Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320167385> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4320167385 abstract "Logical rules, both transferable and explainable, are widely used as weakly supervised signals for many downstream tasks such as named entity tagging. To reduce the human effort of writing rules, previous researchers adopt an iterative approach to automatically learn logical rules from several seed rules. However, obtaining more seed rules can only be accomplished by extra human annotation with heavy costs. Limited by the size and quality of the seed rules, the model performance of previous systems is bounded. In this paper, we develop a novel framework STREAM to distill task-specific logical rules from large pre-trained models. Specifically, we borrow recent prompt-based language models as the knowledge expert to yield initial seed rules, and based on the formed high-quality instance pool that acts as an intermediary role, we keep teaching the expert to fit our task and learning task-specific logical rules. Experiments on three public named entity tagging benchmarks demonstrate the effectiveness of our proposed framework. With several predefined prompt templates, our system has gained significant improvements over previous state-of-the-art methods." @default.
- W4320167385 created "2023-02-13" @default.
- W4320167385 creator A5009379173 @default.
- W4320167385 creator A5011773760 @default.
- W4320167385 creator A5024818901 @default.
- W4320167385 creator A5039812037 @default.
- W4320167385 creator A5062552218 @default.
- W4320167385 creator A5063062444 @default.
- W4320167385 date "2022-10-06" @default.
- W4320167385 modified "2023-09-29" @default.
- W4320167385 title "Distilling Task-specific Logical Rules from Large Pre-trained Models" @default.
- W4320167385 doi "https://doi.org/10.48550/arxiv.2210.02768" @default.
- W4320167385 hasPublicationYear "2022" @default.
- W4320167385 type Work @default.
- W4320167385 citedByCount "0" @default.
- W4320167385 crossrefType "posted-content" @default.
- W4320167385 hasAuthorship W4320167385A5009379173 @default.
- W4320167385 hasAuthorship W4320167385A5011773760 @default.
- W4320167385 hasAuthorship W4320167385A5024818901 @default.
- W4320167385 hasAuthorship W4320167385A5039812037 @default.
- W4320167385 hasAuthorship W4320167385A5062552218 @default.
- W4320167385 hasAuthorship W4320167385A5063062444 @default.
- W4320167385 hasBestOaLocation W43201673851 @default.
- W4320167385 hasConcept C111472728 @default.
- W4320167385 hasConcept C119857082 @default.
- W4320167385 hasConcept C134752490 @default.
- W4320167385 hasConcept C138885662 @default.
- W4320167385 hasConcept C154945302 @default.
- W4320167385 hasConcept C162324750 @default.
- W4320167385 hasConcept C187736073 @default.
- W4320167385 hasConcept C204321447 @default.
- W4320167385 hasConcept C2776321320 @default.
- W4320167385 hasConcept C2779530757 @default.
- W4320167385 hasConcept C2780451532 @default.
- W4320167385 hasConcept C41008148 @default.
- W4320167385 hasConceptScore W4320167385C111472728 @default.
- W4320167385 hasConceptScore W4320167385C119857082 @default.
- W4320167385 hasConceptScore W4320167385C134752490 @default.
- W4320167385 hasConceptScore W4320167385C138885662 @default.
- W4320167385 hasConceptScore W4320167385C154945302 @default.
- W4320167385 hasConceptScore W4320167385C162324750 @default.
- W4320167385 hasConceptScore W4320167385C187736073 @default.
- W4320167385 hasConceptScore W4320167385C204321447 @default.
- W4320167385 hasConceptScore W4320167385C2776321320 @default.
- W4320167385 hasConceptScore W4320167385C2779530757 @default.
- W4320167385 hasConceptScore W4320167385C2780451532 @default.
- W4320167385 hasConceptScore W4320167385C41008148 @default.
- W4320167385 hasLocation W43201673851 @default.
- W4320167385 hasOpenAccess W4320167385 @default.
- W4320167385 hasPrimaryLocation W43201673851 @default.
- W4320167385 hasRelatedWork W151193258 @default.
- W4320167385 hasRelatedWork W1584192349 @default.
- W4320167385 hasRelatedWork W1607472309 @default.
- W4320167385 hasRelatedWork W2081647779 @default.
- W4320167385 hasRelatedWork W2251869843 @default.
- W4320167385 hasRelatedWork W3107474891 @default.
- W4320167385 hasRelatedWork W3185852197 @default.
- W4320167385 hasRelatedWork W38394648 @default.
- W4320167385 hasRelatedWork W97423259 @default.
- W4320167385 hasRelatedWork W2611524888 @default.
- W4320167385 isParatext "false" @default.
- W4320167385 isRetracted "false" @default.
- W4320167385 workType "article" @default.