Question Answering for the Curated Web: Tasks and Methods in QA over Knowledge Bases and Text Collections

Roy, Rishiraj Saha; Anand, Avishek

doi:10.2200/s0113ed1v01y202109icr076

Cited by 27 publications

(2 citation statements)

References 118 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We performed a user study to highlight the utility of our extractive explanations to human users. We believe that the applicability of a sparsity-inducing component can extend beyond document ranking to other ranking [27,28,72], graph [17], and web tasks [4,61,70].…”

Section: Discussionmentioning

confidence: 99%

“…Information prioritization is an essential and important problem to reduce information overload in a large multitude of Web-based tasks like question-answering [61], fact verification [76] and conversational search [4]. Prioritizing information relies on retrieving a small set of highly relevant knowledge units from a large source of world knowledge contained in unstructured text collections with web and textual knowledge bases like Wikipedia that contain documents and articles.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Extractive Explanations for Interpretable Text Ranking

Leonhardt

Rudra

Anand

2023

ACM Trans. Inf. Syst.

Self Cite

View full text Add to dashboard Cite

Neural document ranking models perform impressively well due to superior language understanding gained from pre-training tasks. However, due to their complexity and large number of parameters, these (typically transformer-based) models are often non-interpretable in that ranking decisions can not be clearly attributed to specific parts of the input documents. In this paper we propose ranking models that are inherently interpretable by generating explanations as a by-product of the prediction decision. We introduce the Select-And-Rank paradigm for document ranking, where we first output an explanation as a selected subset of sentences in a document. Thereafter, we solely use the explanation or selection to make the prediction, making explanations first-class citizens in the ranking process. Technically, we treat sentence selection as a latent variable trained jointly with the ranker from the final output. To that end, we propose an end-to-end training technique for Select-And-Rank models utilizing reparameterizable subset sampling using the Gumbel-max trick . We conduct extensive experiments to demonstrate that our approach is competitive to state-of-the-art methods. Our approach is broadly applicable to numerous ranking tasks and furthers the goal of building models that are interpretable by design . Finally, we present real-world applications that benefit from our sentence selection method.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Extractive Explanations for Interpretable Text Ranking

Leonhardt

Rudra

Anand

2023

ACM Trans. Inf. Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

Beyond NED

Christmann

Roy

Weikum

2022

Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

Answering complex questions over knowledge bases (KB-QA) faces huge input data with billions of facts, involving millions of entities and thousands of predicates. For efficiency, QA systems first reduce the answer search space by identifying a set of facts that is likely to contain all answers and relevant cues. The most common technique for doing this is to apply named entity disambiguation (NED) on the question, and retrieve KB facts for the disambiguated entities. This work presents Clocq, an efficient method that prunes irrelevant parts of the search space using KB-aware signals. Clocq uses a top-𝑘 query processor over score-ordered lists of KB items that combine signals about lexical matching, relevance to the question, coherence among candidate items, and connectivity in the KB graph. Experiments with two recent QA benchmarks for complex questions demonstrate the superiority of Clocq over state-of-theart baselines with respect to answer presence, size of the search space, and runtimes. CCS CONCEPTS• Information systems → Question answering.

show abstract