Matches in SemOpenAlex for { <https://semopenalex.org/work/W2938179091> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2938179091 abstract "Traditional language models are unable to efficiently model entity names observed in text. All but the most popular named entities appear infrequently in text providing insufficient context. Recent efforts have recognized that context can be generalized between entity names that share the same type (e.g., emph{person} or emph{location}) and have equipped language models with access to an external knowledge base (KB). Our Knowledge-Augmented Language Model (KALM) continues this line of work by augmenting a traditional model with a KB. Unlike previous methods, however, we train with an end-to-end predictive objective optimizing the perplexity of text. We do not require any additional information such as named entity tags. In addition to improving language modeling performance, KALM learns to recognize named entities in an entirely unsupervised way by using entity type information latent in the model. On a Named Entity Recognition (NER) task, KALM achieves performance comparable with state-of-the-art supervised models. Our work demonstrates that named entities (and possibly other types of world knowledge) can be modeled successfully using predictive learning and training on large corpora of text without any additional information." @default.
- W2938179091 created "2019-04-25" @default.
- W2938179091 creator A5006191011 @default.
- W2938179091 creator A5026647956 @default.
- W2938179091 creator A5091317839 @default.
- W2938179091 date "2019-04-09" @default.
- W2938179091 modified "2023-09-30" @default.
- W2938179091 title "Knowledge-Augmented Language Model and its Application to Unsupervised Named-Entity Recognition" @default.
- W2938179091 cites W1533057952 @default.
- W2938179091 cites W19862471 @default.
- W2938179091 cites W2064675550 @default.
- W2938179091 cites W2102267996 @default.
- W2938179091 cites W2144578941 @default.
- W2938179091 cites W2148540243 @default.
- W2938179091 cites W2250539671 @default.
- W2938179091 cites W2296283641 @default.
- W2938179091 cites W2469104253 @default.
- W2938179091 cites W2476140796 @default.
- W2938179091 cites W2525332836 @default.
- W2938179091 cites W2550448043 @default.
- W2938179091 cites W2610748790 @default.
- W2938179091 cites W2741075451 @default.
- W2938179091 cites W2743945814 @default.
- W2938179091 cites W2785349534 @default.
- W2938179091 cites W2787560479 @default.
- W2938179091 cites W2798904449 @default.
- W2938179091 cites W2889675133 @default.
- W2938179091 cites W2891734001 @default.
- W2938179091 cites W2963341956 @default.
- W2938179091 cites W2964308564 @default.
- W2938179091 doi "https://doi.org/10.48550/arxiv.1904.04458" @default.
- W2938179091 hasPublicationYear "2019" @default.
- W2938179091 type Work @default.
- W2938179091 sameAs 2938179091 @default.
- W2938179091 citedByCount "4" @default.
- W2938179091 countsByYear W29381790912020 @default.
- W2938179091 countsByYear W29381790912021 @default.
- W2938179091 crossrefType "posted-content" @default.
- W2938179091 hasAuthorship W2938179091A5006191011 @default.
- W2938179091 hasAuthorship W2938179091A5026647956 @default.
- W2938179091 hasAuthorship W2938179091A5091317839 @default.
- W2938179091 hasBestOaLocation W29381790911 @default.
- W2938179091 hasConcept C100279451 @default.
- W2938179091 hasConcept C137293760 @default.
- W2938179091 hasConcept C151730666 @default.
- W2938179091 hasConcept C154945302 @default.
- W2938179091 hasConcept C162324750 @default.
- W2938179091 hasConcept C171686336 @default.
- W2938179091 hasConcept C187736073 @default.
- W2938179091 hasConcept C204321447 @default.
- W2938179091 hasConcept C23123220 @default.
- W2938179091 hasConcept C2777889803 @default.
- W2938179091 hasConcept C2779135771 @default.
- W2938179091 hasConcept C2779343474 @default.
- W2938179091 hasConcept C2780451532 @default.
- W2938179091 hasConcept C41008148 @default.
- W2938179091 hasConcept C4554734 @default.
- W2938179091 hasConcept C86803240 @default.
- W2938179091 hasConcept C96711827 @default.
- W2938179091 hasConceptScore W2938179091C100279451 @default.
- W2938179091 hasConceptScore W2938179091C137293760 @default.
- W2938179091 hasConceptScore W2938179091C151730666 @default.
- W2938179091 hasConceptScore W2938179091C154945302 @default.
- W2938179091 hasConceptScore W2938179091C162324750 @default.
- W2938179091 hasConceptScore W2938179091C171686336 @default.
- W2938179091 hasConceptScore W2938179091C187736073 @default.
- W2938179091 hasConceptScore W2938179091C204321447 @default.
- W2938179091 hasConceptScore W2938179091C23123220 @default.
- W2938179091 hasConceptScore W2938179091C2777889803 @default.
- W2938179091 hasConceptScore W2938179091C2779135771 @default.
- W2938179091 hasConceptScore W2938179091C2779343474 @default.
- W2938179091 hasConceptScore W2938179091C2780451532 @default.
- W2938179091 hasConceptScore W2938179091C41008148 @default.
- W2938179091 hasConceptScore W2938179091C4554734 @default.
- W2938179091 hasConceptScore W2938179091C86803240 @default.
- W2938179091 hasConceptScore W2938179091C96711827 @default.
- W2938179091 hasLocation W29381790911 @default.
- W2938179091 hasOpenAccess W2938179091 @default.
- W2938179091 hasPrimaryLocation W29381790911 @default.
- W2938179091 hasRelatedWork W121362744 @default.
- W2938179091 hasRelatedWork W1538473846 @default.
- W2938179091 hasRelatedWork W2250554077 @default.
- W2938179091 hasRelatedWork W2251316131 @default.
- W2938179091 hasRelatedWork W2405038964 @default.
- W2938179091 hasRelatedWork W2472885054 @default.
- W2938179091 hasRelatedWork W2533331606 @default.
- W2938179091 hasRelatedWork W2938179091 @default.
- W2938179091 hasRelatedWork W2957144888 @default.
- W2938179091 hasRelatedWork W2963548348 @default.
- W2938179091 isParatext "false" @default.
- W2938179091 isRetracted "false" @default.
- W2938179091 magId "2938179091" @default.
- W2938179091 workType "article" @default.