Others.md

Others

Efficient Transformers

Efficient Transformers

• Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context Zihang Dai, Zhilin Yang, Yiming Yang, Jaime Carbonell, Quoc V. Le, Ruslan Salakhutdinov ACL19 [pdf] [code]
• Star-Transformer Qipeng Guo, Xipeng Qiu, Pengfei Liu, Yunfan Shao, Xiangyang Xue, Zheng Zhang NAACL19 [pdf] [code]
• BP-Transformer: Modelling Long-Range Context via Binary Partitioning Zihao Ye, Qipeng Guo, Quan Gan, Xipeng Qiu, Zheng Zhang [pdf] [code]
• Reformer: The Efficient Transformer Nikita Kitaev, Łukasz Kaiser, Anselm Levskaya ICLR20 [pdf] [code]
• Longformer: The Long-Document Transformer Iz Beltagy, Matthew E. Peters, Arman Cohan [pdf] [code]
• Big Bird: Transformers for Longer Sequences Manzil Zaheer, Guru Guruganesh, Avinava Dubey, Joshua Ainslie, Chris Alberti, Santiago Ontanon, Philip Pham, Anirudh Ravula, Qifan Wang, Li Yang, Amr Ahmed [pdf]

Topic

1. tBERT: Topic Models and BERT Joining Forces for Semantic Similarity Detection Nicole Peinelt, Dong Nguyen, Maria Liakata ACL20 [pdf] [code]
2. Recurrent Hierarchical Topic-Guided RNN for Language Generation Dandan Guo, Bo Chen, Ruiying Lu, Mingyuan Zhou ICML20 [pdf] [code]

Multi-domain

1. Meta-Curriculum Learning for Domain Adaptation in Neural Machine Translation Runzhe Zhan, Xuebo Liu, Derek F. Wong, Lidia S. Chao AAAI21 [pdf] [code]
2. Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog Libo Qin, Xiao Xu, Wanxiang Che, Yue Zhang, Ting Liu ACL20 [pdf] [code]
3. Revisiting Multi-Domain Machine Translation MinhQuang Pham , Josep Maria Crego , François Yvon TACL21 [pdf]

Lifelong Language Learning

Paper	Conference
LAnguage MOdeling for Lifelong Language Learning	ICLR20
Episodic Memory in Lifelong Language Learning	NIPS19
Toward Continual Learning for Conversational Agents

Paper	Conference
Hierarchical Summary-to-Article Generation	ICLR20 under review
Entity-Relation Extraction as Multi-turn Question Answering	ACL19
GSN: A Graph-Structured Network for Multi-Party Dialogues	IJCAI19
Growing Story Forest Online from Massive Breaking News	CIKM17

Discourse

Paper	Conference
QADiscourse : Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselines	EMNLP20
基于实体网格的语篇表示模型研究
Disentangling Chat with Local Coherence Models	ACL11
Modeling Local Coherence: An Entity-Based Approach

Imitation Learning

Paper	Conference
Non-Monotonic Sequential Text Generation	ICML19
Imitation Learning with Recurrent Neural Networks
Learning to Search Better than Your Teacher	ICML15

Unsupervised

Paper	Conference
Multilingual Unsupervised NMT using Shared Encoder and Language-Specific Decoders	ACL19
Unsupervised Neural Text Simplification	ACL19
Unsupervised Question Answering by Cloze Translation	ACL19
Unsupervised Abstractive Meeting Summarization with Multi-Sentence Compression and Budgeted Submodular Maximization	ACL18

Speaker Modeling

Paper	Conference
Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots
Author2Vec: A Framework for Generating User Embedding
Towards Neural Speaker Modeling in Multi-Party Conversation: The Task, Dataset, and Models	LREC18
Speaker Role Contextual Modeling for Language Understanding and Dialogue Policy Learning	IJCNLP17
Intra-Speaker Topic Modeling for Improved Multi-Party Meeting Summarization with Integrated Random Walk	NAACL12

Textual Adversarial Attack and Defense

Paper	Conference	White or Black
Deep Text Classification Can be Fooled	IJCAI18	Both

Others

Paper	Conference
Learning to Update Natural Language Comments Based on Code Changes	ACL20

• Unsupervised Topic Segmentation of Meetings with BERT Embeddings Alessandro Solbiati, Kevin Heffernan, Georgios Damaskinos, Shivani Poddar, Shubham Modi, Jacques Cali [pdf]

Federated Learning

1. FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks Bill Yuchen Lin, Chaoyang He, Zihang Zeng, Hulin Wang, Yufen Huang, Christophe Dupuy, Rahul Gupta, Mahdi Soltanolkotabi, Xiang Ren, Salman Avestimehr NAACL 2022 Findings [pdf] [code]