RAG / 检索增强生成 - arXivDaily 专题

2208.06959 2022-08-16 cs.IR cs.AI cs.LG 62%

Evaluating Dense Passage Retrieval using Transformers

Nima Sadri

专题命中检索器与排序：dense retrieval(abstract)；分类 cs.IR、cs.AI

2208.05152 2022-08-11 cs.CL cs.IR 62%

TagRec++: Hierarchical Label Aware Attention Network for Question Categorization

Venktesh Viswanathan, Mukesh Mohania, Vikram Goyal

专题命中检索器与排序：dense retrieval(abstract)；分类 cs.IR、cs.CL

Comments 12 pages, double column, Under review at IEEE Transactions on Knwoledge and Data Engineering. arXiv admin note: text overlap with arXiv:2107.10649

2112.01488 2022-07-12 cs.IR cs.CL 62%

ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction

Keshav Santhanam, Omar Khattab, Jon Saad-Falcon, Christopher Potts, Matei Zaharia

专题命中检索器与排序：retriever(abstract)；分类 cs.IR、cs.CL

Comments NAACL 2022. Omar and Keshav contributed equally to this work

2101.00436 2022-07-12 cs.CL cs.IR 62%

Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval

Omar Khattab, Christopher Potts, Matei Zaharia

专题命中检索器与排序：retriever(abstract)；分类 cs.IR、cs.CL

Comments NeurIPS 2021 (Spotlight)

2206.08063 2022-06-17 cs.IR cs.CL 62%

Towards Robust Ranker for Text Retrieval

Yucheng Zhou, Tao Shen, Xiubo Geng, Chongyang Tao, Can Xu, Guodong Long, Binxing Jiao, Daxin Jiang

专题命中检索器与排序：retriever(abstract)；分类 cs.IR、cs.CL

Comments 11 pages of main content, 4 tables, 3 figures

2205.14226 2022-06-02 cs.IR cs.CL 62%

Fast and Light-Weight Answer Text Retrieval in Dialogue Systems

Hui Wan, Siva Sankalp Patel, J. William Murdock, Saloni Potdar, Sachindra Joshi

专题命中检索器与排序：dense retrieval(abstract)；分类 cs.IR、cs.CL

Comments Accepted in NAACL-HLT 2022 Industry Track

2205.07872 2022-05-18 cs.LG cs.AI cs.CL 62%

ScAN: Suicide Attempt and Ideation Events Dataset

Bhanu Pratap Singh Rawat, Samuel Kovaly, Wilfred R. Pigeon, Hong Yu

专题命中检索器与排序：retriever(abstract)；分类 cs.CL、cs.AI

Comments Paper accepted at NAACL 2022

2112.07708 2022-05-18 cs.CL cs.IR 62%

Learning to Retrieve Passages without Supervision

Ori Ram, Gal Shachaf, Omer Levy, Jonathan Berant, Amir Globerson

专题命中检索器与排序：retriever(abstract)；分类 cs.IR、cs.CL

Comments NAACL 2022

2205.04733 2022-05-13 cs.IR cs.CL 62%

From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective

Thibault Formal, Carlos Lassance, Benjamin Piwowarski, Stéphane Clinchant

专题命中检索器与排序：retriever(abstract)；分类 cs.IR、cs.CL

Comments Accepted at SIGIR22 as a short paper (this work is the extension of SPLADE v2)

2204.00716 2022-04-27 cs.IR cs.CL 62%

CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos

Shengyao Zhuang, Guido Zuccon

专题命中检索器与排序：retriever(abstract)；分类 cs.IR、cs.CL

Comments 9 pages full paper, accepted at SIGIR2022

2204.11545 2022-04-26 cs.IR cs.CL cs.LG 62%

LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback

Yunchang Zhu, Liang Pang, Yanyan Lan, Huawei Shen, Xueqi Cheng

专题命中检索器与排序：dense retrieval(abstract)；分类 cs.IR、cs.CL

Comments Accepted at SIGIR 2022

2204.10558 2022-04-25 cs.IR cs.CL cs.LG 62%

Sparse and Dense Approaches for the Full-rank Retrieval of Responses for Dialogues

