LTI Researchers Star Once Again at NAACL 2021
19 Papers Accepted from LTI Authors
LTI faculty and students are once again featured prominently at this year's conference of the North American chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL HLT 2021). The conference includes 19 papers with at least one LTI author, with 23 members of the LTI community represented in total.
NAACL HLT, now in its 19th year, is one of the world’s premier conferences in the fields of computation linguistics and natural language processing. The conference takes place remotely from June 6-11.
Papers and presentations including LTI researchers are as follows, with the names of LTI authors in bold text:
Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models
Po-Yao Huang, Mandela Patrick, Junjie Hu, Graham Neubig, Florian Metze and Alexander Hauptmann
StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer
Yiwei Lyu, Paul Pu Liang, Hai Pham, Eduard Hovy, Barnabás Póczos, Ruslan Salakhutdinov and Louis-Philippe Morency
GSum: A General Framework for Guided Neural Abstractive Summarization
Zi-Yi Dou, Pengfei Liu, Hiroaki Hayashi, Zhengbao Jiang and Graham Neubig
Case Study: Deontological Ethics in NLP
Shrimai Prabhumoye, Brendon Boldt, Ruslan Salakhutdinov and Alan W Black
Multi-view Subword Regularization
Xinyi Wang, Sebastian Ruder and Graham Neubig
Larger-Context Tagging: When and Why Does It Work?
Jinlan Fu, Liangjing Feng, Qi Zhang, Xuanjing Huang and Pengfei Liu
Explicit Alignment Objectives for Multilingual Bidirectional Encoders
Junjie Hu, Melvin Johnson, Orhan Firat, Aditya Siddhant and Graham Neubig
On Learning Text Style Transfer with Direct Rewards
Yixin Liu, Graham Neubig and John Wieting
Focused Attention Improves Document-Grounded Generation
Shrimai Prabhumoye, Kazuma Hashimoto, Yingbo Zhou, Alan W Black and Ruslan Salakhutdinov
Compositional Generalization for Neural Semantic Parsing via Span-level Supervised Attention
Pengcheng Yin, Hao Fang, Graham Neubig, Adam Pauls, Emmanouil Antonios Platanios, Yu Su, Sam Thomson and Jacob AndreasMeta
XL: Meta Representation Transformation for Low-resource Cross-lingual Learning
Mengzhou Xia, Guoqing Zheng, Subhabrata Mukherjee, Milad Shokouhi, Graham Neubig and Ahmed Hassan Awadallah
RefSum: Refactoring Neural Summarization
Yixin Liu, Zi-Yi Dou and Pengfei Liu
MTAG: Modal-Temporal Attention Graph for Unaligned Human Multimodal Language Sequences
Jianing Yang, Yongxin Wang, Ruitao Yi, Yuying Zhu, Azaan Rehman, Amir Zadeh, Soujanya Poria and Louis-Philippe Morency
Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality
Metrics Artidoro Pagnoni, Vidhisha Balachandran and Yulia Tsvetkov
Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks
Siddharth Dalmia, Brian Yan, Vikas Raunak, Florian Metze and Shinji Watanabe
Controlling Dialogue Generation with Semantic Exemplars
Prakhar Gupta, Jeffrey Bigham, Yulia Tsvetkov and Amy Pavel
COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List
Luyu Gao, Zhuyun Dai and Jamie Callan
Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa
Junqi Dai, Hang Yan, Tianxiang Sun, Pengfei Liu and Xipeng Qiu
Neural Language Modeling for Contextualized Temporal Graph Generation
Aman Madaan and Yiming Yang