W12: Workshop on Neural Generation and Translation (WNGT)

Alexandra Birch, Graham Neubig, Andrew Finch, Hiroaki Hayashi, Kenneth Heafield, Ioannis Konstas, Yusuke Oda, Xian Li

Description Schedule External Website
Live Session: Jul 10 (15:30-00:00 GMT)
The 4th Workshop on Neural Generation and Translation provides a forum for research in applications of neural models to language generation and translation tasks.

Time (PDT) Event Speakers
10 Jul, 8:30 AM-9:00 AM Findings of the Efficiency Task Kenneth Heafield
10 Jul, 9:00 AM-9:40 AM Findings of the STAPLE Task Stephen Mayhew
10 Jul, 9:45 AM-10:30 AM Live invited talk: Generating Long Form Text from Long Form Document Input Claire Gardent
10 Jul, 10:30 AM-10:45 AM Live Q&A
10 Jul, 10:45 AM-11:30 AM Break
10 Jul, 11:30 AM-12:15 PM Live invited talk: On Analysing and Generating Faithful Text Shashi Narayan
10 Jul, 12:15 PM-12:30 PM Live Q&A
10 Jul, 12:30 PM-12:40 PM Video of best paper talk: Meta-Learning for Few-Shot NMT Adaptation Amr Sharaf, Hany Hassan and Hal Daumé III
10 Jul, 12:40 PM-12:50 PM Live Best Paper Prize giving and Q&A
10 Jul, 12:50 PM-1:30 PM Break
10 Jul, 1:30 PM-3:00 PM Live paper presentation session Parallel sessions with prerecorded 5-10 min videos and live chat for each paper (Please visit 'External Website' for RockectChat links to each paper).
10 Jul, 3:00 PM-3:45 PM Live invited talk: Text Generation by Offline Reinforcement Learning He He
10 Jul, 3:45 PM-4:00 PM Live Q&A
10 Jul, 4:00 PM-4:45 PM Live invited talk: Multilingual Denoising Pre-training for Neural Machine Translation Jiatao Gu
10 Jul, 4:45 PM-5:00 PM Live Q&A
You can open the livestream video and in a separate window.

Pre-recorded Talks


Learning to Generate Multiple Style Transfer Outputs for an Input Sentence

Kevin Lin


Balancing Cost and Benefit with Tied-Multi Transformers

Raj Dabre


Compressing Neural Machine Translation Models with 4-bit Precision

Alham Fikri Aji


Meta-Learning for Few-Shot NMT Adaptation

Amr Sharaf


Automatically Ranked Russian Paraphrase Corpus for Text Generation

Vadim Gudkov


A Deep Reinforced Model for Zero-Shot Cross-Lingual Summarization with Bilingual Semantic Similarity Rewards

Zi-Yi Dou


A Question Type Driven and Copy Loss Enhanced Framework for Answer-Agnostic Neural Question Generation

Xiuyu Wu


A Generative Approach to Titling and Clustering Wikipedia Sections

Anjalie Field


The Unreasonable Volatility of Neural Machine Translation Models

Marzieh Fadaee


Leveraging Sentence Similarity in Natural Language Generation: Improving Beam Search using Range Voting

Sebastian Borgeaud


Distill, Adapt, Distill: Training Small, In-Domain Models for Neural Machine Translation

Mitchell A. Gordon


Improving Neural Machine Translation Using Energy-Based Models

Subhajit Naskar


Training and Inference Methods for High-Coverage Neural Machine Translation

Michael Yang


Meeting the 2020 Duolingo Challenge on a Shoestring

Tadashi Nomoto


English-to-Japanese Diverse Translation by Combining Forward and Backward Outputs

Masahiro Kaneko


POSTECH Submission on Duolingo Shared Task

Junsu Park


The ADAPT System Description for the STAPLE 2020 English-to-Portuguese Translation Task

Rejwanul Haque


Expand and Filter: CUNI and LMU Systems for the WNGT 2020 Duolingo Shared Task

Jindřich Libovický


Exploring Model Consensus to Generate Translation Paraphrases

Zhenhao Li


Growing Together: Modeling Human Language Learning With n-Best Multi-Checkpoint Machine Translation

El Moatez Billah Nagoudi


Generating Diverse Translations via Weighted Fine-tuning and Hypotheses Filtering for the Duolingo STAPLE Task

Sweta Agrawal


The JHU Submission to the 2020 Duolingo Shared Task on Simultaneous Translation and Paraphrase for Language Education

Huda Khayrallah


Simultaneous paraphrasing and translation by fine-tuning Transformer models

Rakesh Chada


The NiuTrans System for WNGT 2020 Efficiency Task

Chi Hu


Efficient and High-Quality Neural Machine Translation with OpenNMT

Guillaume Klein


Edinburgh’s Submissions to the 2020 Machine Translation Efficiency Task

Nikolay Bogoychev


Increasing Lexical Diversity in Plug and Play Language Models

Soham Parikh


When and Why is Unsupervised Neural Machine Translation Useless?

Yunsu Kim


Transformers without Tears: Improving the Normalization of Self-Attention

Toan Q. Nguyen


Masked Language Model Scoring

Julian Salazar