Matches in SemOpenAlex for { <https://semopenalex.org/work/W4322759712> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4322759712 abstract "Mining large corpora can generate useful discoveries but is time-consuming for humans. We formulate a new task, D5, that automatically discovers differences between two large corpora in a goal-driven way. The task input is a problem comprising a research goal $textit{comparing the side effects of drug A and drug B}$ and a corpus pair (two large collections of patients' self-reported reactions after taking each drug). The output is a language description (discovery) of how these corpora differ (patients taking drug A $textit{mention feelings of paranoia}$ more often). We build a D5 system, and to quantitatively measure its performance, we 1) contribute a meta-dataset, OpenD5, aggregating 675 open-ended problems ranging across business, social sciences, humanities, machine learning, and health, and 2) propose a set of unified evaluation metrics: validity, relevance, novelty, and significance. With the dataset and the unified metrics, we confirm that language models can use the goals to propose more relevant, novel, and significant candidate discoveries. Finally, our system produces discoveries previously unknown to the authors on a wide range of applications in OpenD5, including temporal and demographic differences in discussion topics, political stances and stereotypes in speech, insights in commercial reviews, and error patterns in NLP models." @default.
- W4322759712 created "2023-03-03" @default.
- W4322759712 creator A5003241951 @default.
- W4322759712 creator A5004921249 @default.
- W4322759712 creator A5005720083 @default.
- W4322759712 creator A5046116522 @default.
- W4322759712 creator A5060196069 @default.
- W4322759712 creator A5066990330 @default.
- W4322759712 date "2023-02-27" @default.
- W4322759712 modified "2023-09-27" @default.
- W4322759712 title "Goal Driven Discovery of Distributional Differences via Language Descriptions" @default.
- W4322759712 doi "https://doi.org/10.48550/arxiv.2302.14233" @default.
- W4322759712 hasPublicationYear "2023" @default.
- W4322759712 type Work @default.
- W4322759712 citedByCount "0" @default.
- W4322759712 crossrefType "posted-content" @default.
- W4322759712 hasAuthorship W4322759712A5003241951 @default.
- W4322759712 hasAuthorship W4322759712A5004921249 @default.
- W4322759712 hasAuthorship W4322759712A5005720083 @default.
- W4322759712 hasAuthorship W4322759712A5046116522 @default.
- W4322759712 hasAuthorship W4322759712A5060196069 @default.
- W4322759712 hasAuthorship W4322759712A5066990330 @default.
- W4322759712 hasBestOaLocation W43227597121 @default.
- W4322759712 hasConcept C119857082 @default.
- W4322759712 hasConcept C154945302 @default.
- W4322759712 hasConcept C15744967 @default.
- W4322759712 hasConcept C158154518 @default.
- W4322759712 hasConcept C159985019 @default.
- W4322759712 hasConcept C162324750 @default.
- W4322759712 hasConcept C177264268 @default.
- W4322759712 hasConcept C17744445 @default.
- W4322759712 hasConcept C187736073 @default.
- W4322759712 hasConcept C192562407 @default.
- W4322759712 hasConcept C199360897 @default.
- W4322759712 hasConcept C199539241 @default.
- W4322759712 hasConcept C204321447 @default.
- W4322759712 hasConcept C204323151 @default.
- W4322759712 hasConcept C2522767166 @default.
- W4322759712 hasConcept C2778143727 @default.
- W4322759712 hasConcept C2778738651 @default.
- W4322759712 hasConcept C2780451532 @default.
- W4322759712 hasConcept C41008148 @default.
- W4322759712 hasConcept C77805123 @default.
- W4322759712 hasConceptScore W4322759712C119857082 @default.
- W4322759712 hasConceptScore W4322759712C154945302 @default.
- W4322759712 hasConceptScore W4322759712C15744967 @default.
- W4322759712 hasConceptScore W4322759712C158154518 @default.
- W4322759712 hasConceptScore W4322759712C159985019 @default.
- W4322759712 hasConceptScore W4322759712C162324750 @default.
- W4322759712 hasConceptScore W4322759712C177264268 @default.
- W4322759712 hasConceptScore W4322759712C17744445 @default.
- W4322759712 hasConceptScore W4322759712C187736073 @default.
- W4322759712 hasConceptScore W4322759712C192562407 @default.
- W4322759712 hasConceptScore W4322759712C199360897 @default.
- W4322759712 hasConceptScore W4322759712C199539241 @default.
- W4322759712 hasConceptScore W4322759712C204321447 @default.
- W4322759712 hasConceptScore W4322759712C204323151 @default.
- W4322759712 hasConceptScore W4322759712C2522767166 @default.
- W4322759712 hasConceptScore W4322759712C2778143727 @default.
- W4322759712 hasConceptScore W4322759712C2778738651 @default.
- W4322759712 hasConceptScore W4322759712C2780451532 @default.
- W4322759712 hasConceptScore W4322759712C41008148 @default.
- W4322759712 hasConceptScore W4322759712C77805123 @default.
- W4322759712 hasLocation W43227597121 @default.
- W4322759712 hasOpenAccess W4322759712 @default.
- W4322759712 hasPrimaryLocation W43227597121 @default.
- W4322759712 hasRelatedWork W1509467138 @default.
- W4322759712 hasRelatedWork W1704713987 @default.
- W4322759712 hasRelatedWork W2081647779 @default.
- W4322759712 hasRelatedWork W2106813246 @default.
- W4322759712 hasRelatedWork W3009120927 @default.
- W4322759712 hasRelatedWork W3088458052 @default.
- W4322759712 hasRelatedWork W3107474891 @default.
- W4322759712 hasRelatedWork W3185852197 @default.
- W4322759712 hasRelatedWork W3192308442 @default.
- W4322759712 hasRelatedWork W4287118475 @default.
- W4322759712 isParatext "false" @default.
- W4322759712 isRetracted "false" @default.
- W4322759712 workType "article" @default.