Papers
Transformer Dissection: An Unified Understanding for Transformer’s Attention via the Lens of Kernel
Yao-Hung Hubert Tsai, Shaojie Bai, Makoto Yamada et al.
Neural Gaussian Copula for Variational Autoencoder
Prince Zizhuang Wang, William Yang Wang
Patient Knowledge Distillation for BERT Model Compression
Siqi Sun, Yu Cheng, Zhe Gan et al.
Identifying and Explaining Discriminative Attributes
Armins Stepanjans, André Freitas
WikiCREM: A Large Unsupervised Corpus for Coreference Resolution
Vid Kocijan, Oana-Maria Camburu, Ana-Maria Cretu et al.
Compositional Generalization for Primitive Substitutions
Yuanpeng Li, Liang Zhao, Jianyu Wang et al.
FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow
Xuezhe Ma, Chunting Zhou, Xian Li et al.
ARAML: A Stable Adversarial Training Framework for Text Generation
Pei Ke, Fei Huang, Minlie Huang et al.
Parallel Iterative Edit Models for Local Sequence Transduction
Abhijeet Awasthi, Sunita Sarawagi, Rasna Goyal et al.
Learning Latent Parameters without Human Response Patterns: Item Response Theory with Artificial Crowds
John P. Lalor, Hao Wu, Hong Yu
Unsupervised Domain Adaptation of Contextualized Embeddings for Sequence Labeling
Xiaochuang Han, Jacob Eisenstein
Distributionally Robust Language Modeling
Yonatan Oren, Shiori Sagawa, Tatsunori B. Hashimoto et al.
Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs
Mingyang Chen, Wen Zhang, Wei Zhang et al.
Exploiting Monolingual Data at Scale for Neural Machine Translation
Lijun Wu, Yiren Wang, Yingce Xia et al.
Fine-grained Knowledge Fusion for Sequence Labeling Domain Adaptation
Huiyun Yang, Shujian Huang, Xin-Yu Dai et al.
Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs
Angela Fan, Claire Gardent, Chloé Braud et al.
Learning to Ask for Conversational Machine Learning
Shashank Srivastava, Igor Labutov, Tom Mitchell
Topics to Avoid: Demoting Latent Confounds in Text Classification
Sachin Kumar, Shuly Wintner, Noah A. Smith et al.
Visualizing and Understanding the Effectiveness of BERT
Yaru Hao, Li Dong, Furu Wei et al.
Certified Robustness to Adversarial Word Substitutions
Robin Jia, Aditi Raghunathan, Kerem Göksel et al.
Hierarchically-Refined Label Attention Network for Sequence Labeling
Leyang Cui, Yue Zhang
Experimenting with Power Divergences for Language Modeling
Matthieu Labeau, Shay B. Cohen
Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control
Mo Yu, Shiyu Chang, Yang Zhang et al.
Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation
Po-Sen Huang, Robert Stanforth, Johannes Welbl et al.