Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951342697> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2951342697 abstract "We consider the problem of learning a certain type of lexical semantic knowledge that can be expressed as a binary relation between words, such as the so-called sub-categorization of verbs (a verb-noun relation) and the compound noun phrase relation (a noun-noun relation). Specifically, we view this problem as an on-line learning problem in the sense of Littlestone's learning model in which the learner's goal is to minimize the total number of prediction mistakes. In the computational learning theory literature, Goldman, Rivest and Schapire and subsequently Goldman and Warmuth have considered the on-line learning problem for binary relations R : X * Y -> {0, 1} in which one of the domain sets X can be partitioned into a relatively small number of types, namely clusters consisting of behaviorally indistinguishable members of X. In this paper, we extend this model and suppose that both of the sets X, Y can be partitioned into a small number of types, and propose a host of prediction algorithms which are two-dimensional extensions of Goldman and Warmuth's weighted majority type algorithm proposed for the original model. We apply these algorithms to the learning problem for the `compound noun phrase' relation, in which a noun is related to another just in case they can form a noun phrase together. Our experimental results show that all of our algorithms out-perform Goldman and Warmuth's algorithm. We also theoretically analyze the performance of one of our algorithms, in the form of an upper bound on the worst case number of prediction mistakes it makes." @default.
- W2951342697 created "2019-06-27" @default.
- W2951342697 creator A5060856151 @default.
- W2951342697 creator A5067632149 @default.
- W2951342697 creator A5086275760 @default.
- W2951342697 date "1995-07-24" @default.
- W2951342697 modified "2023-09-25" @default.
- W2951342697 title "On-line Learning of Binary Lexical Relations Using Two-dimensional Weighted Majority Algorithms" @default.
- W2951342697 hasPublicationYear "1995" @default.
- W2951342697 type Work @default.
- W2951342697 sameAs 2951342697 @default.
- W2951342697 citedByCount "0" @default.
- W2951342697 crossrefType "posted-content" @default.
- W2951342697 hasAuthorship W2951342697A5060856151 @default.
- W2951342697 hasAuthorship W2951342697A5067632149 @default.
- W2951342697 hasAuthorship W2951342697A5086275760 @default.
- W2951342697 hasConcept C11413529 @default.
- W2951342697 hasConcept C118615104 @default.
- W2951342697 hasConcept C121934690 @default.
- W2951342697 hasConcept C124101348 @default.
- W2951342697 hasConcept C153962237 @default.
- W2951342697 hasConcept C154945302 @default.
- W2951342697 hasConcept C18903297 @default.
- W2951342697 hasConcept C204321447 @default.
- W2951342697 hasConcept C25343380 @default.
- W2951342697 hasConcept C2776224158 @default.
- W2951342697 hasConcept C2776397901 @default.
- W2951342697 hasConcept C2777299769 @default.
- W2951342697 hasConcept C33923547 @default.
- W2951342697 hasConcept C41008148 @default.
- W2951342697 hasConcept C48372109 @default.
- W2951342697 hasConcept C65180967 @default.
- W2951342697 hasConcept C86803240 @default.
- W2951342697 hasConcept C94124525 @default.
- W2951342697 hasConcept C94375191 @default.
- W2951342697 hasConceptScore W2951342697C11413529 @default.
- W2951342697 hasConceptScore W2951342697C118615104 @default.
- W2951342697 hasConceptScore W2951342697C121934690 @default.
- W2951342697 hasConceptScore W2951342697C124101348 @default.
- W2951342697 hasConceptScore W2951342697C153962237 @default.
- W2951342697 hasConceptScore W2951342697C154945302 @default.
- W2951342697 hasConceptScore W2951342697C18903297 @default.
- W2951342697 hasConceptScore W2951342697C204321447 @default.
- W2951342697 hasConceptScore W2951342697C25343380 @default.
- W2951342697 hasConceptScore W2951342697C2776224158 @default.
- W2951342697 hasConceptScore W2951342697C2776397901 @default.
- W2951342697 hasConceptScore W2951342697C2777299769 @default.
- W2951342697 hasConceptScore W2951342697C33923547 @default.
- W2951342697 hasConceptScore W2951342697C41008148 @default.
- W2951342697 hasConceptScore W2951342697C48372109 @default.
- W2951342697 hasConceptScore W2951342697C65180967 @default.
- W2951342697 hasConceptScore W2951342697C86803240 @default.
- W2951342697 hasConceptScore W2951342697C94124525 @default.
- W2951342697 hasConceptScore W2951342697C94375191 @default.
- W2951342697 hasLocation W29513426971 @default.
- W2951342697 hasOpenAccess W2951342697 @default.
- W2951342697 hasPrimaryLocation W29513426971 @default.
- W2951342697 hasRelatedWork W1482284612 @default.
- W2951342697 hasRelatedWork W1490073685 @default.
- W2951342697 hasRelatedWork W1513756337 @default.
- W2951342697 hasRelatedWork W1546317785 @default.
- W2951342697 hasRelatedWork W1574837278 @default.
- W2951342697 hasRelatedWork W2124015698 @default.
- W2951342697 hasRelatedWork W2150739593 @default.
- W2951342697 hasRelatedWork W2250325467 @default.
- W2951342697 hasRelatedWork W2251152390 @default.
- W2951342697 hasRelatedWork W2305932946 @default.
- W2951342697 hasRelatedWork W2359208715 @default.
- W2951342697 hasRelatedWork W2546634862 @default.
- W2951342697 hasRelatedWork W2764124976 @default.
- W2951342697 hasRelatedWork W2767391551 @default.
- W2951342697 hasRelatedWork W2865541675 @default.
- W2951342697 hasRelatedWork W2906733717 @default.
- W2951342697 hasRelatedWork W2979390460 @default.
- W2951342697 hasRelatedWork W3034237830 @default.
- W2951342697 hasRelatedWork W3153114578 @default.
- W2951342697 hasRelatedWork W52022909 @default.
- W2951342697 isParatext "false" @default.
- W2951342697 isRetracted "false" @default.
- W2951342697 magId "2951342697" @default.
- W2951342697 workType "article" @default.