Specifically, Semi-extractive Multi-source QA (SEMQA) requires models to output a comprehensive answer, while mixing factual quoted spans -- copied verbatim from given input sources -- and non-factual free-text connectors that glue these spans together into a single cohesive passage.
Nov 8, 2023
QuoteSum is a textual QA dataset containing Semi-Extractive Multi-source Question Answering (SEMQA) examples written by humans, based on Wikipedia passages.
This work introduces a new QA task for answering multi-answer questions by summarizing multiple diverse sources in a semi-extractive fashion, ...
Rating
(1)
A new QA task where models generate comprehensive answers by combining verbatim quotes from multiple sources with free-text connectors.
Jul 28, 2024 · Conclusions The RxWhyQA data set can be used to train and evaluate systems that need to handle multianswer and multifocus questions.
Jul 1, 2024 · This paper introduces a novel question answering task called Semi-extractive Multi-source QA (SEMQA), which requires models to generate comprehensive answers.
Nov 13, 2023 · New paper: "SEMQA: Semi-Extractive Multi-Source Question Answering" Answers combine extracted spans with free text -> better attributions ...
People also ask
What is the difference between extractive question answering and generative question answering?
What is extractive question answering?
What is the difference between extractive and abstractive question answering?
What is SemBioNLQA a semantic biomedical question answering system for retrieving exact and ideal answers to natural language questions?
Nov 8, 2023 · Specifically, Semi-extractive Multi-source QA (SEMQA) requires models to outputa comprehensive answer, while mixing factual quoted spans -- ...
Rating
(3)
The paper “SEMQA: Semi-Extractive Multi-Source Question Answering” introduces a new QA task where models generate comprehensive answers by combining verbatim ...
SEMQA: Semi-Extractive Multi-Source Question Answering · Tal Schuster · Adam Lelkes. Haitian Sun. Jai Gupta · Jonathan Berant · William Cohen · Don Metzler.