A Proposal for Evaluating Answer Distillation from Web Data

7 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

MS MARCO: A Human Generated MAchine Reading COmprehension Dataset (2016, methodology): “As shown in subsection 4.1 and 4.2, we use accuracy and precision-recall to measure the quality of the numeric answers, and apply metrics like ROUGE-L [23] and phrasing-aware evaluation framework [24] for long textual answers.”
MS MARCO: A Human Generated MAchine Reading COmprehension Dataset (2016, methodology): “We use accuracy and precision-recall measures for numeric answers and apply metrics like ROUGE-L [Lin, 2004] and phrasing-aware evaluation framework [Mitra et al., 2016] for long textual answers.”
A Deep Look into Neural Ranking Models for Information Retrieval (2019, methodology): “e been a variety of task formats for QA, including multiple-choice selection [52], answer passage/sentence retrieval [53, 37], answer span locating [54], and answer synthesizing from multiple sources [55]. In this survey, we focus on answer passage/sentence retrieval as it can be viewed as a typical”