(完成)ICLR2018
(2.3%的口头展示,31.4%的poster接受,9%的workshop)
-
!!!!(DIIN)Natural Language Inference over Interaction Space
-
!!!!(IR,多任务学习)Multi-Task Learning for Document Ranking and Query Suggestion
-
!!!!(表达学习)An efficient framework for learning sentence representations
-
!!(表达学习,多任务学习)Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning
-
!!!!(序列建模)Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling
-
!!!!(开放域QA)Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering
-
!!!(QA,强化学习)Ask the Right Questions: Active Question Reformulation with Reinforcement Learning
-
!!(MRC)QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension
-
!!(MRC)DCN+: Mixed Objective And Deep Residual Coattention for Question Answering
-
!!(MRC)FusionNet: Fusing via Fully-aware Attention with Application to Machine Comprehension
-
(MRC)Multi-Mention Learning for Reading Comprehension with Neural Cascades
-
(摘要)Generating Wikipedia by Summarizing Long Sequences
-
(表达学习)A New Method of Region Embedding for Text Classification
-
(语言模型)breaking_the_softmax_bottleneck:a_high_rank_rnn_language_model
-
(语言模型)Neural Language Modeling by Jointly Learning Syntax and Lexicon
-
(文本生成,GAN)MaskGAN: Better Text Generation via Filling in the ___
-
(摘要)A Deep Reinforced Model for Abstractive Summarization
-
(LSTM的可解释性,情感分析)Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs
-
(迁移学习)Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation
-
(图卷积+self-attention)Graph Attention Networks
-
(多任务学习)Routing Networks: Adaptive Selection of Non-Linear Functions for Multi-Task Learning
-
All-but-the-Top: Simple and Effective Postprocessing for Word Representations
-
!!(一个逻辑蕴含的数据集)Can Neural Networks Understand Logical Entailment?
-
Spherical CNNs
-
(多任务学习)Beyond Shared Hierarchies: Deep Multitask Learning through Soft Layer Ordering
-
(transformer-based)Non-Autoregressive Neural Machine Translation