搜广推&NLP00-NLP/IR中顶会文章整理(每周更新一次)

paper repository

字体颜色设置: 我是蓝色 Markdown进阶（更改字体、颜色、大小，设置文字背景色，调整图片大小设置居中)
DBLP Conference:
SIGIR: DBLP WWW: DBLP WSDM: DBLP CIKM: DBLP KDD: DBLP

ACL: DBLP EMNLP: DBLP

ICLR: DBLP AAAI: DBLP IJCAI: DBLP NIPS: DBLP

信息检索/数据挖掘/数据库: CCF推荐列表

信息检索/数据挖掘/自然语言处理/人工智能 近几年流程表

说明: 🔨：投稿阶段-->💻:审稿中 -->★:列表公开-->🌙:已经整理

	2019	2020	2021	2022	2023
SIGIR	★	🌙	💻 noti:4.14
CIKM	★	★	🔨 ddl:3.24 crd:8.23
WWW	★	★	🌙
WSDM	★	★	🌙
KDD	★	★	💻 noti:5.17
ACL	★	★	💻
EMNLP	★	★	🔨
ICLR	★	★	★
AAAI	★	★	★
IJCAI	★	★
NIPS	★	★	★
TKDE
TOIS
AIRS
ECIR

---

🐴:正在看 📱:笔记 🏠:重点 ☁️:看过了,啥玩意

Pretrained Langeuage Model

---

Github 资源

1. huggingface/transformers: https://github.com/huggingface/transformers
2. Transformers API: https://huggingface.co/transformers/
3. tomohideshibata/BERT-related-papers:https://github.com/tomohideshibata/BERT-related-papers
4. thu/GNNPapers:https://github.com/thunlp/GNNPapers
5. Jiakui/awesome-bert:https://github.com/Jiakui/awesome-bert
6. xieyuqiang/GNN4NLP-Papers: https://github.com/IndexFziQ/GNN4NLP-Papers
7. THU/OpenMatch: https://github.com/thunlp/OpenMatch
8. THU/PLMPapers: https://github.com/thunlp/PLMpapers

---

综述类

1. [IR 排序模型综述] A Deep Look into Neural Ranking Models for Information Retrieval [2019, guojiafeng] arXiv

2. [NLP NERZ综述] A Survey on Deep Learning for Named Entity Recognition [2020-03] arXiv

3. [BERT 进展] A Primer in BERTology: What we know about how BERT works

4. Matching Algorithms: Fundamentals, Applications and Challenges [2021-03]arXiv

5. Information retrieval: a view from the Chinese IR community [chengxueqi, 2021]PDF

6. Retrieving and Reading : A Comprehensive Survey on Open-domain Question Answering arXiv

7. Pretrained Transformers for Text Ranking: BERT and Beyond arXiv

---

2021

未标注会议

1. Dynamic Model for Query-Document Expansion towards Improving Retrieval Relevance PDF ☁️20210414

2. A Neural Passage Model for Ad-hoc Document Retrieval PDF

3. An In-depth Analysis of Passage-Level Label Transfer for Contextual Document Ranking arXiv

4. Mitigating the Position Bias of Transformer Models in Passage Re-Ranking arXiv [ecir2021]

5. Neural document expansion for ad-hoc information retrieval arXiv [亚马逊] ☁️20200414

6. PARADE: Passage Representation Aggregation for Document Reranking arXiv

7. Neural Methods for Effective, Efficient, and Exposure-Aware Information Retrieval [PhD thesis]arXiv

8. MIMICS: A Large-Scale Data Collection for Search Clarification arXiv

9. Unbiased Learning to Rank via Propensity Ratio Scoring arXiv

10. Conformer-Kernel with Query Term Independence for Document Retrieval arXiv

11. Exploring Classic and Neural Lexical Translation Models for Information Retrieval: Interpretability, Effectiveness, and Efficiency Benefits arXiv

