Asking Clarification Questions to Handle Ambiguity in Open-Domain QA

• URL: http://arxiv.org/abs/2305.13808v2
• Date: Wed, 25 Oct 2023 06:24:16 GMT
• Title: Asking Clarification Questions to Handle Ambiguity in Open-Domain QA
• Authors: Dongryeol Lee, Segwang Kim, Minwoo Lee, Hwanhee Lee, Joonsuk Park, Sang-Woo Lee and Kyomin Jung
• Abstract summary: We propose to ask a clarification question, where the user's response will help identify the interpretation that best aligns with the user's intention. We first present CAMBIGNQ, a dataset consisting of 5,654 ambiguous questions. We then define a pipeline of tasks and design appropriate evaluation metrics.
• Score: 25.80369529145732
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Ambiguous questions persist in open-domain question answering, because formulating a precise question with a unique answer is often challenging. Previously, Min et al. (2020) have tackled this issue by generating disambiguated questions for all possible interpretations of the ambiguous question. This can be effective, but not ideal for providing an answer to the user. Instead, we propose to ask a clarification question, where the user's response will help identify the interpretation that best aligns with the user's intention. We first present CAMBIGNQ, a dataset consisting of 5,654 ambiguous questions, each with relevant passages, possible answers, and a clarification question. The clarification questions were efficiently created by generating them using InstructGPT and manually revising them as necessary. We then define a pipeline of tasks and design appropriate evaluation metrics. Lastly, we achieve 61.3 F1 on ambiguity detection and 40.5 F1 on clarification-based QA, providing strong baselines for future work.

Related papers

• Detecting Temporal Ambiguity in Questions [16.434748534272014]
  Temporally ambiguous questions are one of the most common types of such questions. Our annotations focus on capturing temporal ambiguity to study the task of detecting temporally ambiguous questions. We propose a novel approach by using diverse search strategies based on disambiguated versions of the questions.
  arXiv  Detail & Related papers  (2024-09-25T15:59:58Z)
• Which questions should I answer? Salience Prediction of Inquisitive Questions [118.097974193544]
  We show that highly salient questions are empirically more likely to be answered in the same article. We further validate our findings by showing that answering salient questions is an indicator of summarization quality in news.
  arXiv  Detail & Related papers  (2024-04-16T21:33:05Z)
• Answering Ambiguous Questions with a Database of Questions, Answers, and Revisions [95.92276099234344]
  We present a new state-of-the-art for answering ambiguous questions that exploits a database of unambiguous questions generated from Wikipedia. Our method improves performance by 15% on recall measures and 10% on measures which evaluate disambiguating questions from predicted outputs.
  arXiv  Detail & Related papers  (2023-08-16T20:23:16Z)
• Answering Ambiguous Questions via Iterative Prompting [84.3426020642704]
  In open-domain question answering, due to the ambiguity of questions, multiple plausible answers may exist. One approach is to directly predict all valid answers, but this can struggle with balancing relevance and diversity. We present AmbigPrompt to address the imperfections of existing approaches to answering ambiguous questions.
  arXiv  Detail & Related papers  (2023-07-08T04:32:17Z)
• Answering Unanswered Questions through Semantic Reformulations in Spoken QA [20.216161323866867]
  Spoken Question Answering (QA) is a key feature of voice assistants, usually backed by multiple QA systems. We analyze failed QA requests to identify core challenges: lexical gaps, proposition types, complex syntactic structure, and high specificity. We propose a Semantic Question Reformulation (SURF) model offering three linguistically-grounded operations (repair, syntactic reshaping, generalization) to rewrite questions to facilitate answering.
  arXiv  Detail & Related papers  (2023-05-27T07:19:27Z)
• CREPE: Open-Domain Question Answering with False Presuppositions [92.20501870319765]
  We introduce CREPE, a QA dataset containing a natural distribution of presupposition failures from online information-seeking forums. We find that 25% of questions contain false presuppositions, and provide annotations for these presuppositions and their corrections. We show that adaptations of existing open-domain QA models can find presuppositions moderately well, but struggle when predicting whether a presupposition is factually correct.
  arXiv  Detail & Related papers  (2022-11-30T18:54:49Z)
• ASQA: Factoid Questions Meet Long-Form Answers [35.11889930792675]
  This work focuses on factoid questions that are ambiguous, that is, have different correct answers depending on interpretation. Answers to ambiguous questions should synthesize factual information from multiple sources into a long-form summary. We use this notion of correctness to define an automated metric of performance for ASQA.
  arXiv  Detail & Related papers  (2022-04-12T21:58:44Z)
• GooAQ: Open Question Answering with Diverse Answer Types [63.06454855313667]
  We present GooAQ, a large-scale dataset with a variety of answer types. This dataset contains over 5 million questions and 3 million answers collected from Google.
  arXiv  Detail & Related papers  (2021-04-18T05:40:39Z)
• Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction [46.38201136570501]
  We present a model that aggregates and combines evidence from multiple passages to adaptively predict a single answer or a set of question-answer pairs for ambiguous questions. Our model, named Refuel, achieves a new state-of-the-art performance on the AmbigQA dataset, and shows competitive performance on NQ-Open and TriviaQA.
  arXiv  Detail & Related papers  (2020-11-26T05:48:55Z)
• AmbigQA: Answering Ambiguous Open-domain Questions [99.59747941602684]
  We introduce AmbigQA, a new open-domain question answering task which involves finding every plausible answer. To study this task, we construct AmbigNQ, a dataset covering 14,042 questions from NQ-open. We find that over half of the questions in NQ-open are ambiguous, with diverse sources of ambiguity such as event and entity references.
  arXiv  Detail & Related papers  (2020-04-22T15:42:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.