Papers with neural machine translation framework
Context-Aware Neural Machine Translation Decoding (D19-65)
Copied to clipboard
| Challenge: | Existing approaches to enhance neural machine translation systems to take into account document-level information make the training process slower or require document- level annotated data. |
| Approach: | They propose a decoding architecture that fuses the semantic space language model and a neural translation model. |
| Outcome: | The proposed approach improves translation quality for English–Spanish using BLEU and METEOR. |
A Chinese Writing Correction System for Learning Chinese as a Foreign Language (C18-2)
Copied to clipboard
| Challenge: | a new writing correction system for Chinese learners is available for learning as a second language . a classification approach to English GEC does not require exact recognition of error types . however, there is no general model that handles all types of Chinese writing errors. |
| Approach: | They propose a Chinese writing correction system that takes a wrong input sentence and generates correction suggestions. |
| Outcome: | The proposed system generates correction suggestions for Chinese sentences with English translations, helping users understand correct usages of certain grammar patterns. |
Neural-based Chinese Idiom Recommendation for Enhancing Elegance in Essay Writing (P19-1)
Copied to clipboard
| Challenge: | idiom recommendation is difficult because remembering idiomatic expressions is difficult, authors say . idiomas are often written in ancient classical Chinese for conciseness, meaning is difficult to remember . |
| Approach: | They propose to use a neural machine translation framework to recommend idioms . they assume that idiomatic expressions are written with one pseudo target language . |
| Outcome: | The proposed approach achieves promising performance compared with baseline methods. |