NLP最新论文paper记录

1. Lessons Learned from Applying off-the-shelf BERT: There is no SilverBullet
   
2. Multimodal Joint Attribute Prediction and Value Extraction for E-commerce Product
3. Dialogue Response Ranking Training with Large-Scale Human Feedback Data
   
4. Attention Flows: Analyzing and Comparing Attention Mechanisms in Language Models
5. Combining Word and Character Vector Representation on Neural Machine Translation
6. The birth of Romanian BERT
7. Rethinking Supervised Learning and Reinforcement Learning in Task-Oriented Dialogue Systems
8. Application-Based Coexistence of Different Waveforms on Non-orthogonal Multiple Access
9. Word class flexibility: A deep contextualized approach
   
10. Will it Unblend?
    
11. On the Ability of Self-Attention Networks to Recognize Counter Languages
    
12. Hierarchical Pre-training for Sequence Labelling in Spoken Dialog
    
13. LA-HCN: Label-based Attention for Hierarchical Multi-label TextClassification Neural Network
    
14. On Data Augmentation for Extreme Multi-label Classification
    
15. Novel Keyword Extraction and Language Detection Approaches
    
16. Adapting BERT for Word Sense Disambiguation with Gloss Selection Objective and Example Sentences
    
17. Generating Commonsense Explanation by Extracting Bridge Concepts from Reasoning Paths
    
18. Language Generation with Multi-Hop Reasoning on Commonsense Knowledge Graph
    
19. Structure Aware Negative Sampling in Knowledge Graphs
    
20. Contrastive Distillation on Intermediate Representations for Language Model Compression
    
21. Utility is in the Eye of the User: A Critique of NLP Leaderboards
    
22. SynSetExpan: An Iterative Framework for Joint Entity Set Expansion and Synonym Discovery
    
23. On the importance of pre-training data volume for compact language models
    
24. Discriminatively-Tuned Generative Classifiers for Robust Natural Language Inference
    
25. Exploring and Evaluating Attributes, Values, and Structures for Entity Alignment
    
26. Like hiking? You probably enjoy nature: Persona-grounded Dialog with Commonsense Expansions
    
27. Is the Best Better? Bayesian Statistical Model Comparison for Natural Language Processing
    
28. Learning to Represent Image and Text with Denotation Graph
    
29. Constrained Decoding for Computationally Efficient Named Entity Recognition Taggers
    
30. Text Classification Using Label Names Only: A Language Model Self-Training Approach
    
31. https://arxiv.org/abs/2010.08318
32. Coarse-to-Fine Pre-training for Named Entity Recognition
    
33. Unsupervised Natural Language Inference via Decoupled Multimodal Contrastive Learning
    
34. Not all parameters are born equal: Attention is mostly what you need
    
35. Hierarchical Metadata-Aware Document Categorization under Weak Supervision
    
36. Word2vec Conjecture and A Limitative Result
    
37. Be More with Less: Hypergraph Attention Networks for Inductive Text Classification
    
38. Rumor Detection on Twitter Using Multiloss Hierarchical BiLSTM with an Attenuation Factor
    
39. Semantic similarity-based approach to enhance supervised classification learning accuracy
    
40. Random Feature Attention
41. Few-shot Learning for Slot Tagging with Attentive Relational Network
    
42. Reinforcement Learning with External Knowledge by using Logical Neural Networks
43. Hierarchical Transformer for Multilingual Machine Translation
44. A SURVEY OF EMBODIED AI: FROM SIMULATORS TO RESEARCH TASKS
45. Multimodal VAE Active Inference Controller