paper-with-me

Papers

How do we answer complex questions: Discourse structure of long form answers

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Long form answers, consisting of multiple sentences, can provide nuanced and comprehensive answers to a broader set of questions. However, little prior work exists on this task. To better understand this complex task, we study the functional structure of long form answers on two datasets, Natural Questions~\cite{kwiatkowski2019natural} and ELI5~\cite{Fan2019ELI5LF}. Our main goal is to understand how humans organize information to craft complex answers. We develop an ontology of sentence-level functional roles for long form answers, and annotate 3.3k sentences in 542 examples. Our annotated data enables training a reliable role classifier that can be used for automatic analysis and thus reveals machine generated answers are structured worse than human written answers. Our data further yields an extractive summarization dataset for long form answers, giving models the ability to identify a concise answer to a complex query.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Extractive SummarizationFormNatural QuestionsSentence

Similar Papers 제목 키워드 기반

How Do We Answer Complex Questions: Discourse Structure of Long-form Answers

2022-03-21 · ACL 2022 5 · Fangyuan Xu, Junyi Jessy Li, Eunsol Choi

Long-form answers, consisting of multiple sentences, can provide nuanced and comprehensive answers to a broader set of questions. To better understand this complex and understudied task, we study the functional structure…

FormNatural QuestionsSentence

Discourse-Based Approach to Involvement of Background Knowledge for Question Answering

2019-09-01 · RANLP 2019 9 · Boris Galitsky, Dmitry Ilvovsky

We introduce a concept of a virtual discourse tree to improve question answering (Q/A) recall for complex, multi-sentence questions. Augmenting the discourse tree of an answer with tree fragments obtained from text corpo…

Question AnsweringSentence

Discourse Analysis via Questions and Answers: Parsing Dependency Structures of Questions Under Discussion

2022-10-12 · Wei-Jen Ko, Yating Wu, Cutter Dalton, Dananjay Srinivas 외

Automatic discourse processing is bottlenecked by data: current discourse formalisms pose highly demanding annotation tasks involving large taxonomies of discourse relations, making them inaccessible to lay annotators. T…

Dependency ParsingQuestion AnsweringSentence

Discourse Comprehension: A Question Answering Framework to Represent Sentence Connections

2021-11-01 · Wei-Jen Ko, Cutter Dalton, Mark Simmons, Eliza Fisher 외

While there has been substantial progress in text comprehension through simple factoid question answering, more holistic comprehension of a discourse still presents a major challenge (Dunietz et al., 2020). Someone criti…

Question AnsweringReading ComprehensionSentence

Relying on Discourse Analysis to Answer Complex Questions by Neural Machine Reading Comprehension

2021-09-01 · RANLP 2021 9 · Boris Galitsky, Dmitry Ilvovsky, Elizaveta Goncharova

Machine reading comprehension (MRC) is one of the most challenging tasks in natural language processing domain. Recent state-of-the-art results for MRC have been achieved with the pre-trained language models, such as BER…

Machine Reading ComprehensionQuestion AnsweringReading Comprehension