paper-reading

Group Paper Reading

2022-02-26

Presenter: Shao Wei

Topic: Self Explaining Model

Paper List:

1. Generalizable and Explainable Dialogue Generation via Explicit Action Learning
2. Self-Explaining Structures Improve NLP Models
3. ProtGNN: Towards Self-Explaining Graph Neural Networks

2022-03-04

Presenter: Zhao Xueliang

Topic: Zero-shot Task Generalization

Paper List:

1. ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning
2. Multitask Prompted Training Enables Zero-Shot Task Generalization
3. Finetuned Language Models are Zero-Shot Learners

2022-03-11

Presenter: Jiang Ruili

Topic: Few-shot Classification

Paper List:

1. Few-Shot Named Entity Recognition: An Empirical Baseline Study
2. Prototypical Contrastive Learning of Unsupervised Representations
3. QaNER: Prompting Question Answering Models for Few-shot Named Entity Recognition

2022-03-18

Presenter: Xu Jiahao

Topic: NMT Decoding Bias and Minimum Bayesian Risk

Paper List:

1. If Beam Search is the Answer, What was the Question?
2. Is MAP Decoding All You Need?
3. Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation

2022-03-25

Presenter: Li Huayang

Topic: Instance-level Attribution

Paper List:

1. Input Similarity from the Neural Network Perspective
2. Representer Point Selection for Explaining Deep Neural Networks
3. Influence Functions in Deep Learning Are Fragile

2022-04-01

Presenter: Chen Yi

Topic: Unsupervised Paraphrase Generation

Paper List:

1. Revisiting Pivot-Based Paraphrase Generation: Language Is Not the Only Optional Pivot
2. Unsupervised Paraphrasing with Pretrained Language Models
3. ConRPG: Paraphrase Generation using Contexts as Regularizer

2022-04-08

Presenter: Shen Lingfeng

Topic: Exploration on Mon-adversarial Perturbation in NLP

Paper List:

1. Evaluating the Robustness of Neural Language Models to Input Perturbations
2. Evaluating Robustness to Input Perturbations for Neural Machine Translation
3. Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification
4. Interpreting the Robustness of Neural NLP Models to Textual Perturbations

2022-04-15

Presenter: Lin Wenye

Topic: Graph Neural Network

Paper List:

1. Graph Attention Network
2. GraphSAGE
3. Graph Transformer for Graph-to-Sequence Learning

2022-04-22

Presenter: Yu Guoxin

Topic: Aspect-based Sentiment Analysis

Paper List:

1. Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Training
2. Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis
3. Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction

2022-05-06

Presenter: Hao Hongkun

Topic: Retrieval Augmented Approaches in NLP

Paper List:

1. Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering
2. Efficient Cluster-Based k-Nearest-Neighbor Machine Translation
3. Cross-Lingual Phrase Retrieval

2022-05-13

Presenter: Wang Yan

Topic: The Evolution of Our Retrieval Augmented Generation Paradigm

Paper List:

1. NAACL 2019 Skeleton to Response : Dialogue Generation Guided by Retrieval Memory
2. EMNLP 2019: Retrieval guided Dialogue Response Generation via a Matching to Generation Framework
3. TASLP: Prototype to Style : Dialogue Generation with Style Aware Editing on Retrieval Memory
4. ACL 2020: Generate, Delete and Rewrite: A Three Stage Framework for Improving Persona Consistency of Dialogue Generation
5. ACL 2021: Neural Machine Translation with Monolingual Translation Memory (Outstanding Paper Award)
6. Arxiv : Exploring Dense Retrieval for Dialogue Response Selection