12. Longformer for MS MARCO Document Re-ranking Task arXiv

13. ORCAS: 18 Million Clicked Query-Document Pairs for Analyzing Search arXiv

14. Composite Re-Ranking for Efficient Document Search with BERT arXiv

15. Graph-based Hierarchical Relevance Matching Signals for Ad-hoc Retrieval arXiv

16. Match-Ignition: Plugging PageRank into Transformer for Long-form Text Matching [chengxueqi] arXiv

17. ERNIE-DOC: The Retrospective Long-Document Modeling Transformer arXiv

18. The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models arXiv

19. A Systematic Evaluation of Transfer Learning and Pseudo-labeling with BERT-based Ranking Models arXiv

20. ABNIRML: Analyzing the Behavior of Neural IR Models arXiv

21. Assessing the Benefits of Model Ensembles in Neural Re-Ranking for Passage Retrieval [ECIR short paper] arXiv

22. Distilling Dense Representations for Ranking using Tightly-Coupled Teachers [Jimmy Lin] arXiv

23. Redefining Absent Keyphrases and their Effect on Retrieval Effectiveness arXiv [naacl2021]

24. A Systematic Evaluation of Transfer Learning and Pseudo-labeling with BERT-based Ranking Models arXiv

25. Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation arXiv

26. Investigating the case of weak baselines in Ad-hoc Retrieval and Question Answering arXiv

27. An Attention-based Deep Relevance Model for Few-shot Document Filtering

28. Topic-enhanced knowledge-aware retrieval model for diverse relevance estimation pdf

29. A Pseudo-relevance feedback framework combining relevance matching and semantic matching for information retrieval PDF

30. RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering arXiv

31. CoRT: Complementary Rankings from Transformers arXiv

32. On the Calibration and Uncertainty of Neural Learning to Rank Models arXiv

33. Keyword-Attentive Deep Semantic Matching arXiv

34. ABNIRML: Analyzing the Behavior of Neural IR Models [AI2] arXiv

35. Evaluation of BERT and ALBERT Sentence Embedding Performance on Downstream NLP Tasks arXiv

36. Less is More: Pre-training a Strong Siamese Encoder Using a Weak Decoder [MS] arXiv

37. Learning To Retrieve: How to Train a Dense Retrieval Model Effectively and Efficiently

38. OpenMatch: An Open-Source Package for Information Retrieval arXiv

39. An end-to-end pseudo relevance feedback framework for neural document retrieval [2019]

SIGIR2021 审稿中，4.14 出结果 官网

• 长文:151/720, 21%, 短文: 145/526, 27%

• 1.Optimizing Dense Retrieval Model Training with Hard Negatives [MA SHAO PING]

• 2.Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling

• 3.Dual-View Distilled BERT for Sentence Embedding arXiv

• 4.AdsGNN: Behavior-Graph Augmented Relevance Modeling in Sponsored Search arXiv

• 5.Wizard of Search Engine: Access to Information Through Conversations with Search Engines

• 6.Self-Supervised Contrastive Learning for Code Retrieval and Summarization via Semantic-Preserving Transformations

• 7.Not All Relevance Scores are Equal: Efficient Uncertainty and Calibration Modeling for Deep Retrieval Models [****]

• 8.B-PROP: Bootstrapped Pre-training with Representative Words Prediction for Ad-hoc Retrieval [****]

• 9.Learning to Rank for Mathematical Formula Retrieval

• 10.Investigating User Behavior in Legal Case Retrieval

• 11.Few-Shot Conversational Dense Retrieval

• 12.Heterogeneous Attention Network for Effective and Efficient Cross-modal Retrieval

• 13.PAN: Prototype-based Adaptive Network for Robust Cross-modal Retrieval

• 14.Adapting Interactional Observation Embedding for Counterfactual Learning to Rank

• 15.MS MARCO: Benchmarking Ranking Models in the Large-Data Regime

• 16.KeyBLD: Selecting Key Blocks with Local Pre-ranking for Long Document Information Retrieval

