SIGIR2022论文筛选

写在前面

大家好，我是刘聪NLP。

SIGIR2022会议的论文列表前一段时间放出来了，由于个人时间关系，今天将论文列表过了一边，筛选了一些自己正在做或者感兴趣方向的相关论文，包括：检索排序、小样本、生成、摘要、文本表征、问答等。

由于部分论文还搜不到，所有等后面论文链接放出来后，会将其补上去。并且一些自己特别感兴趣的论文，已经标星”*“，希望对大家有所帮助。

一起学起来吧~~~

官方论文列表：https://sigir.org/sigir2022/program/accepted/

检索排序相关

[1] RankFlow: Joint Optimization of Multi-Stage Cascade Ranking Systems as Flows

[2] * Incorporating Explicit Knowledge in Pre-trained Language Models for Passage Re-ranking

[3] IR Evaluation and Learning in the Presence of Forbidden Documents

[4] Incorporating Retrieval Information into the Truncation of Ranking Lists in the Legal Domain

[5] * Webformer: Pre-training with Web Pages for Information Retrieval

[6] Automatic Expert Selection for Multi-Scenario and Multi-Task Search

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

[8] * H-ERNIE: A Hierarchical Multi-Granularity Pre-Trained Language Model for Chinese Search Engine

[9] Interpreting Patient Descriptions using Distantly Supervised Similar Case Retrieval

[10] Axiomatically Regularized Pre-training for Ad hoc Search

[11] Entity-aware Transformers for Entity Search

[12] * Pre-train a Discriminative Text Encoder for Dense Retrieval via Contrastive Span Prediction

[13] Faster Learned Sparse Retrieval with Guided Traversal

[14] * P^3 Ranker: Mitigating the Gaps between Pre-training and Ranking Fine-tuning with Prompt-based Learning and Pre-finetuning

[15] Curriculum Learning for Dense Retrieval Distillation

[16] Analysing the Robustness of Dual Encoders for Dense Retrieval Against Misspellings

[17] From Cluster Ranking to Document Ranking

[18] How does Feedback Signal Quality Impact Effectiveness of Pseudo Relevance Feedback for Passage Retrieval

[19] * Improving Contrastive Learning of Sentence Embeddings with Case-Augmented Positives and Retrieved Negatives

[20] GERE: Generative Evidence Retrieval for Fact Verification

[21] Learning to Rank Knowledge Sub-Graph Nodes for Entity Retrieval

[22] * BERT-based Dense Intra-ranking and Contextualized Late Interaction via Multi-task Learning for Long Document Retrieval

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

[24] * Long Document Re-ranking with Modular Re-ranker

[25] Unsupervised Dataset Generation for Information Retrieval

[26] On Optimizing Top-K Metrics for Neural Ranking Models

[27] Alignment Rationale for Query-Document

[28] To interpolate or not to interpolate: PRF, Dense Retrievers and BM25

[29] C3: Continued Pretraining with Contrastive Weak Supervision for Cross Language Ad-Hoc Retrieval

小样本

[1] Curriculum Contrastive Context Denoising for Few-shot Conversational Dense Retrieval

[2] Recognizing Medical Search Query Intent by Few-shot Learning

[3] * Zero-shot Query Contextualization for Conversational Search

[4] Relation-Guided Few-Shot Relational Triple Extraction

[5] Multi-labels Masked Language Modeling on Zero-shot Code-switched Sentiment Analysis

生成

[1] * Mutual Disentanglement Learning for Joint Fine-Grained Sentiment Classification and Controllable Text Generation

[2] Target-aware Abstractive Related Work Generation with Contrastive Learning

[3] Generating Clarifying Questions with Web Search Results

[4] Task-Oriented Dialogue System as Natural Language Generation

[5] Entity-Conditioned Question Generation for Robust Attention Distribution in Neural Information Retrieval

摘要

[1] ADPL: Adversarial Prompt-based Domain Adaptation for Dialogue Summarization with Knowledge Disentanglement

[2] * On Extractive Summarization for Profile-centric Neural Expert Search in Academia

[3] QSG Transformer: Transformer with Query-Attentive Semantic Graph for Query-Focused Summarization

[4] * MuchSUM: Multi-channel Graph Neural Network for Extractive Summarization

[5] Lightweight Meta-Learning for Low-Resource Abstractive Summarization

[6] Extractive Elementary Discourse Units for Improving Abstractive Summarization

[7] Summarizing Legal Regulatory Documents using Transformers

文本表征

[1] Structure and Semantics Preserving Document Representations

[2] Unsupervised Belief Representation Learning with Information-Theoretic Variational Graph Auto-Encoders

[3] CRET: Cross-Modal Retrieval Transformer for Efficient Text-Video Retrieval

[4] * BERT-ER: Query-Specific BERT Entity Representations for Entity Ranking

[5] Adaptable Text Matching via Meta-Weight Regulator

[6] Re-weighting Negative Samples for Model-Agnostic Matching

[7] Learned Token Pruning in Contextualized Late Interaction over BERT (ColBERT)

问答

[1] * PTAU: Prompt Tuning for Attributing Unanswerable Questions

[2] DGQAN: Dual Graph Question-Answer Attention Networks for Answer Selection

[3] Conversational Question Answering on Heterogeneous Sources

[4] QUASER: Question Answering with Scalable Extractive Rationalization

[5] Detecting Frozen Phrases in Open-Domain Question Answering

其他

[1] * Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning

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

[3] A Dual-Expert Framework for Event Argument Extraction

[4] Aspect Feature Distillation and Enhancement Network for Aspect-based Sentiment Analysis

[5] * IAOTP: An Interactive End-to-End Solution for Aspect-Opinion Term Pairs Extraction

[6] Relation Extraction as Open-book Examination: Retrieval-enhanced Prompt Tuning

[7] Training Entire-Space Models for Target-oriented Opinion Words Extraction

[8] A Robust Computerized Adaptive Testing Approach in Educational Question Retrieval

[9] Hierarchical Task-aware Multi-Head Attention Network

[10] Enhancing Event-Level Sentiment Analysis with Structured Arguments

[11] End-to-end Distantly Supervised Information Extraction with Retrieval Augmentation

多模态相关

[1] Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion

[2] Learn from Unlabeled Videos for Near-duplicate Video Retrieval

[3] Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation

[4] V2P: Vision-to-Prompt based Multi-Modal Product Summary Generation

[5] CenterCLIP: Token Clustering for Efficient Text-Video Retrieval

[6] Multimodal Entity Linking with Gated Hierarchical Fusion and Contrastive Training

[7] Bit-aware Semantic Transformer Hashing for Multi-modal Retrieval

[8] Multimodal Disentanglement Variational AutoEncoders for Zero-Shot Cross-Modal Retrieval

[9] Animating Images to transfer CLIP for Video-Text Retrieval

[10] Image-Text Retrieval via Contrastive Learning with Auxiliary Generative Features and Support-set Regularization

[11] Cross-Probe BERT for Fast Cross-Modal Search

资源

[1] A Dataset for Sentence Retrieval for Open-Ended Dialogues

[2] * ReMeDi: Resources for Multi-domain, Multi-service, Medical Dialogues

[3] * Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieva

整理不易，请多多点赞，关注，有问题的朋友也欢迎加我微信「logCong」、公众号「NLP工作站」、知乎「刘聪NLP」私聊，交个朋友吧，一起学习，一起进步。

我们的口号是“生命不止，学习不停”。