Accepted Papers

Archival Track - Long Papers

Conditional Adversarial Networks for Multi-Domain Text Classification

Yuan Wu, Diana Inkpen and Ahmed El-Roby

Bridging the gap between supervised classification and unsupervised topic modelling for social-media assisted crisis management

Mikael Brunila, Rosie Zhao, Andrei Mircea Romascanu, Sam Lumley and Renee Sieber

Genres, Parsers, and BERT: The Interaction Between Parsers and BERT Models in Cross-Genre Constituency Parsing in English and Swedish

Daniel Dakota

Cross-Lingual Transfer with MAML on Trees

Jezabel Garcia, Federica Freddi, Jamie McGowan, Tim Nieradzik, Feng-Ting Liao, Ye Tian, Da-shan Shiu and Alberto Bernacchia

Addressing Zero-Resource Domains Using Document-Level Context in Neural Machine Translation

Dario Stojanovski and Alexander Fraser

MultiReQA: A Cross-Domain Evaluation forRetrieval Question Answering Models

Mandy Guo, Yinfei Yang, Daniel Cer, Qinlan Shen and Noah Constant

BERTologiCoMix: How does Code-Mixing interact with Multilingual BERT?

Sebastin Santy, Anirudh Srinivasan and Monojit Choudhury

Locality Preserving Loss: Neighbors that Live together, Align together

Ashwinkumar Ganesan, Francis Ferraro and Tim Oates

Trajectory-Based Meta-Learning for Out-Of-Vocabulary Word Embedding Learning

Gordon Buck and Andreas Vlachos

Dependency Parsing Evaluation for Low-resource Spontaneous Speech

Zoey Liu and Emily Prud'hommeaux

User Factor Adaptation for User Embedding via Multitask Learning

Xiaolei Huang, Michael J. Paul, Franck Dernoncourt, Robin Burke and Mark Dredze

Analyzing the Domain Robustness of Pretrained Language Models, Layer by Layer

Abhinav Ramesh Kashyap, Laiba Mehnaz, Bhavitvya Malik, Abdul Waheed, Devamanyu Hazarika, Min-Yen Kan and Rajiv Ratn Shah

Few-Shot Learning of an Interleaved Text Summarization Model by Pretraining with Synthetic Data

Sanjeev Kumar Karn, Francine Chen, Yan-Ying Chen, Ulli Waltinger and Hinrich Schütze

Archival Track - Short Papers

Multidomain Pretrained Language Models for Green NLP

Antonios Maronikolakis and Hinrich Schütze

Pseudo-Label Guided Unsupervised Domain Adaptation of Contextual Embeddings

Tianyu Chen, Shaohan Huang, Furu Wei and Jianxin Li

The impact of domain-specific representations on BERT-based multi-domain spoken language understanding

Judith Gaspers, Quynh Do, Tobias Röding and Melanie Bradford

Challenges in Annotating and Parsing Spoken, Code-switched, Frisian-Dutch Data

Anouck Braggaar and Rob van der Goot

Domain adaptation in practice: Lessons from a real-world information extraction pipeline

Timothy Miller, Egoitz Laparra and Steven Bethard

On the Hidden Negative Transfer in Sequential Transfer Learning for Domain Adaptation from News to Tweets

Sara Meftah, Nasredine Semmar, Youssef Tamaazousti, Hassane Essafi and Fatiha Sadat

An Empirical Study of Compound PCFGs

Yanpeng Zhao and Ivan Titov

On the Effectiveness of Dataset Embeddings in Mono-lingual,Multi-lingual and Zero-shot Conditions

Rob van der Goot, Ahmet Üstün and Barbara Plank

Effective Distant Supervision for Temporal Relation Extraction

Xinyu Zhao, Shih-Ting Lin and Greg Durrett

Zero-Shot Cross-Lingual Dependency Parsing through Contextual Embedding Transformation

Haoran Xu and Philipp Koehn

Gradual Fine-Tuning for Low-Resource Domain Adaptation

Haoran Xu, Seth Ebner, Mahsa Yarmohammadi, Aaron Steven White, Benjamin Van Durme and Kenton Murray

