FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311806031> ?p ?o ?g. }

• W4311806031 endingPage "372" @default.
• W4311806031 startingPage "325" @default.
• W4311806031 abstract "Abstract Active learning can play an important role in low-resource settings (i.e., where annotated data is scarce), by selecting which instances may be more worthy to annotate. Most active learning approaches for Machine Translation assume the existence of a pool of sentences in a source language, and rely on human annotators to provide translations or post-edits, which can still be costly. In this article, we apply active learning to a real-world human-in-the-loop scenario in which we assume that: (1) the source sentences may not be readily available, but instead arrive in a stream; (2) the automatic translations receive feedback in the form of a rating, instead of a correct/edited translation, since the human-in-the-loop might be a user looking for a translation, but not be able to provide one. To tackle the challenge of deciding whether each incoming pair source–translations is worthy to query for human feedback, we resort to a number of stream-based active learning query strategies. Moreover, because we do not know in advance which query strategy will be the most adequate for a certain language pair and set of Machine Translation models, we propose to dynamically combine multiple strategies using prediction with expert advice. Our experiments on different language pairs and feedback settings show that using active learning allows us to converge on the best Machine Translation systems with fewer human interactions. Furthermore, combining multiple strategies using prediction with expert advice outperforms several individual active learning strategies with even fewer interactions, particularly in partial feedback settings." @default.
• W4311806031 created "2022-12-28" @default.
• W4311806031 creator A5026700159 @default.
• W4311806031 creator A5039347839 @default.
• W4311806031 creator A5067178556 @default.
• W4311806031 creator A5091668153 @default.
• W4311806031 date "2023-01-01" @default.
• W4311806031 modified "2023-10-05" @default.
• W4311806031 title "<i>Onception</i>: Active Learning with Expert Advice for Real World Machine Translation" @default.
• W4311806031 cites W1553262910 @default.
• W4311806031 cites W1570963478 @default.
• W4311806031 cites W1998498767 @default.
• W4311806031 cites W2009551863 @default.
• W4311806031 cites W2013025416 @default.
• W4311806031 cites W2064557848 @default.
• W4311806031 cites W2077902449 @default.
• W4311806031 cites W2080021732 @default.
• W4311806031 cites W2101105183 @default.
• W4311806031 cites W2105410942 @default.
• W4311806031 cites W2115890667 @default.
• W4311806031 cites W2123108597 @default.
• W4311806031 cites W2123402141 @default.
• W4311806031 cites W2138242477 @default.
• W4311806031 cites W2171671120 @default.
• W4311806031 cites W2218630638 @default.
• W4311806031 cites W2250342921 @default.
• W4311806031 cites W2250872883 @default.
• W4311806031 cites W2305312316 @default.
• W4311806031 cites W2493916176 @default.
• W4311806031 cites W2513592723 @default.
• W4311806031 cites W2621526390 @default.
• W4311806031 cites W2773795499 @default.
• W4311806031 cites W2798587560 @default.
• W4311806031 cites W2897771603 @default.
• W4311806031 cites W2899181341 @default.
• W4311806031 cites W2912024054 @default.
• W4311806031 cites W2951262644 @default.
• W4311806031 cites W2962685216 @default.
• W4311806031 cites W2963341956 @default.
• W4311806031 cites W2963505445 @default.
• W4311806031 cites W2963532001 @default.
• W4311806031 cites W2963696295 @default.
• W4311806031 cites W2963856158 @default.
• W4311806031 cites W2963915737 @default.
• W4311806031 cites W2964212550 @default.
• W4311806031 cites W2970152385 @default.
• W4311806031 cites W2970279348 @default.
• W4311806031 cites W2970295111 @default.
• W4311806031 cites W2970450573 @default.
• W4311806031 cites W2970529093 @default.
• W4311806031 cites W2970550184 @default.
• W4311806031 cites W2970663072 @default.
• W4311806031 cites W2970676607 @default.
• W4311806031 cites W2970731908 @default.
• W4311806031 cites W2970752831 @default.
• W4311806031 cites W2970900338 @default.
• W4311806031 cites W2971073020 @default.
• W4311806031 cites W2984227554 @default.
• W4311806031 cites W3082479561 @default.
• W4311806031 cites W3099942180 @default.
• W4311806031 cites W3105214104 @default.
• W4311806031 cites W3159243351 @default.
• W4311806031 cites W3159892921 @default.
• W4311806031 cites W3176953596 @default.
• W4311806031 cites W4230030242 @default.
• W4311806031 doi "https://doi.org/10.1162/coli_a_00473" @default.
• W4311806031 hasPublicationYear "2023" @default.
• W4311806031 type Work @default.
• W4311806031 citedByCount "0" @default.
• W4311806031 crossrefType "journal-article" @default.
• W4311806031 hasAuthorship W4311806031A5026700159 @default.
• W4311806031 hasAuthorship W4311806031A5039347839 @default.
• W4311806031 hasAuthorship W4311806031A5067178556 @default.
• W4311806031 hasAuthorship W4311806031A5091668153 @default.
• W4311806031 hasBestOaLocation W43118060311 @default.
• W4311806031 hasConcept C104317684 @default.
• W4311806031 hasConcept C105580179 @default.
• W4311806031 hasConcept C119857082 @default.
• W4311806031 hasConcept C149364088 @default.
• W4311806031 hasConcept C154945302 @default.
• W4311806031 hasConcept C177264268 @default.
• W4311806031 hasConcept C185592680 @default.
• W4311806031 hasConcept C199360897 @default.
• W4311806031 hasConcept C203005215 @default.
• W4311806031 hasConcept C204321447 @default.
• W4311806031 hasConcept C2779955035 @default.
• W4311806031 hasConcept C2780626000 @default.
• W4311806031 hasConcept C41008148 @default.
• W4311806031 hasConcept C55493867 @default.
• W4311806031 hasConcept C77967617 @default.
• W4311806031 hasConceptScore W4311806031C104317684 @default.
• W4311806031 hasConceptScore W4311806031C105580179 @default.
• W4311806031 hasConceptScore W4311806031C119857082 @default.
• W4311806031 hasConceptScore W4311806031C149364088 @default.
• W4311806031 hasConceptScore W4311806031C154945302 @default.
• W4311806031 hasConceptScore W4311806031C177264268 @default.
• W4311806031 hasConceptScore W4311806031C185592680 @default.
• W4311806031 hasConceptScore W4311806031C199360897 @default.

• next