Matches in SemOpenAlex for { <https://semopenalex.org/work/W960066740> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W960066740 endingPage "118" @default.
- W960066740 startingPage "110" @default.
- W960066740 abstract "We develop a recursive neural network (RNN) to extract answers to arbitrary natural language questions from supporting sentences, by training on a crowdsourced data set (to be released upon presentation). The RNN defines feature representations at every node of the parse trees of questions and supporting sentences, when applied recursively, starting with token vectors from a neural probabilistic language model. In contrast to prior work, we fix neither the types of the questions nor the forms of the answers; the system classifies tokens to match a substring chosen by the question’s author. Our classifier decides to follow each parse tree node of a support sentence or not, by classifying its RNN embedding together with those of its siblings and the root node of the question, until reaching the tokens it selects as the answer. A novel co-training task for the RNN, on subtree recognition, boosts performance, along with a scheme to consistently handle words that are not well-represented in the language model. On our data set, we surpass an open source system epitomizing a classic “pattern bootstrapping” approach to question answering." @default.
- W960066740 created "2016-06-24" @default.
- W960066740 creator A5080693025 @default.
- W960066740 creator A5090022501 @default.
- W960066740 date "2013-08-01" @default.
- W960066740 modified "2023-09-26" @default.
- W960066740 title "Answer Extraction by Recursive Parse Tree Descent" @default.
- W960066740 cites W1489949474 @default.
- W960066740 cites W1540916400 @default.
- W960066740 cites W1604644367 @default.
- W960066740 cites W1971844566 @default.
- W960066740 cites W2039371384 @default.
- W960066740 cites W2091896764 @default.
- W960066740 cites W2103305545 @default.
- W960066740 cites W2107598941 @default.
- W960066740 cites W2117671523 @default.
- W960066740 cites W2140679639 @default.
- W960066740 cites W2150406842 @default.
- W960066740 cites W2153813398 @default.
- W960066740 cites W2158899491 @default.
- W960066740 cites W2161002933 @default.
- W960066740 cites W2170986599 @default.
- W960066740 cites W2593172760 @default.
- W960066740 cites W2917433478 @default.
- W960066740 cites W71795751 @default.
- W960066740 hasPublicationYear "2013" @default.
- W960066740 type Work @default.
- W960066740 sameAs 960066740 @default.
- W960066740 citedByCount "2" @default.
- W960066740 countsByYear W9600667402021 @default.
- W960066740 crossrefType "proceedings-article" @default.
- W960066740 hasAuthorship W960066740A5080693025 @default.
- W960066740 hasAuthorship W960066740A5090022501 @default.
- W960066740 hasConcept C127413603 @default.
- W960066740 hasConcept C137293760 @default.
- W960066740 hasConcept C147168706 @default.
- W960066740 hasConcept C154945302 @default.
- W960066740 hasConcept C186644900 @default.
- W960066740 hasConcept C204321447 @default.
- W960066740 hasConcept C2777530160 @default.
- W960066740 hasConcept C2781466058 @default.
- W960066740 hasConcept C41008148 @default.
- W960066740 hasConcept C44291984 @default.
- W960066740 hasConcept C50644808 @default.
- W960066740 hasConcept C62611344 @default.
- W960066740 hasConcept C66938386 @default.
- W960066740 hasConcept C95623464 @default.
- W960066740 hasConceptScore W960066740C127413603 @default.
- W960066740 hasConceptScore W960066740C137293760 @default.
- W960066740 hasConceptScore W960066740C147168706 @default.
- W960066740 hasConceptScore W960066740C154945302 @default.
- W960066740 hasConceptScore W960066740C186644900 @default.
- W960066740 hasConceptScore W960066740C204321447 @default.
- W960066740 hasConceptScore W960066740C2777530160 @default.
- W960066740 hasConceptScore W960066740C2781466058 @default.
- W960066740 hasConceptScore W960066740C41008148 @default.
- W960066740 hasConceptScore W960066740C44291984 @default.
- W960066740 hasConceptScore W960066740C50644808 @default.
- W960066740 hasConceptScore W960066740C62611344 @default.
- W960066740 hasConceptScore W960066740C66938386 @default.
- W960066740 hasConceptScore W960066740C95623464 @default.
- W960066740 hasOpenAccess W960066740 @default.
- W960066740 hasRelatedWork W2736613389 @default.
- W960066740 hasRelatedWork W2788982938 @default.
- W960066740 hasRelatedWork W2951828725 @default.
- W960066740 hasRelatedWork W3086115640 @default.
- W960066740 hasRelatedWork W2099520214 @default.
- W960066740 hasRelatedWork W2183764481 @default.
- W960066740 hasRelatedWork W2596199460 @default.
- W960066740 hasRelatedWork W2737712467 @default.
- W960066740 hasRelatedWork W2934123574 @default.
- W960066740 hasRelatedWork W2961206258 @default.
- W960066740 hasRelatedWork W2962217327 @default.
- W960066740 hasRelatedWork W2964623728 @default.
- W960066740 hasRelatedWork W2975585501 @default.
- W960066740 hasRelatedWork W2993445670 @default.
- W960066740 hasRelatedWork W3019032439 @default.
- W960066740 hasRelatedWork W3027515120 @default.
- W960066740 hasRelatedWork W3027953281 @default.
- W960066740 hasRelatedWork W3057841202 @default.
- W960066740 hasRelatedWork W3089572108 @default.
- W960066740 hasRelatedWork W3171961237 @default.
- W960066740 isParatext "false" @default.
- W960066740 isRetracted "false" @default.
- W960066740 magId "960066740" @default.
- W960066740 workType "article" @default.