Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287127961> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4287127961 abstract "Named entity recognition (NER) is a fundamental component in many applications, such as Web Search and Voice Assistants. Although deep neural networks greatly improve the performance of NER, due to the requirement of large amounts of training data, deep neural networks can hardly scale out to many languages in an industry setting. To tackle this challenge, cross-lingual NER transfers knowledge from a rich-resource language to languages with low resources through pre-trained multilingual language models. Instead of using training data in target languages, cross-lingual NER has to rely on only training data in source languages, and optionally adds the translated training data derived from source languages. However, the existing cross-lingual NER methods do not make good use of rich unlabeled data in target languages, which is relatively easy to collect in industry applications. To address the opportunities and challenges, in this paper we describe our novel practice in Microsoft to leverage such large amounts of unlabeled data in target languages in real production settings. To effectively extract weak supervision signals from the unlabeled data, we develop a novel approach based on the ideas of semi-supervised learning and reinforcement learning. The empirical study on three benchmark data sets verifies that our approach establishes the new state-of-the-art performance with clear edges. Now, the NER techniques reported in this paper are on their way to become a fundamental component for Web ranking, Entity Pane, Answers Triggering, and Question Answering in the Microsoft Bing search engine. Moreover, our techniques will also serve as part of the Spoken Language Understanding module for a commercial voice assistant. We plan to open source the code of the prototype framework after deployment." @default.
- W4287127961 created "2022-07-25" @default.
- W4287127961 creator A5018318136 @default.
- W4287127961 creator A5038131159 @default.
- W4287127961 creator A5060116992 @default.
- W4287127961 creator A5062247330 @default.
- W4287127961 creator A5063079555 @default.
- W4287127961 creator A5072054932 @default.
- W4287127961 creator A5077262995 @default.
- W4287127961 date "2021-06-01" @default.
- W4287127961 modified "2023-09-28" @default.
- W4287127961 title "Reinforced Iterative Knowledge Distillation for Cross-Lingual Named Entity Recognition" @default.
- W4287127961 hasPublicationYear "2021" @default.
- W4287127961 type Work @default.
- W4287127961 citedByCount "0" @default.
- W4287127961 crossrefType "posted-content" @default.
- W4287127961 hasAuthorship W4287127961A5018318136 @default.
- W4287127961 hasAuthorship W4287127961A5038131159 @default.
- W4287127961 hasAuthorship W4287127961A5060116992 @default.
- W4287127961 hasAuthorship W4287127961A5062247330 @default.
- W4287127961 hasAuthorship W4287127961A5063079555 @default.
- W4287127961 hasAuthorship W4287127961A5072054932 @default.
- W4287127961 hasAuthorship W4287127961A5077262995 @default.
- W4287127961 hasBestOaLocation W42871279611 @default.
- W4287127961 hasConcept C119857082 @default.
- W4287127961 hasConcept C121332964 @default.
- W4287127961 hasConcept C13280743 @default.
- W4287127961 hasConcept C153083717 @default.
- W4287127961 hasConcept C154945302 @default.
- W4287127961 hasConcept C162324750 @default.
- W4287127961 hasConcept C168167062 @default.
- W4287127961 hasConcept C185798385 @default.
- W4287127961 hasConcept C187736073 @default.
- W4287127961 hasConcept C189430467 @default.
- W4287127961 hasConcept C204321447 @default.
- W4287127961 hasConcept C205649164 @default.
- W4287127961 hasConcept C23123220 @default.
- W4287127961 hasConcept C2776145971 @default.
- W4287127961 hasConcept C2779135771 @default.
- W4287127961 hasConcept C2780451532 @default.
- W4287127961 hasConcept C41008148 @default.
- W4287127961 hasConcept C4554734 @default.
- W4287127961 hasConcept C96711827 @default.
- W4287127961 hasConcept C97355855 @default.
- W4287127961 hasConceptScore W4287127961C119857082 @default.
- W4287127961 hasConceptScore W4287127961C121332964 @default.
- W4287127961 hasConceptScore W4287127961C13280743 @default.
- W4287127961 hasConceptScore W4287127961C153083717 @default.
- W4287127961 hasConceptScore W4287127961C154945302 @default.
- W4287127961 hasConceptScore W4287127961C162324750 @default.
- W4287127961 hasConceptScore W4287127961C168167062 @default.
- W4287127961 hasConceptScore W4287127961C185798385 @default.
- W4287127961 hasConceptScore W4287127961C187736073 @default.
- W4287127961 hasConceptScore W4287127961C189430467 @default.
- W4287127961 hasConceptScore W4287127961C204321447 @default.
- W4287127961 hasConceptScore W4287127961C205649164 @default.
- W4287127961 hasConceptScore W4287127961C23123220 @default.
- W4287127961 hasConceptScore W4287127961C2776145971 @default.
- W4287127961 hasConceptScore W4287127961C2779135771 @default.
- W4287127961 hasConceptScore W4287127961C2780451532 @default.
- W4287127961 hasConceptScore W4287127961C41008148 @default.
- W4287127961 hasConceptScore W4287127961C4554734 @default.
- W4287127961 hasConceptScore W4287127961C96711827 @default.
- W4287127961 hasConceptScore W4287127961C97355855 @default.
- W4287127961 hasLocation W42871279611 @default.
- W4287127961 hasOpenAccess W4287127961 @default.
- W4287127961 hasPrimaryLocation W42871279611 @default.
- W4287127961 hasRelatedWork W11196620 @default.
- W4287127961 hasRelatedWork W11298561 @default.
- W4287127961 hasRelatedWork W14854443 @default.
- W4287127961 hasRelatedWork W382276 @default.
- W4287127961 hasRelatedWork W4867410 @default.
- W4287127961 hasRelatedWork W5053386 @default.
- W4287127961 hasRelatedWork W6745161 @default.
- W4287127961 hasRelatedWork W7072919 @default.
- W4287127961 hasRelatedWork W7812533 @default.
- W4287127961 hasRelatedWork W8902685 @default.
- W4287127961 isParatext "false" @default.
- W4287127961 isRetracted "false" @default.
- W4287127961 workType "article" @default.