Semantic Parsing of Brief and Multi-Intent Natural Language Utterances

Logan Lebanoff, Charles Newton, Victor Hung, Beth Atkinson, John Killilea and Fei Liu

Domain Adaptation for NMT via Filtered Iterative Back-Translation

Surabhi Kumari, Nikhil Jaiswal, Mayur Patidar, Manasi Patwardhan, Shirish Karande, Puneet Agarwal and Lovekesh Vig

Non-Archival Track

Training and Domain Adaptation for Supervised Text Segmentation

Goran Glavaš, Ananya Ganesh and Swapna Somasundaran

Adapting to the Long Tail in Language Understanding

Aakanksha Naik and Carolyn Rose

Oral Presentation

Conditional Adversarial Networks for Multi-Domain Text Classification
Dependency Parsing Evaluation for Low-resource Spontaneous Speech
Few-Shot Learning of an Interleaved Text Summarization Model by Pretraining with Synthetic Data
Semantic Parsing of Brief and Multi-Intent Natural Language Utterances
Locality Preserving Loss: Neighbors that Live together, Align together

Posters

Since the workshop participants come from different time zones and because of the virtual nature of the conference, the poster session occur twice and is accessible for any time zone.

First Poster Session - 10:00am - 11:00am (CET)

Pseudo-Label Guided Unsupervised Domain Adaptation of Contextual Embeddings
The impact of domain-specific representations on BERT-based multi-domain spoken language understanding
Challenges in Annotating and Parsing Spoken, Code-switched, Frisian-Dutch Data
Genres, Parsers, and BERT: The Interaction Between Parsers and BERT Models in Cross-Genre Constituency Parsing in English and Swedish
Cross-Lingual Transfer with MAML on Trees
Addressing Zero-Resource Domains Using Document-Level Context in Neural Machine Translation
Domain adaptation in practice: Lessons from a real-world information extraction pipeline
BERTologiCoMix: How does Code-Mixing interact with Multilingual BERT?
Training and Domain Adaptation for Supervised Text Segmentation
On the Effectiveness of Dataset Embeddings in Mono-lingual,Multi-lingual and Zero-shot Conditions
Zero-Shot Cross-Lingual Dependency Parsing through Contextual Embedding Transformation
Gradual Fine-Tuning for Low-Resource Domain Adaptation
Analyzing the Domain Robustness of Pretrained Language Models, Layer by Layer
Domain Adaptation for NMT via Filtered Iterative Back-Translation

Second Poster Session - 3:40pm - 4:40pm (CET)

Multidomain Pretrained Language Models for Green NLP
The impact of domain-specific representations on BERT-based multi-domain spoken language understanding
Bridging the gap between supervised classification and unsupervised topic modelling for social-media assisted crisis management
Challenges in Annotating and Parsing Spoken, Code-switched, Frisian-Dutch Data
Cross-Lingual Transfer with MAML on Trees
Addressing Zero-Resource Domains Using Document-Level Context in Neural Machine Translation
MultiReQA: A Cross-Domain Evaluation forRetrieval Question Answering Models
Domain adaptation in practice: Lessons from a real-world information extraction pipeline
On the Hidden Negative Transfer in Sequential Transfer Learning for Domain Adaptation from News to Tweets
Training and Domain Adaptation for Supervised Text Segmentation
Trajectory-Based Meta-Learning for Out-Of-Vocabulary Word Embedding Learning
An Empirical Study of Compound PCFGs
User Factor Adaptation for User Embedding via Multitask Learning
On the Effectiveness of Dataset Embeddings in Mono-lingual,Multi-lingual and Zero-shot Conditions
Effective Distant Supervision for Temporal Relation Extraction
Zero-Shot Cross-Lingual Dependency Parsing through Contextual Embedding Transformation
Gradual Fine-Tuning for Low-Resource Domain Adaptation
Adapting to the Long Tail in Language Understanding
Domain Adaptation for NMT via Filtered Iterative Back-Translation