.4% and 1.8%.”
- Improving Question Answering with External Knowledge (2019, methodology): “trieving relevant documents in Wikipedia and then running a MRC model to extract a text span from the documents based on the question (Chen et al., 2017; Wang et al., 2018b; Kratzwald and Feuerriegel, 2018; Lee et al., 2018; Lin et al., 2018).”
- Distilling Knowledge from Reader to Retriever for Question Answering (2020, methodology): “Following previous work (Chen et al., 2017), our approach uses two models: the first one retrieves documents from a large source of knowledge (the retriever), the second one processes the support documents to solve the task (the reader).”
- TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages (2020, background): “, 2019) ranging from generating an answer word-by-word (Mitra, 2017) or finding an answer from within an entire corpus as in TREC (Voorhees and Tice, 2000) and DrQA (Chen et al., 2017).”
- Augmented Language Models: a Survey (2023, methodology): “Various works augment LMs with a dense retriever by adding the retrieved documents to the current context (Chen et al., 2017; Clark and Gardner, 2017; Lee et al., 2019; Guu et al., 2020; Khandelwal et al., 2020; Lewis et al., 2020; Izacard and Grave, 2020; Zhong et al., 2022; Borgeaud et al., 2022;…”