• 17.Decoupling Representation and Regressor for Long-Tailed Information Cascade Prediction

• 18.On the Orthogonality of Bias and Effectiveness in Ad hoc Retrieval

• 19.Entity Retrieval Using Fine-Grained Entity Aspects

• 20.Contextualized Offline Relevance Weighting for Efficient and Effective Neural Retrieval

• 21.Conversational vs Traditional: Comparing Search Behavior and Outcome in Legal Case Retrieval

• 22.Learning Robust Dense Retrieval Models from Incomplete Relevance Labels

• 23.Joint Learning of Deep Retrieval Model and Product Quantization based Embedding Index

• 24.APRF-Net: Attentive Pseudo-Relevance Feedback Network for Query Categorization

• 25.Podcast Metadata and Content: Episode Relevance and Attractiveness in Ad Hoc Search

• 26.Revisiting the Tag Relevance Prediction Problem

• 27.Computationally Efficient Optimization of Plackett-Luce Ranking Models for Relevance and Fairness

• 28.Learning a Fine-Grained Review-based Transformer Model for Personalized Product Search

• 29.Do Affective Cues Validate Behavioural Metrics for Search?

• 30.Modeling Intent Graph for Search Result Diversification [wenjirong]

• 31.Group based Personalized Search by Integrating Search Behaviour and Friend Network [wenjirogn]

• 32.When Fair Ranking Meets Uncertain Inference arXiv [***]

• 33.Intra-Document Cascading: Learning to Select Passages for Neural Document Ranking

• 34.IDRQA: Iterative Document Reranking for Open-domain Multi-hop Question Answering

• 35.Improving Bi-encoder Document Ranking Models with Two Rankers and Multi-teacher Distillation

• 36.SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking

• 37.Significant Improvements over the State of the Art? A Case Study of the MS MARCO Document Ranking Leaderboard

• 38.Towards a Better Tradeoff between Effectiveness and Efficiency in Pre-Ranking: A Learnable Feature Selection based Approach

• 39.Improving Transformer-Kernel Ranking Model Using Conformer and Query Term Independence

• 40.A Systematic Evaluation of Transfer Learning and Pseudo-labeling with BERT-based Ranking Models

• 41.Societal Biases in Retrieved Contents: Measurement Framework and Adversarial Mitigation for BERT Rankers

• 42.Learning Passage Impacts for Inverted Indexes(https://arxiv.org/abs/2104.12016) [下载]

• 43.Text-to-Text Multi-view Learning for Passage Re-ranking

• 44.[AutoDebias: Learning to Debias for Recommendation] [2021-07-02]

• 45. [Set2setRank: Collaborative Set to Set Ranking for Implicit Feedback based Recommendation]
• 46. [Long-Tail Hashing]

• 47.[Looking at CTR Prediction Again: Is Attention All You Need?]

• 48. [Allowing for The Grounded Use of Temporal Difference Learning in Large Ranking Models via Sub State Updates ]

• 49.[How Do Biased Search Result Rankings Affect User Attitudes on Debated Topics?]

• 50 [Partner Matters! An Empirical Study on Fusing Personas for Personalized Response Selection in Retrieval-Based Chatbots]

• 51. [ScaleFreeCTR: MixCache-based Distributed Training System for CTR Models with Huge Embedding Table]

• 52 [Enhanced Doubly Robust Learning for Debiasing Post-Click Conversion Rate Estimation]

• 53 [Improving Video Retrieval by Adaptive Margin]

• 54 [Intra-Document Cascading: Learning to Select Passages for Neural Document Ranking]

• 55 [Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling]

• 56 [A Graph-Enhanced Click Model for Web Search]

• 57 [Adapting Interactional Observation Embedding for Counterfactual Learning to Rank]

• 58 [Tracing Knowledge State with Individual Cognition and Acquisition Estimation]

• 59 [A General Method For Automatic Discovery of Powerful Interactions In Click-Through Rate Prediction]

