Sarah's Participation in WAT 2019

WS 2019 · Raymond Hendy Susanto, Ohnmar Htun, Liling Tan ·

This paper describes our MT systems{'} participation in the of WAT 2019. We participated in the (i) Patent, (ii) Timely Disclosure, (iii) Newswire and (iv) Mixed-domain tasks. Our main focus is to explore how similar Transformer models perform on various tasks. We observed that for tasks with smaller datasets, our best model setup are shallower models with lesser number of attention heads. We investigated practical issues in NMT that often appear in production settings, such as coping with multilinguality and simplifying pre- and post-processing pipeline in deployment.

PDF Abstract

Code

Add Remove Mark official

No code implementations yet. Submit your code now

Tasks

Add Remove

NMT

Datasets

Add Datasets introduced or used in this paper

Results from the Paper

Add Remove

Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods

Add Remove

Absolute Position Encodings • Adam • BPE • Dense Connections • Dropout • Label Smoothing • Layer Normalization • Linear Layer • Multi-Head Attention • Position-Wise Feed-Forward Layer • ReLU • Residual Connection • Scaled Dot-Product Attention • Softmax • Transformer

Edit Social Preview

Sarah's Participation in WAT 2019

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit Add Remove

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Add Remove

Methods

Add Remove