1 |
Multilingual Neural Machine Translation:Can Linguistic Hierarchies Help? ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Multilingual Neural Machine Translation: Can Linguistic Hierarchies Help? ...
|
|
|
|
Abstract:
Multilingual Neural Machine Translation (MNMT) trains a single NMT model that supports translation between multiple languages, rather than training separate models for different languages. Learning a single model can enhance the low-resource translation by leveraging data from multiple languages. However, the performance of an MNMT model is highly dependent on the type of languages used in training, as transferring knowledge from a diverse set of languages degrades the translation performance due to negative transfer. In this paper, we propose a Hierarchical Knowledge Distillation (HKD) approach for MNMT which capitalises on language groups generated according to typological features and phylogeny of languages to overcome the issue of negative transfer. HKD generates a set of multilingual teacher-assistant models via a selective knowledge distillation mechanism based on the language groups, and then distills the ultimate multilingual model from those assistants in an adaptive way. Experimental results ...
|
|
URL: https://dx.doi.org/10.48448/antx-0x85 https://underline.io/lecture/38410-multilingual-neural-machine-translation-can-linguistic-hierarchies-helpquestion
|
|
BASE
|
|
Hide details
|
|
4 |
SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Semantic Title Evaluation and Recommendation Based on Topic Models
|
|
|
|
In: Trends and Applications in Knowledge Discovery and Data Mining: PAKDD 2013 Workshops ; http://pakdd2013.pakdd.org/ (2015)
|
|
BASE
|
|
Show details
|
|
6 |
Semantic Title Evaluation and Recommendation Based on Topic Models
|
|
|
|
In: Trends and Applications in Knowledge Discovery and Data Mining: PAKDD 2013 Workshops ; http://pakdd2013.pakdd.org/ (2015)
|
|
BASE
|
|
Show details
|
|
8 |
Topic Segmentation with a Structured Topic Model
|
|
|
|
In: Topic Segmentation with a Structured Topic Model (2015)
|
|
BASE
|
|
Show details
|
|
9 |
Topic Segmentation with a Structured Topic Model
|
|
|
|
In: Topic Segmentation with a Structured Topic Model (2015)
|
|
BASE
|
|
Show details
|
|
11 |
A Computationally efficient algorithm for learning topical collocation models
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Semantic title evaluation and recommendation based on topic models
|
|
|
|
BASE
|
|
Show details
|
|
|
|