Thailand

Existing multilingual machine translation approaches mainly focus on English-centric directions, while the non-English directions still lag behind. In this work, we aim to build a many-to-many translation system with an emphasis on the quality of non-English language directions. Our intuition is based on the hypothesis that a universal cross-language representation leads to better multilingual translation performance. To this end, we propose mRASP2, a training method to obtain a single unified multilingual translation model. mRASP2 is empowered by two techniques: a) a contrastive learning scheme to close the gap among representations of different languages, and b) data augmentation on both multiple parallel and monolingual data to further align token representations. For English-centric directions, mRASP2 achieves competitive or even better performance than a strong pre-trained model mBART on tens of WMT benchmarks. For non-English directions, mRASP2 achieves an improvement of average 10+ BLEU compared with the multilingual baseline

ACL 2021

Contrastive Learning for Many-to-many Multilingual Neural Machine Translation

contrastive learning

data augmentation

multilingual

machine translation

**Welcome to ACL-IJCNLP 2021!**

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP). 

This Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021) was to be held in Bangkok, Thailand, during August 1-6, 2021 and is now virtual on the Underline platform.

As in previous years, the program of the conference includes a poster session, tutorials, workshops and demonstrations in addition to the main conference.


We were able to keep the registration fees similar to those charged for the virtual ACL 2020. The one fee allows attendance at the main conference and any/all tutorials and workshops. These fees would be $125 Regular Early and $175 Regular Late; $50 Student Early and $75 Student Late. Early registration closes at midnight July 11, 2021 (Eastern Daylight Time).

**Reminder:** It is ACL’s policy that at least one author of each accepted paper (including ACL Finding papers) must register for the conference.

**Reminder2:** Underline site will open closer to the event. If you already registered you will receive access detail

Registration is now open

technical paper

Accelerating BERT Inference for Sequence Labeling via Early-Exit

Modularized Interaction Network for Named Entity Recognition

UniRE: A Unified Label Space for Entity Relation Extraction

Refining Sample Embeddings with Relation Prototypes to Enhance Continual Relation Extraction

GoG: Relation-aware Graph-over-Graph Network for Visual Dialog

Joint Optimization of Tokenization and Downstream Model

How does Attention Affect the Model?

Contrastive Attention for Automatic Chest X-ray Report Generation

O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning

Better {C}hinese Sentence Segmentation with Reinforcement Learning

https://d3smihljt9218e.cloudfront.net/transcript/17692/subtitle/527f13aa3111299118f492612181e1f2.vtt

English (automatic)

Contrastive Learning for Many-to-many Multilingual Neural Machine Translation

Downloads

Next from ACL 2021

Accelerating BERT Inference for Sequence Labeling via Early-Exit

Similar lecture

BERTGen: Multi-task Generation through BERT

VIDEO LIBRARY

EVENTS

COMPANY

RESOURCES