Gustavo Penha, Claudia Hauff

专题命中检索器与排序：dense retrieval(abstract)；分类 cs.IR、cs.CL

2204.09248 2022-04-21 cs.CL cs.IR 62%

Synthetic Target Domain Supervision for Open Retrieval QA

Revanth Gangi Reddy, Bhavani Iyer, Md Arafat Sultan, Rong Zhang, Avirup Sil, Vittorio Castelli, Radu Florian, Salim Roukos

专题命中检索器与排序：retriever(abstract)；分类 cs.IR、cs.CL

Comments Published at SIGIR 2021

2203.08517 2022-03-17 cs.CL cs.AI 62%

TegTok: Augmenting Text Generation via Task-specific and Open-world Knowledge

Chao-Hong Tan, Jia-Chen Gu, Chongyang Tao, Zhen-Hua Ling, Can Xu, Huang Hu, Xiubo Geng, Daxin Jiang

专题命中检索器与排序：dense retrieval(abstract)；分类 cs.CL、cs.AI

Comments Accepted by Findings of ACL 2022

2203.07722 2022-03-16 cs.SE cs.AI cs.CL 62%

ReACC: A Retrieval-Augmented Code Completion Framework

Shuai Lu, Nan Duan, Hojae Han, Daya Guo, Seung-won Hwang, Alexey Svyatkovskiy

专题命中检索器与排序：retriever(abstract)；分类 cs.CL、cs.AI

Comments Published in ACL 2022

2105.06597 2022-02-25 cs.CL cs.AI 62%

RetGen: A Joint framework for Retrieval and Grounded Text Generation Modeling

Yizhe Zhang, Siqi Sun, Xiang Gao, Yuwei Fang, Chris Brockett, Michel Galley, Jianfeng Gao, Bill Dolan

专题命中检索器与排序：retriever(abstract)；分类 cs.CL、cs.AI

Comments accepted by AAAI-22, camera ready version

2201.11153 2022-01-28 cs.CL cs.IR 62%

Addressing Issues of Cross-Linguality in Open-Retrieval Question Answering Systems For Emergent Domains

Alon Albalak, Sharon Levy, William Yang Wang

专题命中检索器与排序：retriever(abstract)；分类 cs.IR、cs.CL

Comments 6 pages, 8 figures

2201.07745 2022-01-20 cs.IR cs.CL 62%

Improving Biomedical Information Retrieval with Neural Retrievers

Man Luo, Arindam Mitra, Tejas Gokhale, Chitta Baral

专题命中检索器与排序：retriever(abstract)；分类 cs.IR、cs.CL

Comments Accepted at AAAI 2022

2201.01706 2022-01-06 cs.CL cs.AI 62%

Multi Document Reading Comprehension

Avi Chawla

专题命中检索器与排序：retriever(abstract)；分类 cs.CL、cs.AI

Comments 10 pages, 6 Figures

2201.00365 2022-01-04 cs.IR cs.CL 62%

Establishing Strong Baselines for TripClick Health Retrieval

Sebastian Hofstätter, Sophia Althammer, Mete Sertkan, Allan Hanbury

专题命中检索器与排序：dense retrieval(abstract)；分类 cs.IR、cs.CL

Comments Accepted at ECIR 2022

2110.07752 2021-10-22 cs.CL cs.IR 62%

Hindsight: Posterior-guided training of retrievers for improved open-ended generation

Ashwin Paranjape, Omar Khattab, Christopher Potts, Matei Zaharia, Christopher D. Manning

专题命中检索器与排序：retriever(abstract)；分类 cs.IR、cs.CL

2109.08133 2021-09-17 cs.CL cs.IR 62%

Phrase Retrieval Learns Passage Retrieval, Too

Jinhyuk Lee, Alexander Wettig, Danqi Chen

专题命中检索器与排序：dense retrieval(abstract)；分类 cs.IR、cs.CL

Comments EMNLP 2021. Code available at https://github.com/princeton-nlp/DensePhrases

2108.06279 2021-08-20 cs.IR cs.CL 62%

On Single and Multiple Representations in Dense Passage Retrieval

Craig Macdonald, Nicola Tonellotto, Iadh Ounis

专题命中检索器与排序：dense retrieval(abstract)；分类 cs.IR、cs.CL

Comments Published at the 11th Italian Information Retrieval Workshop (IIR 2021)