• 60 [Computationally Efficient Optimization of Plackett-Luce Ranking Models for Relevance and Fairness]

• 61 [Learning Graph Meta Embeddings for Cold-Start Ads in Click-Through Rate Prediction]

• 62 [Societal Biases in Retrieved Contents: Measurement Framework and Adversarial Mitigation of BERT Rankers]

• 63 [Wizard of Search Engine: Access to Information Through Conversations with Search Engines]

• 64 Clicks can be Cheating: Counterfactual Recommendation for Mitigating Clickbait Issue

• 65 AdsGNN: Behavior-Graph Augmented Relevance Modeling in Sponsored Search

• 66 Few-Shot Conversational Dense Retrieval

• 67 Optimizing Dense Retrieval Model Training with Hard Negatives

• 68 IDRQA: Iterative Document Reranking for Open-domain Multi-hop Question Answering

• 69 Answer Complex Questions: Path Ranker Is All You Need

• 70 On the Orthogonality of Bias and Effectiveness in Ad hoc Retrieval

• 71 Podcast Metadata and Content: Episode Relevance and Attractiveness in Ad Hoc Search

• 72 Contextualized Offline Relevance Weighting for Efficient and Effective Neural Retrieval

• 73 Dual-View Distilled BERT for Sentence Embedding

• 74 GemNN: Gating-enhanced Multi-task Neural Networks with Feature Interaction Learning for CTR Prediction

• 75 Deep Position-wise Interaction Network For CTR Prediction

• 76 Deep User Match Network for Click-Through Rate Prediction

• 77 Revisiting the Tag Relevance Prediction Problem

• 78 Dual Unbiased Recommender Learning for Implicit Feedback

• 79 Explicit Semantic Cross Feature Learning via Pre-trained Graph Neural Networks for CTR Prediction

• 80 KeyBLD: Selecting Key Blocks with Local Pre-ranking for Long Document Information Retrieval

• 81 Significant Improvements over the State of the Art? A Case Study of the MS MARCO Document Ranking Leaderboard

• 82 Cross-Batch Negative Sampling for Training Two-Tower Recommenders

• 83 RLNF: Reinforcement Learning based Noise Filtering for Click-Through Rate Prediction

• 84 A Test Collection for Ad-hoc Dataset Retrieval

• 85 WWW3E8: 259,000 Relevance Labels for Studying the Effect of Document Presentation Order for Relevance Assessors

CIKM2021 投稿中,8.23 CRD 官网

WWW2021

1. Robust Generalization and Safe Query-Specialization in Counterfactual Learning to Rank AMiner

2. A Linguistic Study on Relevance Modeling in Information Retrieval [chengxuqi & guojiafeng]AMiner

3. Maximizing Marginal Fairness for Dynamic Learning to Rank [qingao ai] AMiner

4. An Alternative Cross Entropy Loss for Learning-to-Rank AMiner

5. Using Prior Knowledge to Guide BERT's Attention in Semantic Textual Matching Tasks AMiner

6. Graph-based Hierarchical Relevance Matching Signals for Ad-hoc Retrieval AMiner

7. MIRA: Leveraging Multi-Intention Co-click Information in Web-scale Document Retrieval using Deep Neural Networks AMiner

8. Event-Driven Query Expansion 。。。

9. Density-Ratio Based Personalised Ranking from Implicit Feedback AMiner

10. Relevance-guided Supervision for OpenQA with ColBERT arXiv

11. An Adversarial Imitation Click Model for Information Retrieval arXiv

WSDM2021:

1. PROP: Pre-training with Representative Words Prediction for Ad-hoc Retrieval [chengxueqi & guojiafeng] arXiv

2. Bias-Variance Decomposition for Ranking PDF

3. Unifying Online and Counterfactual Learning to Rank: A Novel Counterfactual Estimator that Effectively Utilizes Online Interventions

