LEPOR: An Augmented Machine Translation Evaluation Metric

MT Evaluation, Quality Estimation, and Multilingual Treebanks
 
 
LAP Lambert Academic Publishing
  • erschienen am 13. Januar 2018
 
  • Buch
  • |
  • Softcover
  • |
  • 136 Seiten
978-620-2-19981-0 (ISBN)
 
Machine translation (MT) was developed as one of the hottest research topics in the natural language processing (NLP) literature. One important issue in MT is that how to evaluate the MT system reasonably and tell us whether the translation system makes an improvement or not. The traditional manual judgment methods are expensive, time-consuming, unrepeatable, and sometimes with a low agreement. On the other hand, the popular automatic MT evaluation methods have some weaknesses. Firstly, they tend to perform well on the language pairs with English as the target language, but weak when English is used as the source. Secondly, some methods rely on many additional linguistic features to achieve good performance, which makes the metric unable to replicate and apply to other language pairs easily. Thirdly, some popular metrics utilize incomprehensive factors, which result in low performance on some practical tasks. In this thesis, to address the existing problems, we design novel MT evaluation methods and investigate their performances in different languages. Firstly, we design augmented factors to yield highly accurate evaluation. Secondly, we design tunable evaluation models, ...
  • Englisch
  • Höhe: 220 mm
  • |
  • Breite: 150 mm
  • |
  • Dicke: 8 mm
  • 219 gr
978-620-2-19981-0 (9786202199810)
6202199814 (6202199814)
My research topics include Machine Translation and NLP. I had research project experiences at the University of Macau, University of Amsterdam and Dublin City University. I hold Master degree in CS with Excellent Award for my thesis, Bachelor degree in Math. My team won National Second Prize in Postgraduate Mathematical Modeling Contest of China.

Sofort lieferbar

55,90 €
inkl. 7% MwSt.
in den Warenkorb

Abholung vor Ort? Sehr gerne!
Unsere Web-Seiten verwenden Cookies. Mit der Nutzung dieser Web-Seiten erklären Sie sich damit einverstanden. Mehr Informationen finden Sie in unserem Datenschutzhinweis. Ok