Matches in SemOpenAlex for { <https://semopenalex.org/work/W2815204851> ?p ?o ?g. }
- W2815204851 endingPage "1533" @default.
- W2815204851 startingPage "1521" @default.
- W2815204851 abstract "This paper provides an evaluation of a wide range of advanced sentence-level Quality Estimation models, including Support Vector Regression, Ride Regression, Neural Networks, Gaussian Processes, Bayesian Neural Networks, Deep Kernel Learning and Deep Gaussian Processes. Beside the accurateness, our main concerns are also the robustness of Quality Estimation models. Our work raises the difficulty in building strong models. Specifically, we show that Quality Estimation models often behave differently in Quality Estimation feature space, depending on whether the scale of feature space is small, medium or large. We also show that Quality Estimation models often behave differently in evaluation settings, depending on whether test data come from the same domain as the training data or not. Our work suggests several strong candidates to use in different circumstances." @default.
- W2815204851 created "2018-07-19" @default.
- W2815204851 creator A5064649079 @default.
- W2815204851 creator A5071924020 @default.
- W2815204851 date "2018-08-01" @default.
- W2815204851 modified "2023-09-28" @default.
- W2815204851 title "Assessing Quality Estimation Models for Sentence-Level Prediction" @default.
- W2815204851 cites W1567512734 @default.
- W2815204851 cites W164706946 @default.
- W2815204851 cites W1702387805 @default.
- W2815204851 cites W1911647372 @default.
- W2815204851 cites W1959608418 @default.
- W2815204851 cites W1975742580 @default.
- W2815204851 cites W1991418309 @default.
- W2815204851 cites W2037831268 @default.
- W2815204851 cites W2047028564 @default.
- W2815204851 cites W2095705004 @default.
- W2815204851 cites W2099768828 @default.
- W2815204851 cites W2119821739 @default.
- W2815204851 cites W2124223001 @default.
- W2815204851 cites W2125849100 @default.
- W2815204851 cites W2130283669 @default.
- W2815204851 cites W2137135057 @default.
- W2815204851 cites W2144746247 @default.
- W2815204851 cites W2149327368 @default.
- W2815204851 cites W2160001241 @default.
- W2815204851 cites W2166851633 @default.
- W2815204851 cites W2250771471 @default.
- W2815204851 cites W2250799045 @default.
- W2815204851 cites W2251311344 @default.
- W2815204851 cites W2251314653 @default.
- W2815204851 cites W2251333340 @default.
- W2815204851 cites W2251406574 @default.
- W2815204851 cites W2257113116 @default.
- W2815204851 cites W2335874026 @default.
- W2815204851 cites W2471347784 @default.
- W2815204851 cites W2507438968 @default.
- W2815204851 cites W2508032974 @default.
- W2815204851 cites W2511164486 @default.
- W2815204851 cites W2512415098 @default.
- W2815204851 cites W2532176768 @default.
- W2815204851 cites W2549019841 @default.
- W2815204851 cites W2606347107 @default.
- W2815204851 cites W2621975677 @default.
- W2815204851 cites W2735471653 @default.
- W2815204851 cites W2754753494 @default.
- W2815204851 cites W2755256826 @default.
- W2815204851 cites W2757578620 @default.
- W2815204851 cites W2759192729 @default.
- W2815204851 cites W2760258467 @default.
- W2815204851 cites W2760656271 @default.
- W2815204851 cites W2913243980 @default.
- W2815204851 cites W2951497035 @default.
- W2815204851 cites W2962875063 @default.
- W2815204851 cites W2962897886 @default.
- W2815204851 cites W2963173382 @default.
- W2815204851 cites W2963506925 @default.
- W2815204851 cites W2963711523 @default.
- W2815204851 cites W2963832833 @default.
- W2815204851 cites W2964019776 @default.
- W2815204851 cites W2964121744 @default.
- W2815204851 cites W2964135722 @default.
- W2815204851 cites W2964339145 @default.
- W2815204851 cites W3044695148 @default.
- W2815204851 cites W71896076 @default.
- W2815204851 cites W2963900082 @default.
- W2815204851 hasPublicationYear "2018" @default.
- W2815204851 type Work @default.
- W2815204851 sameAs 2815204851 @default.
- W2815204851 citedByCount "0" @default.
- W2815204851 crossrefType "proceedings-article" @default.
- W2815204851 hasAuthorship W2815204851A5064649079 @default.
- W2815204851 hasAuthorship W2815204851A5071924020 @default.
- W2815204851 hasConcept C104317684 @default.
- W2815204851 hasConcept C105795698 @default.
- W2815204851 hasConcept C107673813 @default.
- W2815204851 hasConcept C111472728 @default.
- W2815204851 hasConcept C119857082 @default.
- W2815204851 hasConcept C121332964 @default.
- W2815204851 hasConcept C12267149 @default.
- W2815204851 hasConcept C124101348 @default.
- W2815204851 hasConcept C138885662 @default.
- W2815204851 hasConcept C154945302 @default.
- W2815204851 hasConcept C162324750 @default.
- W2815204851 hasConcept C163716315 @default.
- W2815204851 hasConcept C185592680 @default.
- W2815204851 hasConcept C187736073 @default.
- W2815204851 hasConcept C2776401178 @default.
- W2815204851 hasConcept C2779530757 @default.
- W2815204851 hasConcept C33923547 @default.
- W2815204851 hasConcept C41008148 @default.
- W2815204851 hasConcept C41895202 @default.
- W2815204851 hasConcept C50644808 @default.
- W2815204851 hasConcept C55493867 @default.
- W2815204851 hasConcept C61326573 @default.
- W2815204851 hasConcept C62520636 @default.
- W2815204851 hasConcept C63479239 @default.
- W2815204851 hasConcept C81692654 @default.