4. Pretrained Transformers for Text Ranking: BERT and Beyond PDF

5. Non-Clicks Mean Irrelevant? Propensity Ratio Scoring As a Correction PDF

6. Beyond Relevance: Trustworthy Answer Selection via Consensus Verification PDF

7. Beyond Probability Ranking Principle: Modeling the Dependencies among Documents PDF

8. QueryBlazer: Efficient Query Autocompletion Framework PDF

KDD2021: 5.17 录用结果 官网

ACL2021:

EMNLP2021:

AAAI2021: 1692篇

笔记整理:

1. AAAI2021 | NLP所有方向论文列表（情感分析、句法、NER、对话/问答、关系抽取、KD等）
2. AAAI2021-图神经网络预览

论文整理:

1. Learning to Truncate Ranked Lists for Information Retrieval [chengxueqi & guojiafeng]AMiner

2. A Graph-based Relevance Matching Model for Ad-hoc Retrieval AMiner

3. LET: Linguistic Knowledge Enhanced Graph Transformer for Chinese Short Text Matching AMiner

4. Making the Relation Matters: Relation of Relation Learning Network for Sentence Semantic Matching AMiner

5. Fake it Till You Make it: Self-Supervised Semantic Shifts for Monolingual Word Embedding Tasks AMiner

IJCAI2021:

ICLR2021:

1. Are Neural Rankers still Outperformed by Gradient Boosted Decision Trees? AMiner

2. Individually Fair Rankings AMiner

3. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval AMiner

NIPS2021:

---

2020

SIGIR2020:

SIGIR2020: 官网 dblp aminer
SIGIR会议之文本表征、检索重排序、阅读理解论文整理
一、文本的表征

1. Convolutional Embedding for Edit Distance arXiv
2. Match^2: A Matching over Matching Model for Similar Question Identification arXiv AMiner
3. Hier-SPCNet: A Legal Statute Hierarchy-based Heterogeneous Network for Computing Legal Document Similarity arXiv
4. Attending to Inter-sentential Features in Neural Text Classification pdf
5. Towards Differentially Private Text Representations arXiv
6. Expansion via Prediction of Importance with Contextualization arXiv
7. DC-BERT: Decoupling Question and Document for Efficient Contextual Encoding [jiang daxin] arXiv [AMiner](DC-BERT: Decoupling Question and Document for Efficient Contextual Encoding)
8. Improving Matching Models with Hierarchical Contextualized Representations for Multi-turn Response Selection arXiv
9. Symmetric Regularization based BERT for Pair-wise Semantic Reasoning arXiv

二、检索及重排序

1. Table Search Using a Deep Contextualized Language Model arXiv
2. ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT arXiv
3. Finding the Best of Both Worlds: Faster and More Robust Top-k Document Retrieval PDF
4. Efficient Document Re-Ranking for Transformers by Precomputing Term Representations arXiv
5. Training Curricula for Open Domain Answer Re-Ranking arXiv
6. SetRank: Learning a Permutation-Invariant Ranking Model for Information Retrieval arXiv
7. MarkedBERT: Integrating Traditional IR cues in pre-trained language models for passage retrieval pdf
8. Context-Aware Term Weighting For First-Stage Passage Retrieval PDF
9. Learning Term Discrimination arXiv
10. Improving Document-Level Text Retrieval using Local Attention in the Transformer-Kernel Pooling Model arXiv
11. Query-level Early Exit for Additive Learning-to-Rank Ensembles arXiv
12. Efficiency Implications of Term Re-Weighting for Passage Retrieval PDF
13. Contextual Re-Ranking with Behavior Aware Transformers [MS]arXiv AMiner
14. An analysis of BERT in document ranking [mashaoping] arXiv* AMiner

三、QA及阅读理解

1. Open-Retrieval Conversational Question Answering arXiv AMiner
2. Reranking for Efficient Transformer-based Answer Selection arXiv

四、其他

1. 2. Automatic Generation of Topic Labels arXiv
2. CrossBERT with Triplet Neural Architecture for Entity Property Ranking arXiv
3. Few-Shot Generative Conversational Query Rewriting arXiv

