Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387074862> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4387074862 abstract "We introduce the submissions of the NJUNLP team to the WMT 2023 Quality Estimation (QE) shared task. Our team submitted predictions for the English-German language pair on all two sub-tasks: (i) sentence- and word-level quality prediction; and (ii) fine-grained error span detection. This year, we further explore pseudo data methods for QE based on NJUQE framework (https://github.com/NJUNLP/njuqe). We generate pseudo MQM data using parallel data from the WMT translation task. We pre-train the XLMR large model on pseudo QE data, then fine-tune it on real QE data. At both stages, we jointly learn sentence-level scores and word-level tags. Empirically, we conduct experiments to find the key hyper-parameters that improve the performance. Technically, we propose a simple method that covert the word-level outputs to fine-grained error span results. Overall, our models achieved the best results in English-German for both word-level and fine-grained error span detection sub-tasks by a considerable margin." @default.
- W4387074862 created "2023-09-27" @default.
- W4387074862 creator A5006709668 @default.
- W4387074862 creator A5013884466 @default.
- W4387074862 creator A5025001381 @default.
- W4387074862 creator A5025469065 @default.
- W4387074862 creator A5040256399 @default.
- W4387074862 creator A5067322430 @default.
- W4387074862 creator A5071773009 @default.
- W4387074862 date "2023-09-22" @default.
- W4387074862 modified "2023-10-17" @default.
- W4387074862 title "NJUNLP's Participation for the WMT2023 Quality Estimation Shared Task" @default.
- W4387074862 doi "https://doi.org/10.48550/arxiv.2309.13230" @default.
- W4387074862 hasPublicationYear "2023" @default.
- W4387074862 type Work @default.
- W4387074862 citedByCount "0" @default.
- W4387074862 crossrefType "posted-content" @default.
- W4387074862 hasAuthorship W4387074862A5006709668 @default.
- W4387074862 hasAuthorship W4387074862A5013884466 @default.
- W4387074862 hasAuthorship W4387074862A5025001381 @default.
- W4387074862 hasAuthorship W4387074862A5025469065 @default.
- W4387074862 hasAuthorship W4387074862A5040256399 @default.
- W4387074862 hasAuthorship W4387074862A5067322430 @default.
- W4387074862 hasAuthorship W4387074862A5071773009 @default.
- W4387074862 hasBestOaLocation W43870748621 @default.
- W4387074862 hasConcept C111472728 @default.
- W4387074862 hasConcept C119857082 @default.
- W4387074862 hasConcept C138885662 @default.
- W4387074862 hasConcept C154775046 @default.
- W4387074862 hasConcept C154945302 @default.
- W4387074862 hasConcept C162324750 @default.
- W4387074862 hasConcept C187736073 @default.
- W4387074862 hasConcept C204321447 @default.
- W4387074862 hasConcept C2777530160 @default.
- W4387074862 hasConcept C2779338814 @default.
- W4387074862 hasConcept C2779530757 @default.
- W4387074862 hasConcept C2780451532 @default.
- W4387074862 hasConcept C28490314 @default.
- W4387074862 hasConcept C41008148 @default.
- W4387074862 hasConcept C41895202 @default.
- W4387074862 hasConcept C774472 @default.
- W4387074862 hasConcept C90805587 @default.
- W4387074862 hasConceptScore W4387074862C111472728 @default.
- W4387074862 hasConceptScore W4387074862C119857082 @default.
- W4387074862 hasConceptScore W4387074862C138885662 @default.
- W4387074862 hasConceptScore W4387074862C154775046 @default.
- W4387074862 hasConceptScore W4387074862C154945302 @default.
- W4387074862 hasConceptScore W4387074862C162324750 @default.
- W4387074862 hasConceptScore W4387074862C187736073 @default.
- W4387074862 hasConceptScore W4387074862C204321447 @default.
- W4387074862 hasConceptScore W4387074862C2777530160 @default.
- W4387074862 hasConceptScore W4387074862C2779338814 @default.
- W4387074862 hasConceptScore W4387074862C2779530757 @default.
- W4387074862 hasConceptScore W4387074862C2780451532 @default.
- W4387074862 hasConceptScore W4387074862C28490314 @default.
- W4387074862 hasConceptScore W4387074862C41008148 @default.
- W4387074862 hasConceptScore W4387074862C41895202 @default.
- W4387074862 hasConceptScore W4387074862C774472 @default.
- W4387074862 hasConceptScore W4387074862C90805587 @default.
- W4387074862 hasLocation W43870748621 @default.
- W4387074862 hasOpenAccess W4387074862 @default.
- W4387074862 hasPrimaryLocation W43870748621 @default.
- W4387074862 hasRelatedWork W1539050421 @default.
- W4387074862 hasRelatedWork W1563147278 @default.
- W4387074862 hasRelatedWork W1573537589 @default.
- W4387074862 hasRelatedWork W159132833 @default.
- W4387074862 hasRelatedWork W2125145484 @default.
- W4387074862 hasRelatedWork W2903246208 @default.
- W4387074862 hasRelatedWork W2969773591 @default.
- W4387074862 hasRelatedWork W3024381485 @default.
- W4387074862 hasRelatedWork W4225619937 @default.
- W4387074862 hasRelatedWork W4385572842 @default.
- W4387074862 isParatext "false" @default.
- W4387074862 isRetracted "false" @default.
- W4387074862 workType "article" @default.