caiyinqiong/semantic-retrieval-models

A curated list of awesome papers for Semantic Retrieval (TOIS Accepted: Semantic Models for the First-stage Retrieval: A Comprehensive Review).

semantic-retrieval-models's Issues

new

Questions Are All You Need to Train a Dense Passage Retriever（zero-shot）
HypeR: Multitask Hyper-Prompted Training Enables Large-Scale Retrieval Generalization（ICLR2023，zero-shot）
COCO-DR: Combating Distribution Shifts in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning (EMNLP2022, zero-shot)

Recommend to use this tool to collect retrieval-related papers

Hi, I am Gordon Lee.
Sorry to bother you with this issue.
Thanks for your excellent work on sematic-retrieval models.
Recently, MLNLP and I have made a search tool to collect top-tier conference up-to-date papers, which includes most top-tier conferences and journals from 2019-2022.
Unlike to dblp or google scholar, it only includes top-tier conferences and journals. So you can find the most related and valuable papers more effectively.
I believe this tool can help you to find more retrieval-related papers more efficiently. Welcome to use!
You can access it via the following link:
https://ai-paper-collector.vercel.app/
and you can find more details from our repo:
https://github.com/MLNLP-World/AI-Paper-collector
Such as:

The search category is as follows:

- [EMNLP 2019-2021] [ACL 2019-2022] [NAACL 2019-2022] [COLING 2020-2022] 
- [ICASSP 2019-2022] [WWW 2019-2022] [ICLR 2019-2022] [ICML 2019-2022] 
- [AAAI 2019-2022] [IJCAI 2019-2022] [CVPR 2019-2022] [ICCV 2019-2021] 
- [MM 2019-2022] [KDD 2019-2022] [CIKM 2019-2021] [SIGIR 2019-2022] 
- [WSDM 2019-2022] [ECIR 2019-2022] [ECCV 2020-2020] [COLT 2019-2022] 
- [AISTATS 2019-2022] [INTERSPEECH 2019-2021] [ISWC 2019-2021] [JMLR 2019-2022] 
- [VLDB 2019-2021] [ICME 2019-2022] [TIP 2020-2022] [TPAMI 2020-2022] 
- [RECSYS 2019-2022] [TKDE 2020-2022] [TOIS 2020-2022] [ICDM 2019-2021] 
- [TASLP 2020-2022] [BMVC 2019-2021] [MICCAI 2019-2022] [NIPS 2019-2021] 
- [MLSYS 2020-2022] [WACV 2020-2022] 

It also supports searching papers with specific years or/and specific authors, such as:

The results also can be exported to CSV/TXT/JSON files. You need only a few edits to add to your README.md.
For example:

[ACL2022]	Sentence-aware Contrastive Learning for Open-Domain Passage Retrieval
[ACL2022]	Retrieval-guided Counterfactual Generation for QA
[ACL2022]	Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval
[ACL2022]	Image Retrieval from Contextual Descriptions
[ACL2022]	Cross-Lingual Phrase Retrieval
[ACL2022]	Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering
[ACL2022]	Multi-View Document Representation Learning for Open-Domain Dense Retrieval
[ACL2022]	ReACC: A Retrieval-Augmented Code Completion Framework
[ACL2022]	A Statutory Article Retrieval Dataset in French
[ACL2022]	Clickbait Spoiling via Question Answering and Passage Retrieval
[ACL2022]	Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering
[ACL2022]	Generating Biographies on Wikipedia: The Impact of Gender Bias on the Retrieval-Based Generation of Women Biographies
[ACL2022]	Augmenting Document Representations for Dense Retrieval with Interpolation and Perturbation
[ACL2022]	Scene-Text Aware Image and Text Retrieval with Dual-Encoder
[ACL2022]	Compressing Sentence Representation for Semantic Retrieval via Homomorphic Projective Distillation
[ACL2022]	Two-Step Question Retrieval for Open-Domain QA
[ACL2022]	TABi: Type-Aware Bi-Encoders for Open-Domain Entity Retrieval
[ACL2022]	OneAligner: Zero-shot Cross-lingual Transfer with One Rich-Resource Language Pair for Low-Resource Sentence Retrieval
[ACL2022]	The Inefficiency of Language Models in Scholarly Retrieval: An Experimental Walk-through
[ACL2022]	LaPraDoR: Unsupervised Pretrained Dense Retriever for Zero-Shot Text Retrieval
[ACL2022]	Improving Candidate Retrieval with Entity Profile Generation for Wikidata Entity Linking
[ACL2022]	Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant Representations
[COLING2022]	Pan More Gold from the Sand: Refining Open-domain Dialogue Training with Noisy Self-Retrieval Generation
[COLING2022]	Addressing Leakage in Self-Supervised Contextualized Code Retrieval
[COLING2022]	CONCRETE: Improving Cross-lingual Fact-checking with Cross-lingual Retrieval
[COLING2022]	Towards Robust Neural Retrieval with Source Domain Synthetic Pre-Finetuning
[COLING2022]	Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval
[COLING2022]	Dense Template Retrieval for Customer Support
[COLING2022]	MuSeCLIR: A Multiple Senses and Cross-lingual Information Retrieval Dataset
[COLING2022]	Virtual Knowledge Graph Construction for Zero-Shot Domain-Specific Document Retrieval
[COLING2022]	DPTDR: Deep Prompt Tuning for Dense Passage Retrieval
[COLING2022]	Repo4QA: Answering Coding Questions via Dense Retrieval on GitHub Repositories
[COLING2022]	Augmentation, Retrieval, Generation: Event Sequence Prediction with a Three-Stage Sequence-to-Sequence Approach
[COLING2022]	DocQueryNet: Value Retrieval with Arbitrary Queries for Form-like Documents
[COLING2022]	Diverse Multi-Answer Retrieval with Determinantal Point Processes
[COLING2022]	SCL-RAI: Span-based Contrastive Learning with Retrieval Augmented Inference for Unlabeled Entity Problem in NER
[COLING2022]	CitRet: A Hybrid Model for Cited Text Span Retrieval
[COLING2022]	Generate-and-Retrieve: Use Your Predictions to Improve Retrieval for Semantic Parsing
[COLING2022]	Learning Decoupled Retrieval Representation for Nearest Neighbour Neural Machine Translation
...

new

Learning Diverse Document Representations with Deep Query Interactions for Dense Retrieval（2022，多向量）
Topic-Grained Text Representation-based Model for Document Retrieval（2022，多向量）

ToUpdate

Pre-training：

1. Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering（ACL2022）
2. RetroMAE v2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models(Arxiv, 2022)

Toupdate

Others
1: remove Towards Robust Dense Retrieval via Local Ranking Alignment
2. Asyncval: A Toolkit for Asynchronously Validating Dense Retriever Checkpoints during Training(SIGIR2022)

ToUpdate

Zero-shot：

1. Large Dual Encoders Are Generalizable Retrievers（Ni et al., 2021, arXiv, DTR）change to EMNLP2022
2. GPL: Generative pseudo labeling for unsupervised domain adaptation of dense retrieval. change to NAACL2022
3. LaPraDoR: Unsupervised pretrained dense retriever for zero-shot text retrieval. （ACL2022）
4. A thorough examination on zero-shot dense retrieval（2022）
5. Low-resource dense retrieval for opendomain question answering: A comprehensive survey（2022）
6. Challenges in generalization in open domain question answering（NAACL2022）