五. 补充

1. Investigating reading behavior in Fine-grained Relevance Judgment [liuyiqun & mashaoping]AMiner

2. Query-level Early Exit for Additive Learning-to-Rank Ensembles AMiner

3. Sampling Bias Due to Near-Duplicates in Learning to Rank AMiner

4. Policy-Aware Unbiased Learning to Rank for Top-k Rankings AMiner

5. Accelerated Convergence for Counterfactual Learning to Rank AMiner

6. Cascade Model-based Propensity Estimation for Counterfactual Learning to Rank AMiner

7. Re-ranking Answer Selection with Similarity Aggregation AMiner

8. Multi-grouping Robust Fair Ranking AMiner

9. Feature Transformation for Neural Ranking Models AMiner

10. SetRank: Learning a Permutation-Invariant Ranking Model for Information Retrieval [wenjirong & chengxueqi ] AMiner

11. Efficient Document Re-Ranking for Transformers by Precomputing Term Representations AMiner

12. Training Curricula for Open Domain Answer Re-Ranking AMiner

13. A Deep Recurrent Survival Model for Unbiased Ranking [gaikun] AMiner

14. Studying Ranking-Incentivized Web Dynamics AMiner

15. Choppy: Cut Transformer For Ranked List Truncation AMiner

16. Unsupervised Semantic Hashing with Pairwise Reconstruction AMiner

17. Improving Contextual Language Models for Response Retrieval in Multi-Turn Conversation AMiner

18. Retrieving Potential Causes from a Query Event AMiner

19. A Study of Neural Matching Models for Cross-lingual IR AMiner

20. A Quantum Interference Inspired Neural Matching Model for Ad-hoc Retrieval AMiner

21. Improving Matching Models with Hierarchical Contextualized Representations for Multi-turn Response Selection AMiner

22. Soft Kernel-based Ranking on a Statistical Manifold AMiner

23. Analyzing and Learning from User Interactions for Search Clarification AMiner

24. Knowledge Enhanced Personalized Search [renjirong] AMiner

25. Topic Propagation in Conversational Search AMiner

26. Search Result Explanations Improve Efficiency and Trust AMiner

27. Encoding History with Context-aware Representation Learning for Personalized Search AMiner

28. Do Neural Ranking Models Intensify Gender Bias? AMiner

29. Query Resolution for Conversational Search with Limited Supervision AMiner

30. Local Self-Attention over Long Text for Efficient Document Retrieval arXiv

31. End-to-End Contextualized Document Indexing and Retrieval with Neural Networks PDF

32. Listwise Learning to Rank by Exploring Unique Ratings arXiv

CIKM2020:

1. Fine-Grained Relevance Annotations for Multi-Task Document Ranking and Question Answering arXiv

2. Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Long-Form Document Matching arXiv

3. Distant Supervision in BERT-based Adhoc Document Retrieval PDF

4. Learning Better Representations for Neural Information Retrieval with Graph Information PDF

WWW2020:

1. Selective Weak Supervision for Neural Information Retrieval arXiv

2. Context-Aware Document Term Weighting for Ad-Hoc Search PDF

3. Leveraging Passage-level Cumulative Gain for Document Ranking PDF

4. IART: Intent-aware Response Ranking with Transformers in Information-seeking Conversation Systems
   arXiv

5. HDCT:Context-Aware Document Term Weighting for Ad-Hoc Search PDF

WADM2020*

KDD2020:

1.Hierarchical Topic Mining via Joint Spherical Tree and Text Embedding AMiner

2.Mining Implicit Relevance Feedback from User Behavior for Web Question Answering AMiner

3. FreeDOM: A Transferable Neural Architecture for Structured Information Extraction on Web Documents AMiner

4. MinSearch: An Efficient Algorithm for Similarity Search under Edit Distance AMiner

5. Embedding-based Retrieval in Facebook Search AMiner

6. Managing Diversity in Airbnb Search AMiner

7. Improving Deep Learning For Airbnb Search AMiner

ACL2020:

1. QUASE: Question-Answer Driven Sentence Encoding [ai2]arXiv

2. tBERT: Topic Models and BERT Joining Forces for Semantic Similarity Detection PDF

3. Rationalizing Text Matching: Learning Sparse Alignments via Optimal Transport AMiner

4. Extractive Summarization as Text Matching AMiner

5. Neural Graph Matching Networks for Chinese Short Text Matching AMiner

EMNLP2020:

1. BERT-QE: Contextualized Query Expansion for Document Re-ranking [sunle]arXiv

2. Beyond [CLS] through Ranking by Generation AMiner

3. Modularized Transfomer based Ranking Framework AMiner

4. Wasserstein Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains [wenjirong] AMiner

5. A Bilingual Generative Transformer for Semantic Sentence Embedding AMiner

6. MultiCQA: Zero Shot Transfer of Self Supervised Text Matching Models on a Massive Scale AMiner

7. SLM: Learning a Discourse Language Representation with Sentence Unshuffling AMiner

8. Better Highlighting: Creating Sub Sentence Summary Highlights

9. KERMIT: Complementing Transformer Architectures with Encoders of Explicit Syntactic Interpretations AMiner

10. With More Contexts Comes Better Performance: Contextualized Sense Embeddings for All Round Word Sense Disambiguation AMiner

11. Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space [zhouming] AMiner

12. Cross Thought for Sentence Encoder Pre training AMiner

13. Long Document Ranking with Query-Directed Sparse Transformer arXiv

14. Ad-hoc Document Retrieval using Weak-Supervision with BERT and GPT2 AMiner

15. DiPair: Fast and Accurate Distillation for Trillion-Scale Text Matching and Pair Modeling arXiv

AAAI2020:

IJCAI2020:

ICLR2020:

1. Pre-training Tasks for Embedding-based Large-scale Retrieval arXiv AMiner

2. Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring AMiner

3. Encoding word order in complex embeddings AMiner

4. Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models AMiner

NIPS2020:

---

2019

SIGIR2019:

CIKM2019:

1. IMN: Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots arXiv

WWW2019:

KDD2019:

1. Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Search AMiner

2. MediaRank: Computational Ranking of Online News Sources AMiner

3. MOBIUS: Towards the Next Generation of Query-Ad Matching in Baidu's Sponsored Search [baidu] AMiner

4. A Memory-Efficient Sketch Method for Estimating High Similarities in Streaming Sets AMiner

ACL2019:

EMNLP2019:

1. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks arXiv

2. Bridging the Gap Between Relevance Matching and Semantic Matching for Short Text Similarity Modeling

AAAI2019:

1. DRCN: Semantic Sentence Matching with Densely-connected Recurrent and Co-attentive Information arXiv

IJCAI2019:

ICLR2019:

NIPS2019:

other

1. Context-Aware Sentence/Passage Term Importance Estimation For First Stage Retrieval arXiv

2. Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network [BaiDu ACL2018]

---

LTR

• 1.Document Ranking with a Pretrained Sequence-to-Sequence Model
• 2.[2020 NeurIPS] [51] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• 3.Match-Ignition: Plugging PageRank into Transformer for Long-form Text Matching
• 4.Cross-Thought for Sentence Encoder Pre-training
• 5.On the Sentence Embeddings from Pre-trained Language Models
• 6.PROP: Pre-training with Representative Words Prediction for Ad-hoc Retrieval
• 7.[2020 ACL-Enhancing Pre-trained Chinese Character Representation with Word-aligned Attention
• 8.Integrating fine- and coarse-grained information for natural language understanding
• 9.2020 SIGIR】MarkedBERT: Integrating Traditional IR Cues in Pre-trained Language Models for Passage Retrieval
• 10.【2019 AAAI】Semantic Sentence Matching with Densely-connected Recurrent and Co-attentive Information
• 11.Towards Personalized and Semantic Retrieval: An End-to-End Solution for E-commerce Search via Embedding Learning
• 12.[2020 KDD] Embedding-based Retrieval in Facebook Search.
• 13.[ 2020 SIGIR ] ColBERT Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
• 14.[ 2020 ICLR ] Reformer: The efficient Transformer
• 15.[SIGIR 2020] Efficient Document Re-Ranking for Transformers by Precomputing Term Representations
• 16.Adaptive Multi-Attention Network Incorporating Answer Information for Duplicate Question Detection
• 17.[2019 AAAI] [66] Semantic Sentence Matching with Densely-Connected Recurrent and Co-Attentive Information

