Search-based Neural Structured Learning for Sequential Question Answering

Iyyer, Mohit; Yih, Wen-tau; Chang, Ming‐Wei

doi:10.18653/v1/p17-1167

Cited by 162 publications

(216 citation statements)

References 18 publications

(22 reference statements)

Supporting

Mentioning

216

Contrasting

Order By: Relevance

“…QBLink [9], CoQA [27], ans ShARC [29] are recent resources for sequential QA over text. The SQA resource [16], derived from WikiTableQuestions [25], is aimed at driving conversational QA over (relatively small) Web tables.…”

Section: The Convquestions Benchmark 41 Benchmark Creationmentioning

confidence: 99%

Look before you Hop: Conversational Question Answering over Knowledge Graphs Using Judicious Context Expansion

Christmann

Roy

Abujabal

et al. 2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

114

View full text Add to dashboard Cite

Fact-centric information needs are rarely one-shot; users typically ask follow-up questions to explore a topic. In such a conversational setting, the user's inputs are often incomplete, with entities or predicates left out, and ungrammatical phrases. This poses a huge challenge to question answering (QA) systems that typically rely on cues in full-fledged interrogative sentences. As a solution, we develop Convex: an unsupervised method that can answer incomplete questions over a knowledge graph (KG) by maintaining conversation context using entities and predicates seen so far and automatically inferring missing or ambiguous pieces for follow-up questions. The core of our method is a graph exploration algorithm that judiciously expands a frontier to find candidate answers for the current question. To evaluate Convex, we release ConvQuestions, a crowdsourced benchmark with 11, 200 distinct conversations from five different domains. We show that Convex: (i) adds conversational support to any stand-alone QA system, and (ii) outperforms state-of-the-art baselines and question completion strategies.

show abstract

Section: The Convquestions Benchmark 41 Benchmark Creationmentioning

confidence: 99%

Look before you Hop: Conversational Question Answering over Knowledge Graphs Using Judicious Context Expansion

Christmann

Roy

Abujabal

et al. 2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

114

View full text Add to dashboard Cite

show abstract

“…The execution results will be used to calculate the Jaccard coefficient with respect to the labeled answers as the approximated rewards. The use of approximated reward has been proven to be effective in (Iyyer et al, 2017). …”

Section: Discussionmentioning

confidence: 99%

Maximum Margin Reward Networks for Learning from Explicit and Implicit Supervision

Peng¹,

Chang²,

Yih³

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Self Cite

View full text Add to dashboard Cite

Neural networks have achieved state-ofthe-art performance on several structuredoutput prediction tasks, trained in a fully supervised fashion. However, annotated examples in structured domains are often costly to obtain, which thus limits the applications of neural networks. In this work, we propose Maximum Margin Reward Networks, a neural networkbased framework that aims to learn from both explicit (full structures) and implicit supervision signals (delayed feedback on the correctness of the predicted structure). On named entity recognition and semantic parsing, our model outperforms previous systems on the benchmark datasets, CoNLL-2003 and WebQuestionsSP.

show abstract

“…For example, given the precedent query "what's the biggest zone?" and the follow-up query "the smallest one", STAR prefers to recognize "the biggest zone" and "the smallest one" as two spans, rather (Iyyer et al, 2017) 70.9 35.8 NP (Neelakantan et al, 2016) 58.9 35.9 NP + STAR 58.9 38.1 DynSP + STAR 70.9 39.5 DynSP * (Iyyer et al, 2017) 70.4 41.1 than perform split operations inside them. The SplitNet fails probably because the conflicting spans, "the biggest" ↔ "the smallest" and "zone" ↔ "one", are adjacent, which makes it difficult to identify span boundaries well.…”

Section: Error Analysismentioning

confidence: 99%

A Split-and-Recombine Approach for Follow-up Query Analysis

Liu

Chen

Liu

et al. 2019

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

View full text Add to dashboard Cite

Context-dependent semantic parsing has proven to be an important yet challenging task. To leverage the advances in contextindependent semantic parsing, we propose to perform follow-up query analysis, aiming to restate context-dependent natural language queries with contextual information.To accomplish the task, we propose STAR, a novel approach with a well-designed two-phase process. It is parser-independent and able to handle multifarious follow-up scenarios in different domains. Experiments on the FollowUp dataset show that STAR outperforms the state-of-the-art baseline by a large margin of nearly 8%. The superiority on parsing results verifies the feasibility of follow-up query analysis. We also explore the extensibility of STAR on the SQA dataset, which is very promising.

show abstract

Search-based Neural Structured Learning for Sequential Question Answering

Cited by 162 publications

References 18 publications

Look before you Hop: Conversational Question Answering over Knowledge Graphs Using Judicious Context Expansion

Look before you Hop: Conversational Question Answering over Knowledge Graphs Using Judicious Context Expansion

Maximum Margin Reward Networks for Learning from Explicit and Implicit Supervision

A Split-and-Recombine Approach for Follow-up Query Analysis

Contact Info

Product

Resources

About