2010.06467 2021-08-20 cs.IR cs.CL 62%

Pretrained Transformers for Text Ranking: BERT and Beyond

Jimmy Lin, Rodrigo Nogueira, Andrew Yates

专题命中检索器与排序：dense retrieval(abstract)；分类 cs.IR、cs.CL

Comments Final preproduction version of volume in Synthesis Lectures on Human Language Technologies by Morgan & Claypool

2108.05540 2021-08-13 cs.IR cs.CL 62%

Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval

Luyu Gao, Jamie Callan

专题命中检索器与排序：dense retrieval(abstract)；分类 cs.IR、cs.CL

2106.04134 2021-06-09 cs.CL cs.AI cs.LG 62%

Cheap and Good? Simple and Effective Data Augmentation for Low Resource Machine Reading

Hoang Van, Vikas Yadav, Mihai Surdeanu

专题命中检索器与排序：retriever(abstract)；分类 cs.CL、cs.AI

Comments 5 pages, 1 figure, SIGIR 2021

2105.11269 2021-06-03 cs.CL cs.AI 62%

Neural Machine Translation with Monolingual Translation Memory

Deng Cai, Yan Wang, Huayang Li, Wai Lam, Lemao Liu

专题命中检索器与排序：retriever(abstract)；分类 cs.CL、cs.AI

Comments ACL2021

2105.11174 2021-05-25 cs.CL cs.AI 62%

Retrieval Enhanced Model for Commonsense Generation

Han Wang, Yang Liu, Chenguang Zhu, Linjun Shou, Ming Gong, Yichong Xu, Michael Zeng

专题命中检索器与排序：retriever(abstract)；分类 cs.CL、cs.AI

Comments Findings of ACL-IJCNLP 2021

2011.02705 2020-11-06 cs.CL cs.AI 62%

Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources

Qianglong Chen, Feng Ji, Haiqing Chen, Yin Zhang

专题命中检索器与排序：knowledge retrieval(abstract)；分类 cs.CL、cs.AI

Comments Accepted at COLING 2020

2011.01580 2020-11-04 cs.IR cs.CL 62%

CMT in TREC-COVID Round 2: Mitigating the Generalization Gaps from Web to Special Domain Search

Chenyan Xiong, Zhenghao Liu, Si Sun, Zhuyun Dai, Kaitao Zhang, Shi Yu, Zhiyuan Liu, Hoifung Poon, Jianfeng Gao, Paul Bennett

专题命中检索器与排序：dense retrieval(abstract)；分类 cs.IR、cs.CL

Comments 5 pages, 3 figures, 2 tables

1. 检索器与排序 4558 篇

Evaluating Dense Passage Retrieval using Transformers

TagRec++: Hierarchical Label Aware Attention Network for Question Categorization

ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction

Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval

Towards Robust Ranker for Text Retrieval

Fast and Light-Weight Answer Text Retrieval in Dialogue Systems

ScAN: Suicide Attempt and Ideation Events Dataset

Learning to Retrieve Passages without Supervision

From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective

CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos

LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback

Sparse and Dense Approaches for the Full-rank Retrieval of Responses for Dialogues

Synthetic Target Domain Supervision for Open Retrieval QA

TegTok: Augmenting Text Generation via Task-specific and Open-world Knowledge

ReACC: A Retrieval-Augmented Code Completion Framework

RetGen: A Joint framework for Retrieval and Grounded Text Generation Modeling

Addressing Issues of Cross-Linguality in Open-Retrieval Question Answering Systems For Emergent Domains

Improving Biomedical Information Retrieval with Neural Retrievers

Multi Document Reading Comprehension

Establishing Strong Baselines for TripClick Health Retrieval

Hindsight: Posterior-guided training of retrievers for improved open-ended generation

Phrase Retrieval Learns Passage Retrieval, Too

On Single and Multiple Representations in Dense Passage Retrieval

Pretrained Transformers for Text Ranking: BERT and Beyond

Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval

Cheap and Good? Simple and Effective Data Augmentation for Low Resource Machine Reading

Neural Machine Translation with Monolingual Translation Memory

Retrieval Enhanced Model for Commonsense Generation

Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources

CMT in TREC-COVID Round 2: Mitigating the Generalization Gaps from Web to Special Domain Search