Matches in SemOpenAlex for { <https://semopenalex.org/work/W2110207985> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2110207985 abstract "Much recent work focuses on formal interpretation of natural question utterances, with the goal of executing the resulting structured queries on knowledge graphs (KGs) such as Freebase. Here we address two limitations of this approach when applied to open-domain, entity-oriented Web queries. First, Web queries are rarely wellformed questions. They are “telegraphic”, with missing verbs, prepositions, clauses, case and phrase clues. Second, the KG is always incomplete, unable to directly answer many queries. We propose a novel technique to segment a telegraphic query and assign a coarse-grained purpose to each segment: a base entity e1, a relation type r, a target entity type t2, and contextual words s. The query seeks entity e2 2 t2 where r(e1,e2) holds, further evidenced by schema-agnostic words s. Query segmentation is integrated with the KG and an unstructured corpus where mentions of entities have been linked to the KG. We do not trust the best or any specific query segmentation. Instead, evidence in favor of candidate e2s are aggregated across several segmentations. Extensive experiments on the ClueWeb corpus and parts of Freebase as our KG, using over a thousand telegraphic queries adapted from TREC, INEX, and WebQuestions, show the efficacy of our approach. For one benchmark, MAP improves from 0.2‐0.29 (competitive baselines) to 0.42 (our system). NDCG@10 improves from 0.29‐0.36 to 0.54." @default.
- W2110207985 created "2016-06-24" @default.
- W2110207985 creator A5005651819 @default.
- W2110207985 creator A5008781655 @default.
- W2110207985 creator A5081690204 @default.
- W2110207985 date "2014-01-01" @default.
- W2110207985 modified "2023-09-26" @default.
- W2110207985 title "Knowledge Graph and Corpus Driven Segmentation and Answer Inference for Telegraphic Entity-seeking Queries" @default.
- W2110207985 cites W1483236033 @default.
- W2110207985 cites W1511986666 @default.
- W2110207985 cites W1539162551 @default.
- W2110207985 cites W1990423373 @default.
- W2110207985 cites W2008036300 @default.
- W2110207985 cites W2020862320 @default.
- W2110207985 cites W2047221353 @default.
- W2110207985 cites W2090243146 @default.
- W2110207985 cites W2098700435 @default.
- W2110207985 cites W2100408869 @default.
- W2110207985 cites W2123142779 @default.
- W2110207985 cites W2130780865 @default.
- W2110207985 cites W2134282875 @default.
- W2110207985 cites W2144886574 @default.
- W2110207985 cites W2146304342 @default.
- W2110207985 cites W2146772539 @default.
- W2110207985 cites W2147196093 @default.
- W2110207985 cites W2148721079 @default.
- W2110207985 cites W2153267064 @default.
- W2110207985 cites W2154610494 @default.
- W2110207985 cites W2156233801 @default.
- W2110207985 cites W2162235411 @default.
- W2110207985 cites W2166765763 @default.
- W2110207985 cites W2168859760 @default.
- W2110207985 cites W2174945390 @default.
- W2110207985 cites W2250225488 @default.
- W2110207985 cites W2251143283 @default.
- W2110207985 cites W2251673953 @default.
- W2110207985 cites W2252136820 @default.
- W2110207985 cites W2915092747 @default.
- W2110207985 doi "https://doi.org/10.3115/v1/d14-1117" @default.
- W2110207985 hasPublicationYear "2014" @default.
- W2110207985 type Work @default.
- W2110207985 sameAs 2110207985 @default.
- W2110207985 citedByCount "40" @default.
- W2110207985 countsByYear W21102079852015 @default.
- W2110207985 countsByYear W21102079852016 @default.
- W2110207985 countsByYear W21102079852017 @default.
- W2110207985 countsByYear W21102079852018 @default.
- W2110207985 countsByYear W21102079852019 @default.
- W2110207985 countsByYear W21102079852020 @default.
- W2110207985 countsByYear W21102079852021 @default.
- W2110207985 countsByYear W21102079852022 @default.
- W2110207985 crossrefType "proceedings-article" @default.
- W2110207985 hasAuthorship W2110207985A5005651819 @default.
- W2110207985 hasAuthorship W2110207985A5008781655 @default.
- W2110207985 hasAuthorship W2110207985A5081690204 @default.
- W2110207985 hasBestOaLocation W21102079851 @default.
- W2110207985 hasConcept C132525143 @default.
- W2110207985 hasConcept C154945302 @default.
- W2110207985 hasConcept C204321447 @default.
- W2110207985 hasConcept C23123220 @default.
- W2110207985 hasConcept C2776214188 @default.
- W2110207985 hasConcept C2987255567 @default.
- W2110207985 hasConcept C41008148 @default.
- W2110207985 hasConcept C80444323 @default.
- W2110207985 hasConcept C89600930 @default.
- W2110207985 hasConceptScore W2110207985C132525143 @default.
- W2110207985 hasConceptScore W2110207985C154945302 @default.
- W2110207985 hasConceptScore W2110207985C204321447 @default.
- W2110207985 hasConceptScore W2110207985C23123220 @default.
- W2110207985 hasConceptScore W2110207985C2776214188 @default.
- W2110207985 hasConceptScore W2110207985C2987255567 @default.
- W2110207985 hasConceptScore W2110207985C41008148 @default.
- W2110207985 hasConceptScore W2110207985C80444323 @default.
- W2110207985 hasConceptScore W2110207985C89600930 @default.
- W2110207985 hasLocation W21102079851 @default.
- W2110207985 hasLocation W21102079852 @default.
- W2110207985 hasOpenAccess W2110207985 @default.
- W2110207985 hasPrimaryLocation W21102079851 @default.
- W2110207985 hasRelatedWork W1774954898 @default.
- W2110207985 hasRelatedWork W2583738779 @default.
- W2110207985 hasRelatedWork W2907467702 @default.
- W2110207985 hasRelatedWork W2972912144 @default.
- W2110207985 hasRelatedWork W3005218912 @default.
- W2110207985 hasRelatedWork W3043226534 @default.
- W2110207985 hasRelatedWork W3044187822 @default.
- W2110207985 hasRelatedWork W3187460820 @default.
- W2110207985 hasRelatedWork W4221140418 @default.
- W2110207985 hasRelatedWork W4287712122 @default.
- W2110207985 isParatext "false" @default.
- W2110207985 isRetracted "false" @default.
- W2110207985 magId "2110207985" @default.
- W2110207985 workType "article" @default.