Skip to main content

Vocabulary of natural language processing

Search from vocabulary

  • Help
align
annotate
download

Concept information

applied NLP > human-computer interaction > question answering system > machine reading comprehension

Preferred term

machine reading comprehension  

Definition

  • A task that requires machines to read a text, comprehend given passages and answer questions related to the text. (Cui et al., ExpMRC: explainability evaluation for machine reading comprehension, in Heliyon, 2022)

Broader concept

Synonym(s)

  • extractive question answering
  • MRC
  • reading comprehension

Definitional context(s)

  • Extractive question answering (extractive QA) aims to provide answer spans extracted from the context to answer questions. (Nie, Huang, Chi & Mao, 2022)
  • Extractive Question Answering (Extractive-QA) is a common and widely used task where a model is tasked with locating and reproducing an answer to a question posed directly with regard to a source text. (Cohen, Merhav-Fine, Goldberg & Tsarfaty, 2023)
  • Extractive question answering is a common task in NLP where the goal is to select a contiguous span a from a given text T that answers a question Q. (Ram, Kirstain, Berant, Globerson & Levy, 2021)
  • Machine reading comprehension aims to assess the ability to comprehend natural language and answer questions from a given document or passage. (Zheng, Huang & Sun, 2019)
  • Machine reading comprehension (MRC) reflects the ability to read and understand an unstructured text and answer questions regarding it. (Galitsky, Ilvovsky & Goncharova, 2021)

Example

  • Also MRC failed to match the question with the sentence "However clinicians are not always able to find out which germ caused someone to get sick with pneumonia.". (Galitsky, Ilvovsky & Goncharova, 2021)
  • Machine reading comprehension has been increasingly studied in the NLP area which aims to read a given passage and then answer questions correctly. (Yeh & Chen, 2019)
  • MRC is the ability to answer the question based on the input paragraph of the text. (Galitsky, Ilvovsky & Goncharova, 2021)
  • On top of this feature extractor we add a linear layer for extractive question answers whose output dimension is two. (Yin, Wang, Dong & Ling, 2024)

In other languages

URI

http://data.loterre.fr/ark:/67375/8LP-ZWNX93XW-B

Download this concept:

RDF/XML TURTLE JSON-LD Last modified 6/26/24