Dense Passage Retrieval for Open-Domain Question Answering

NLP Papers === Information Retrieval --- - [Dense Passage Retrieval for Open-Domain Question Answering ](https://hackmd.io/@eric88525/DPR) - [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://hackmd.io/@eric88525/colbert) - [ColBERTv2:Effective and Efficient Retrieval via Lightweight Late Interaction](https://hackmd.io/@eric88525/colbert-v2) - [RocketQAv2: A Joint Training Method for Dense Passage Retrievaland Passage Re-ranking](https://hackmd.io/@eric88525/rocketqa-v2) - [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://hackmd.io/@eric88525/ance) - [Multi-Stage Document Ranking with BERT](https://hackmd.io/@eric88525/mranknig) - [PAIR: Leveraging Passage-Centric Similarity Relation forImproving Dense Passage Retrieval](https://hackmd.io/@eric88525/pair) - [GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of](https://hackmd.io/@eric88525/GPL) Named Entity Recognition --- + [MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NER (ACL 2022)](https://hackmd.io/@eric88525/melm) + [Learning from Noisy Labels for Entity-Centric Information Extraction (EMNLP 2021)](https://hackmd.io/@eric88525/noise-ner) + [LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention (EMNLP 2020)](https://hackmd.io/@eric88525/luke) + [Automated Concatenation of Embeddings for Structured Prediction (ACL 2021)](https://hackmd.io/@eric88525/ACE) + [SpanNER: Named Entity Re-/Recognition as Span Prediction (ACL 2021)](https://hackmd.io/@eric88525/span-ner) + [Packed Levitated Marker for Entity and Relation Extraction (ACL 2022)](https://hackmd.io/@eric88525/plm) Pre-trainning --- + [Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks (ACL2020)](https://hackmd.io/@eric88525/dapt) + [ALBERT: A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS (ICLR 2020)](https://hackmd.io/@eric88525/albert) QA --- - [Reading Wikipedia to Answer Open-Domain Questions (ACL 2017)](https://hackmd.io/@eric88525/drqa) + [Named Entity Recognition without Gazetteers (ACL 1999)](https://hackmd.io/@eric88525/ner-wo-gazetteers)