Skip to content

Language Modeling Broadened to Account for Discourse Aspects (LAMBADA)

Natural Language UnderstandingLanguage ModelingEnglish

Created by Paperno et al. at 2016, the Language Modeling Broadened to Account for Discourse Aspects (LAMBADA) is a natural language understanding dataset in English containing 10,022 records in Text format.

About Language Modeling Broadened to Account for Discourse Aspects (LAMBADA)

Dataset contains narrative passages sharing the characteristic that human subjects are able to guess their last word if they are exposed to the whole passage, but not if they only see the last sentence preceding the target word.

Details

Task
Natural Language Understanding, Language Modeling
Language
English
Format
Text
Rows / instances
10,022
Creator
Paperno et al.
Year
2016
Download Paper

FAQ