🗂 ACL2020 的论文、代码和博客。
- 【1995】Centering: A Framework for Modeling the Local Coherence of Discourse.[Paper]
- 【1995】Unsupervised Word Sense Disambiguation Rivaling Supervised Methods.[Paper]
- 【2010】Distributional Memory: A General Framework for Corpus-based Semantics.[Paper]
- 【2010】Word Representations: A Simple and General Method for Semi-supervised Learning.[Paper]
-
ACL2020 Tutorial: Open-Domain Question Answering [Code]
-
KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation [Paper] [Code] [Blog]
-
Multi-Agent Task-Oriented Dialog Policy Learning with Role-aware Reward Decomposition [Paper]
-
ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems [Paper]
-
CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset [Paper] [Code]
-
PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable [Paper]
-
dynamic induction networks for few-shot text classification [Blog]
-
Learning Low-Resource End-To-End Goal-Oriented Dialog for Fast and Reliable System Deployment [Blog]
-
Data Manipulation: Towards Effective Instance Learning for Neural Dialogue Generation via Learning to Augment and Reweight [Paper]
-
Grounding Conversations with Improvised Dialogues [Paper] [Code]
-
Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking [Paper] [Code]
-
Dialogue Coherence Assessment Without Explicit Dialogue Act Labels [Code]
-
Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA [Paper] [Code]
-
Conversational Word Embedding for Retrieval-based Dialog System [Paper] [Code]
-
INFOTABS: Inference on Tables as Semi-structured Data [Paper] [Code] [Blog]
- A Self-training Method for Machine Reading Comprehension with Soft Evidence Extraction
-
ScriptWriter: Narrative-Guided Script Generation [Blog]
-
A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation [Paper] [Code]
-
Pre-train and Plug-in: Flexible Conditional Text Generation with Variational Auto-Encoders [Paper] [Code]
-
Logical Natural Language Generation from Open-Domain Tables [Paper] [Code]
- A Discourse-Aware Neural Extractive Model for Text Summarization [Paper] [Code]
- Heterogeneous Graph Neural Networks for Extractive Document Summarization [Paper] [Code]
- Unsupervised Opinion Summarization with Noising and Denoising [Paper] [Code]
- A Novel Hierarchical Binary Tagging Framework for Relational Triple Extraction [Paper] [Code] [Blog]
- Modeling Code-Switch Languages Using Bilingual Parallel Corpus [Blog]
-
Character-Level Translation with Self-attention [Paper] [Code]
-
Contextual Neural Machine Translation Improves Translation of Cataphoric Pronouns [Paper] [Code]
-
GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Media [Paper] [Code]
-
Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior? [Paper] [Code]
-
FastBERT: a Self-distilling BERT with Adaptive Inference Time [Paper] [Code] [Code2]
-
Attend, Translate and Summarize: An Efficient Method for Neural Cross-Lingual Summarization [Code]
-
An Effective Transition-based Model for Discontinuous NER [Paper] [Code]
-
AMR Parsing via Graph-Sequence Iterative Inference [Paper] [Code]
-
Hypernymy Detection for Low-Resource Languages via Meta Learning [Code]
-
NAT: Noise-Aware Training for Robust Neural Sequence Labeling [Code]
-
R^3: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge [Paper] [Code]
-
Learning Constraints for Structured Prediction Using Rectifier Networks [Code]
-
Contrastive Self-Supervised Learning for Commonsense Reasoning [Paper] [Code]
-
Transformer Anatomy: Roles and Utilization of Attention Heads in Transformer-based Neural Language Models [Code]
-
Improving Segmentation for Technical Support Problems [Code]
-
AMR Parsing with Latent Structural Information [Code]
-
From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains [Code]
-
Diverse and Informative Dialogue Generation with Context-Specific Commonsense Knowledge Awareness [Code]
-
Supervised Grapheme-to-Phoneme Conversion of Orthographic Schwas in Hindi and Punjabi [Paper] [Code]
-
Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance [Paper] [Code]
-
On the Robustness of Language Encoders against Grammatical Errors Paper] [Code]
-
Will-They-Won’t-They: A Very Large Dataset for Stance Detection on Twitter Paper] [Code]
-
Semi-supervised Contextual Historical Text Normalization [Code]
-
Empowering Active Learning to Jointly Optimize System and User Demands Paper] [Code]
-
Enhancing Pre-trained Chinese Character Representation with Word-aligned Attention [Code]
-
Refer360°: A Referring Expression Recognition Dataset in 360°Images [Code]
-
Tree-Structured Neural Topic Model [Code]
-
A Contextual Hierarchical Attention Network with Adaptive Objective for Dialogue State Tracking [Code]
-
MOOCCube: A Large-scale Data Repository for NLP Applications in MOOCs [Code] [Blog]
-
Fact-based Content Weighting for Evaluating Abstractive Summarisation [Code]
未被接受并不表面工作没有意义，也可能是不幸运！