Paper-Seminar

• Response Generation

  • Internet-Augmented Dialogue Generation
    • https://arxiv.org/pdf/2107.07566.pdf
  • Retrieve and Refine: Improved Sequence Generation Models For Dialogue
    • https://arxiv.org/pdf/1808.04776.pdf
  • Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue
    • https://arxiv.org/pdf/2002.07510.pdf
  • Learning to Copy Coherent Knowledge for Response Generation
    • https://ojs.aaai.org/index.php/AAAI/article/view/17486
  • Conversational Graph Grounded Policy Learning for Open-Domain Conversation Generation
    • https://aclanthology.org/2020.acl-main.166.pdf
  • Learning a Simple and Effective Model for Multi-turn Response Generation with Auxiliary Tasks
    • https://arxiv.org/pdf/2004.01972.pdf
  • Sequence to Backward and Forward Sequences: A Content-Introducing Approach to Generative Short-Text Conversation
    • https://aclanthology.org/C16-1316.pdf

• Sentence Embedding

  • DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings
    • https://arxiv.org/abs/2204.10298
  • Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models
    • https://arxiv.org/abs/2108.08877
  • Dual-View Distilled BERT for Sentence Embedding
    • https://arxiv.org/pdf/2104.08675.pdf
  • SimCSE: Simple Contrastive Learning of Sentence Embeddings
    • https://arxiv.org/pdf/2104.08821.pdf
  • SBERT-WK: A Sentence Embedding Method by Dissecting BERT-based Word Models
    • https://arxiv.org/pdf/2002.06652.pdf
  • Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
    • https://arxiv.org/pdf/1908.10084.pdf
  • Learning Effective and Interpretable Semantic Models using Non-Negative Sparse Embedding
    • https://www.aclweb.org/anthology/C12-1118.pdf

• Knoweldge Distillation

  • Distilling the Knowledge in a Neural Network
    • https://arxiv.org/pdf/1503.02531.pdf
  • Improved Knowledge Distillation via Teacher Assistant
    • https://arxiv.org/pdf/1902.03393.pdf
  • Knowledge Distillation Meets Self-Supervistion
    • https://arxiv.org/pdf/2006.07114.pdf
  • DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
    • https://arxiv.org/pdf/1910.01108.pdf
  • TinyBERT: Distilling BERT for Natural Language Understanding
    • https://arxiv.org/pdf/1909.10351.pdf
  • MINILM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers
    • https://arxiv.org/pdf/2002.10957.pdf
  • ERNIE-Tiny : A Progressive Distillation Framework for Pretrained Transformer Compression
    • https://arxiv.org/pdf/2106.02241.pdf

• Video Question Answering

  • DramaQA: Character-Centered Video Story Understanding with Hierarchical QA
    • https://arxiv.org/pdf/2005.03356.pdf
  • Modality Shifting Attention Network for Multi-modal Video Question Answering
    • https://arxiv.org/pdf/2007.02036.pdf
  • MMFT-BERT: Multimodal Fusion Transformer with BERT Encodings for Visual Question Answering
    • https://arxiv.org/pdf/2010.14095.pdf

• Information Retrieval

  • Dense Passage Retrieval for Open-Domain Question Answering
    • https://arxiv.org/pdf/2004.04906.pdf
  • ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
    • https://arxiv.org/pdf/2004.12832.pdf

• Natural Language Understanding

  • Don't Stop Pretraining: Adapt Language Models to Domains and Tasks
    • https://arxiv.org/abs/2004.10964
  • ELECTRA pre-training text encoders as discriminators rather than generators
    • https://arxiv.org/pdf/2003.10555.pdf
  • BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
    • https://arxiv.org/pdf/1810.04805.pdf
  • Unifying Vision-and-Language Tasks via Text Generation
    • https://arxiv.org/pdf/2102.02779.pdf
  • Understanding the difficulty of training transformers
    • https://arxiv.org/pdf/2004.08249.pdf
  • Do NLP Models Know Numbers? Probing Numeracy in Embeddings
    • https://arxiv.org/pdf/1909.07940.pdf

• Continual Learning

  • Overcoming catastrophic forgetting in neural networks
    • https://arxiv.org/pdf/1612.00796.pdf
  • Progressive Neural Networks
    • https://arxiv.org/pdf/1606.04671.pdf
  • Continual Learning with Deep Generative Replay
    • https://arxiv.org/pdf/1705.08690.pdf
  • Continual Learning for Natural Language Generation in Task-oriented Dialog Systems
    • https://arxiv.org/pdf/2010.00910.pdf

• Text Summarization

  • BRIO: Bringing Order to Abstractive Summarization
    • https://arxiv.org/abs/2203.16804

• Meta Learning

  • BOIL: Towards Representation Change for Few-shot Learning
    • https://arxiv.org/abs/2008.08882
  • Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
    • https://arxiv.org/abs/1703.03400