paper-with-me

Papers

Answer-based Adversarial Training for Generating Clarification Questions

2019-04-04 · NAACL 2019 6 · Sudha Rao, Hal Daumé III

We present an approach for generating clarification questions with the goal of eliciting new information that would make the given textual context more complete. We propose that modeling hypothetical answers (to clarification questions) as latent variables can guide our approach into generating more useful clarification questions. We develop a Generative Adversarial Network (GAN) where the generator is a sequence-to-sequence model and the discriminator is a utility function that models the value of updating the context with the answer to the clarification question. We evaluate on two datasets, using both automatic metrics and human judgments of usefulness, specificity and relevance, showing that our approach outperforms both a retrieval-based model and ablations that exclude the utility model and the adversarial training.

📄 PDF Abstract BibTeX arXiv:1904.02281

Code (1)

raosudha89/clarification_question_generation_pytorch 공식 구현 pytorch

Tasks

Generative Adversarial NetworkRetrievalSpecificity

Similar Papers 제목 키워드 기반

Asking Clarification Questions to Handle Ambiguity in Open-Domain QA

2023-05-23 · Dongryeol Lee, Segwang Kim, Minwoo Lee, Hwanhee Lee 외

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 disambi…

Open-Domain Question AnsweringQuestion Answering

Asking What Matters: Reward-Driven Clarification for Software Engineering Tasks

2026-04-16 · Sanidhya Vijayvargiya, Vijay Viswanathan, Graham Neubig arxiv

Humans often specify tasks incompletely, so assistants must know when and how to ask clarifying questions. However, effective clarification remains challenging in software engineering tasks as not all missing information…

Reinforcement Learning

ClarQ: A large-scale and diverse dataset for Clarification Question Generation

2020-06-10 · ACL 2020 6 · Vaibhav Kumar, Alan W. black

Question answering and conversational systems are often baffled and need help clarifying certain ambiguities. However, limitations of existing datasets hinder the development of large-scale models capable of generating a…

Question AnsweringQuestion GenerationQuestion-Generation

Abg-CoQA: Clarifying Ambiguity in Conversational Question Answering

2021-06-22 · AKBC 2021 10 · Meiqi Guo, Mingda Zhang, Siva Reddy, Malihe Alikhani

Effective communication is about the dissemination of properly worded meaningful ideas/messages that are comprehensible to both sender and receiver and which ultimately can attract the desired response or feedba…

4kConversational Question AnsweringQuestion AnsweringText Generation

RAC: Retrieval-Augmented Clarification for Faithful Conversational Search

2026-01-16 · Ahmed Rayane Kebir, Vincent Guigue, Lynda Said Lhadj, Laure Soulier arxiv

Clarification questions help conversational search systems resolve ambiguous or underspecified user queries. While prior work has focused on fluency and alignment with user intent, especially through facet extraction, mu…