Matches in SemOpenAlex for { <https://semopenalex.org/work/W2993231387> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2993231387 abstract "Knowledge-graph-based reasoning has drawn a lot of attention due to its interpretability. However, previous methods suffer from the incompleteness of the knowledge graph, namely the interested link or entity that can be missing in the knowledge graph(explicit missing). Also, most previous models assume the distance between the target and source entity is short, which is not true on a real-world KG like Freebase(implicit missing). The sensitivity to the incompleteness of KG and the incapability to capture the long-distance link between entities have limited the performance of these models on large KG. In this paper, we propose a model that leverages the text corpus to cure such limitations, either the explicit or implicit missing links. We model the question answering on KG as a cooperative task between two agents, a knowledge graph reasoning agent and an information extraction agent. Each agent learns its skill to complete its own task, hopping on KG or select knowledge from the corpus, via maximizing the reward for correctly answering the question. The reasoning agent decides how to find an equivalent path for the given entity and relation. The extraction agent provide shortcut for long-distance target entity or provide missing relations for explicit missing links with messages from the reasoning agent. Through such cooperative reward design, our model can augment the incomplete KG strategically while not introduce much unnecessary noise that could enlarge the search space and lower the performance." @default.
- W2993231387 created "2019-12-13" @default.
- W2993231387 creator A5028518494 @default.
- W2993231387 creator A5062327704 @default.
- W2993231387 creator A5062673325 @default.
- W2993231387 creator A5080011047 @default.
- W2993231387 date "2019-12-04" @default.
- W2993231387 modified "2023-09-26" @default.
- W2993231387 title "Cooperative Reasoning on Knowledge Graph and Corpus: A Multi-agentReinforcement Learning Approach" @default.
- W2993231387 cites W114118985 @default.
- W2993231387 cites W1505937442 @default.
- W2993231387 cites W1542941925 @default.
- W2993231387 cites W1587447546 @default.
- W2993231387 cites W1641379095 @default.
- W2993231387 cites W1756422141 @default.
- W2993231387 cites W175897666 @default.
- W2993231387 cites W1852412531 @default.
- W2993231387 cites W2038880450 @default.
- W2993231387 cites W2145544171 @default.
- W2993231387 cites W2162584647 @default.
- W2993231387 cites W2251616524 @default.
- W2993231387 cites W2476140796 @default.
- W2993231387 cites W2593804007 @default.
- W2993231387 cites W2604314403 @default.
- W2993231387 cites W2769099080 @default.
- W2993231387 cites W2788902803 @default.
- W2993231387 cites W2794945088 @default.
- W2993231387 cites W2889344053 @default.
- W2993231387 cites W2890961898 @default.
- W2993231387 cites W2898632797 @default.
- W2993231387 cites W2929985644 @default.
- W2993231387 cites W2946765201 @default.
- W2993231387 cites W2963380480 @default.
- W2993231387 cites W2964059756 @default.
- W2993231387 cites W2964116313 @default.
- W2993231387 cites W2982320652 @default.
- W2993231387 doi "https://doi.org/10.48550/arxiv.1912.02206" @default.
- W2993231387 hasPublicationYear "2019" @default.
- W2993231387 type Work @default.
- W2993231387 sameAs 2993231387 @default.
- W2993231387 citedByCount "0" @default.
- W2993231387 crossrefType "posted-content" @default.
- W2993231387 hasAuthorship W2993231387A5028518494 @default.
- W2993231387 hasAuthorship W2993231387A5062327704 @default.
- W2993231387 hasAuthorship W2993231387A5062673325 @default.
- W2993231387 hasAuthorship W2993231387A5080011047 @default.
- W2993231387 hasBestOaLocation W29932313871 @default.
- W2993231387 hasConcept C119857082 @default.
- W2993231387 hasConcept C132525143 @default.
- W2993231387 hasConcept C154945302 @default.
- W2993231387 hasConcept C162324750 @default.
- W2993231387 hasConcept C187736073 @default.
- W2993231387 hasConcept C204321447 @default.
- W2993231387 hasConcept C2780451532 @default.
- W2993231387 hasConcept C2781067378 @default.
- W2993231387 hasConcept C2987255567 @default.
- W2993231387 hasConcept C41008148 @default.
- W2993231387 hasConcept C44291984 @default.
- W2993231387 hasConcept C80444323 @default.
- W2993231387 hasConcept C9357733 @default.
- W2993231387 hasConceptScore W2993231387C119857082 @default.
- W2993231387 hasConceptScore W2993231387C132525143 @default.
- W2993231387 hasConceptScore W2993231387C154945302 @default.
- W2993231387 hasConceptScore W2993231387C162324750 @default.
- W2993231387 hasConceptScore W2993231387C187736073 @default.
- W2993231387 hasConceptScore W2993231387C204321447 @default.
- W2993231387 hasConceptScore W2993231387C2780451532 @default.
- W2993231387 hasConceptScore W2993231387C2781067378 @default.
- W2993231387 hasConceptScore W2993231387C2987255567 @default.
- W2993231387 hasConceptScore W2993231387C41008148 @default.
- W2993231387 hasConceptScore W2993231387C44291984 @default.
- W2993231387 hasConceptScore W2993231387C80444323 @default.
- W2993231387 hasConceptScore W2993231387C9357733 @default.
- W2993231387 hasLocation W29932313871 @default.
- W2993231387 hasOpenAccess W2993231387 @default.
- W2993231387 hasPrimaryLocation W29932313871 @default.
- W2993231387 hasRelatedWork W128392744 @default.
- W2993231387 hasRelatedWork W2993231387 @default.
- W2993231387 hasRelatedWork W3006943036 @default.
- W2993231387 hasRelatedWork W3012234327 @default.
- W2993231387 hasRelatedWork W3191046242 @default.
- W2993231387 hasRelatedWork W3203961807 @default.
- W2993231387 hasRelatedWork W4205364923 @default.
- W2993231387 hasRelatedWork W4206534706 @default.
- W2993231387 hasRelatedWork W4229079080 @default.
- W2993231387 hasRelatedWork W4297899248 @default.
- W2993231387 isParatext "false" @default.
- W2993231387 isRetracted "false" @default.
- W2993231387 magId "2993231387" @default.
- W2993231387 workType "article" @default.