Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912982029> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2912982029 abstract "Humans routinely learn new concepts using natural language communications,even in scenarios with limited or no labeled examples. For example, ahuman can learn the concept of a phishing email from natural language explanationssuch as ‘phishing emails often request your bank account number’.On the other hand, purely inductive learning systems typically require a largecollection of labeled data for learning such a concept. We believe that advancesin Computational Linguistics and the growing ubiquity of computing devicestogether can enable people to teach computers classification tasks using naturallanguage interactions.Learning from language presents some key challenges. A preliminary challengelies in the basic problem of learning to interpret language, which refersto an agent’s ability to map natural language explanations in pedagogical contextsto formal semantic representations that computers can process and reasonover. A second challenge is that of learning from interpretations, which refersto the mechanisms through which interpretations of language statements canbe used by computers to solve learning tasks in the environment. We addressaspects of both these problems, and provide an interface for guiding conceptlearning methods using language.For learning from interpretation, we focus on concept learning (binary classification)tasks. We demonstrate that language can define rich and expressivefeatures for learning tasks, and show that machine learning can benefit substantiallyfrom this ability. We also investigate assimilation of linguistic cuesin everyday language that implicitly provide constraints for classification models(e.g., ‘Most emails are not phishing emails’). In particular, we focus onconditional statements and linguistic quantifiers (such as usually, never, etc.),and show that such advice can be used to train classifiers even with few or nolabeled examples of a concept.For learning to interpret, we develop new algorithms for semantic parsingthat incorporate pragmatic cues, including conversational history and sensoryobservation, to improve automatic language interpretation. We show that environmentalcontext can enrich semantic parsing methods by not only providingdiscriminative features, but also reducing the need for expensive labeled dataused for training them.A separate but immensely valuable attribute of human language is thatit is inherently conversational and interactive. We also briefly explore thepossibility of agents that can learn to interact with a human teacher in a mixedinitiativesetting, where the learner can also proactively engage the teacher byasking questions, rather than only passively listen. We develop a reinforcelearning framework for learning effective question asking strategies in contextof conversational concept learning." @default.
- W2912982029 created "2019-02-21" @default.
- W2912982029 creator A5090095198 @default.
- W2912982029 date "2018-09-01" @default.
- W2912982029 modified "2023-09-24" @default.
- W2912982029 title "Teaching Machines to Classify from Natural Language Interactions" @default.
- W2912982029 cites W2145215286 @default.
- W2912982029 cites W2146411805 @default.
- W2912982029 cites W2163234897 @default.
- W2912982029 cites W2963281204 @default.
- W2912982029 cites W92973652 @default.
- W2912982029 doi "https://doi.org/10.1184/r1/7553933.v1" @default.
- W2912982029 hasPublicationYear "2018" @default.
- W2912982029 type Work @default.
- W2912982029 sameAs 2912982029 @default.
- W2912982029 citedByCount "1" @default.
- W2912982029 countsByYear W29129820292020 @default.
- W2912982029 crossrefType "dissertation" @default.
- W2912982029 hasAuthorship W2912982029A5090095198 @default.
- W2912982029 hasConcept C113843644 @default.
- W2912982029 hasConcept C120665830 @default.
- W2912982029 hasConcept C121332964 @default.
- W2912982029 hasConcept C129307140 @default.
- W2912982029 hasConcept C129353971 @default.
- W2912982029 hasConcept C154945302 @default.
- W2912982029 hasConcept C155092808 @default.
- W2912982029 hasConcept C157915830 @default.
- W2912982029 hasConcept C173608175 @default.
- W2912982029 hasConcept C192209626 @default.
- W2912982029 hasConcept C195324797 @default.
- W2912982029 hasConcept C204321447 @default.
- W2912982029 hasConcept C2779439875 @default.
- W2912982029 hasConcept C32254414 @default.
- W2912982029 hasConcept C41008148 @default.
- W2912982029 hasConcept C67463725 @default.
- W2912982029 hasConcept C77967617 @default.
- W2912982029 hasConcept C83479923 @default.
- W2912982029 hasConceptScore W2912982029C113843644 @default.
- W2912982029 hasConceptScore W2912982029C120665830 @default.
- W2912982029 hasConceptScore W2912982029C121332964 @default.
- W2912982029 hasConceptScore W2912982029C129307140 @default.
- W2912982029 hasConceptScore W2912982029C129353971 @default.
- W2912982029 hasConceptScore W2912982029C154945302 @default.
- W2912982029 hasConceptScore W2912982029C155092808 @default.
- W2912982029 hasConceptScore W2912982029C157915830 @default.
- W2912982029 hasConceptScore W2912982029C173608175 @default.
- W2912982029 hasConceptScore W2912982029C192209626 @default.
- W2912982029 hasConceptScore W2912982029C195324797 @default.
- W2912982029 hasConceptScore W2912982029C204321447 @default.
- W2912982029 hasConceptScore W2912982029C2779439875 @default.
- W2912982029 hasConceptScore W2912982029C32254414 @default.
- W2912982029 hasConceptScore W2912982029C41008148 @default.
- W2912982029 hasConceptScore W2912982029C67463725 @default.
- W2912982029 hasConceptScore W2912982029C77967617 @default.
- W2912982029 hasConceptScore W2912982029C83479923 @default.
- W2912982029 hasLocation W29129820291 @default.
- W2912982029 hasOpenAccess W2912982029 @default.
- W2912982029 hasPrimaryLocation W29129820291 @default.
- W2912982029 hasRelatedWork W1501126425 @default.
- W2912982029 hasRelatedWork W1531393276 @default.
- W2912982029 hasRelatedWork W1608059655 @default.
- W2912982029 hasRelatedWork W2073381168 @default.
- W2912982029 hasRelatedWork W2140244685 @default.
- W2912982029 hasRelatedWork W2460580556 @default.
- W2912982029 hasRelatedWork W2466897270 @default.
- W2912982029 hasRelatedWork W2736695557 @default.
- W2912982029 hasRelatedWork W2758782048 @default.
- W2912982029 hasRelatedWork W2766990604 @default.
- W2912982029 hasRelatedWork W2962792000 @default.
- W2912982029 hasRelatedWork W2978165923 @default.
- W2912982029 hasRelatedWork W3004304303 @default.
- W2912982029 hasRelatedWork W3128954351 @default.
- W2912982029 hasRelatedWork W3130558314 @default.
- W2912982029 hasRelatedWork W3136275640 @default.
- W2912982029 hasRelatedWork W3196463170 @default.
- W2912982029 hasRelatedWork W643027706 @default.
- W2912982029 hasRelatedWork W87415491 @default.
- W2912982029 hasRelatedWork W2107658862 @default.
- W2912982029 isParatext "false" @default.
- W2912982029 isRetracted "false" @default.
- W2912982029 magId "2912982029" @default.
- W2912982029 workType "dissertation" @default.