日常补充

2021-04-23

• 1.Semantic Models for the First-stage Retrieval: A Comprehensive Review
• 2.A Replication Study of Dense Passage Retriever
• 4.Efficient Retrieval Optimized Multi-task Learning
• 5.Anytime Ranking on Document-Ordered Indexes
• 6.Co-BERT: A Context-Aware BERT Retrieval Model Incorporating Local and Query-specific Context [孙乐]
• 7.BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
• 8.ASBERT: Siamese and Triplet network embedding for open question answering
• 9.Contextualized Query Embeddings for Conversational Search
• 10.[
• 11.SciCo: Hierarchical Cross-Document Coreference for Scientific Concepts
• 12.COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List [NAACL2021]
• 13. RoFormer: Enhanced Transformer with Rotary Position Embedding arXiv
• 14.Simple and Efficient ways to Improve REALM arXiv
• 15.SimCSE: Simple Contrastive Learning of Sentence Embeddings arXiv
• 16.Joint Passage Ranking for Diverse Multi-Answer Retrieval arXiv
• 17.Knowledge Neurons in Pretrained Transformers arXiv
• 18.Demystifying the Better Performance of Position Encoding Variants for Transformer arXiv
• 19.Chinese Sentences Similarity via Cross-Attention Based Siamese Network arXiv
• 20.Reference-based Weak Supervision for Answer Sentence Selection using Web Data arXiv
• 21.Context-Aware Interaction Network for Question Matching arXiv
• 22.A Graph-guided Multi-round Retrieval Method for Conversational Open-domain Question Answering arXiv
• 23.Ranking Structured Objects with Graph Neural Networks arXiv
• 24.Fast, Effective and Self-Supervised: Transforming Masked LanguageModels into Universal Lexical and Sentence Encoders arXiv
• 25.Towards Robust Neural Retrieval Models with Synthetic Pre-Training arXiv
• 26.Lattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language Models arXiv [NAACL2021]
• 27.Designing a Minimal Retrieve-and-Read System for Open-Domain Question Answering arXiv
• 28.Sentence Embeddings by Ensemble Distillation arXiv
• 29.Significant Improvements over the State of the Art? A Case Study of the MS MARCO Document Ranking Leaderboard arXiv
• 30.Latte-Mix: Measuring Sentence Semantic Similarity with Latent Categorical Mixtures []

2021-04-27
1.Extract then Distill: Efficient and Effective Task-Agnostic BERT Distillation arXiv [THU]

2021-05-04
1.Extract then Distill: Efficient and Effective Task-Agnostic BERT Distillation
2. SmoothI: Smooth Rank Indicators for Differentiable IR Metrics
3.Transformers: "The End of History" for NLP?

2021-05-05
1.Pretrained Transformers for Text Ranking:
BERT and Beyond
2. Comparing Score Aggregation Approaches for Document Retrieval with Pretrained Transformers [ECIR2021]
3.A White Box Analysis of ColBERT [ECIR2021]
4.TREC Deep Learning Track: Reusable Test Collections in the Large Data Regime
5.

博客收藏

• 深度学习中的知识蒸馏技术-上 [MS]
• 深度学习中的知识蒸馏技术(下)-知识蒸馏与推荐系统 [MS]
• 语义索引（向量检索）的几类经典方法