The Web as a Knowledge-Base for Answering Complex Questions

Talmor, Alon; Berant, Jonathan

doi:10.18653/v1/n18-1059

Cited by 393 publications

(416 citation statements)

References 33 publications

Supporting

Mentioning

356

Contrasting

Unclassified

Order By: Relevance

“…SplitQA (Talmor and Berant, 2018) is a textbased QA system that cam decompose complex questions (e.g. conjunction, composition) into simple subquestions, and perform retrieval on them sequentially.…”

Section: Related Workmentioning

confidence: 99%

PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text

Sun

Bedrax-Weiss

Cohen

2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

218

206

View full text Add to dashboard Cite

We consider open-domain queston answering (QA) where answers are drawn from either a corpus, a knowledge base (KB), or a combination of both of these. We focus on a setting in which a corpus is supplemented with a large but incomplete KB, and on questions that require non-trivial (e.g., "multi-hop") reasoning. We describe PullNet, an integrated framework for (1) learning what to retrieve (from the KB and/or corpus) and (2) reasoning with this heterogeneous information to find the best answer. PullNet uses an iterative process to construct a question-specific subgraph that contains information relevant to the question. In each iteration, a graph convolutional network (graph CNN) is used to identify subgraph nodes that should be expanded using retrieval (or "pull") operations on the corpus and/or KB. After the subgraph is complete, a similar graph CNN is used to extract the answer from the subgraph. This retrieve-and-reason process allows us to answer multi-hop questions using large KBs and corpora. PullNet is weakly supervised, requiring question-answer pairs but not gold inference paths. Experimentally PullNet improves over the prior state-ofthe art, and in the setting where a corpus is used with incomplete KB these improvements are often dramatic. PullNet is also often superior to prior systems in a KB-only setting or a text-only setting.

show abstract

Section: Related Workmentioning

confidence: 99%

PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text

Sun

Bedrax-Weiss

Cohen

2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

218

206

View full text Add to dashboard Cite

show abstract

“…Multi-Hop QA Pioneering datasets of multi-hop QA are either based on limited knowledge base schemas (Talmor and Berant, 2018), or under multiple choices setting (Welbl et al, 2018). The noise in these datasets also restricted the development of multi-hop QA until high-quality Hot-potQA (Yang et al, 2018) is released recently.…”

Section: Related Workmentioning

confidence: 99%

Cognitive Graph for Multi-Hop Reading Comprehension at Scale

Ding¹,

Zhou²,

Chen³

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

168

132

View full text Add to dashboard Cite

We propose a new CogQA framework for multi-hop question answering in web-scale documents. Founded on the dual process theory in cognitive science, the framework gradually builds a cognitive graph in an iterative process by coordinating an implicit extraction module (System 1) and an explicit reasoning module (System 2). While giving accurate answers, our framework further provides explainable reasoning paths. Specifically, our implementation 1 based on BERT and graph neural network (GNN) efficiently handles millions of documents for multi-hop reasoning questions in the HotpotQA fullwiki dataset, achieving a winning joint F 1 score of 34.9 on the leaderboard, compared to 23.6 of the best competitor. 2

show abstract

“…Unfortunately this method is restricted to questions with prepositional and adverbial constraints only. [56] addressed complex questions by decomposing them into a sequence of simple questions, but relies on training data obtained via Amazon Mechanical Turk. Some methods start with KGs as a source for candidate answers and use text corpora like Wikipedia or ClueWeb as additional evidence [15,54,66], or start with answer sentences from text corpora and combine these with KGs for entity answers [50,55].…”

Section: Related Workmentioning

confidence: 99%

Answering Complex Questions by Joining Multi-Document Evidence with Quasi Knowledge Graphs

Pramanik

Roy

et al. 2019

Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

Direct answering of questions that involve multiple entities and relations is a challenge for text-based QA. This problem is most pronounced when answers can be found only by joining evidence from multiple documents. Curated knowledge graphs (KGs) may yield good answers, but are limited by their inherent incompleteness and potential staleness. This paper presents QUEST, a method that can answer complex questions directly from textual sources on-the-fly, by computing similarity joins over partial results from different documents. Our method is completely unsupervised, avoiding trainingdata bottlenecks and being able to cope with rapidly evolving ad hoc topics and formulation style in user questions. QUEST builds a noisy quasi KG with node and edge weights, consisting of dynamically retrieved entity names and relational phrases. It augments this graph with types and semantic alignments, and computes the best answers by an algorithm for Group Steiner Trees. We evaluate QUEST on benchmarks of complex questions, and show that it substantially outperforms state-of-the-art baselines.

show abstract

The Web as a Knowledge-Base for Answering Complex Questions

Cited by 393 publications

References 33 publications

PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text

PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text

Cognitive Graph for Multi-Hop Reading Comprehension at Scale

Answering Complex Questions by Joining Multi-Document Evidence with Quasi Knowledge Graphs

Contact Info

Product

Resources

About