SIGIR会议之文本表征、检索重排序、阅读理解论文整理

余生颓废 提交于 2020-08-07 08:57:54

SIGIR会议已开,论文已全部放出,已做修改!


花一个上午的时间整理了一下SIGIR会议的检索相关论文,主要涉及:文本的表征、检索及重排序、阅读理解,其他等。不过有一些论文还搜不到(还没放出来),只能把题目挂上来,后续再做补充。

SIGIR会议论文地址如下:

SIGIR 2020sigir.org

一、文本的表征

(1) Convolutional Embedding for Edit Distance

Paper:https://arxiv.org/abs/2001.11692

(2) Match^2: A Matching over Matching Model for Similar Question Identification

Paper:https://arxiv.org/abs/2006.11719

(3) Hier-SPCNet: A Legal Statute Hierarchy-based Heterogeneous Network for Computing Legal Document Similarity

Paper: https://arxiv.org/abs/2007.03225

(4) Attending to Inter-sentential Features in Neural Text Classification

Paper:https://dl.acm.org/doi/pdf/10.1145/3397271.3401203

(5) Towards Differentially Private Text Representations

Paper: https://arxiv.org/abs/2006.14170

(6) Expansion via Prediction of Importance with Contextualization

Paper: https://arxiv.org/abs/2004.14245

(7) DC-BERT: Decoupling Question and Document for Efficient Contextual Encoding

Paper: https://arxiv.org/abs/2002.12591

(8) Improving Matching Models with Hierarchical Contextualized Representations for Multi-turn Response Selection

Paper: https://arxiv.org/abs/1808.07244

(9) Symmetric Regularization based BERT for Pair-wise Semantic Reasoning

Paper: https://arxiv.org/abs/1909.03405

二、检索及重排序

(1) Table Search Using a Deep Contextualized Language Model

Paper:https://arxiv.org/abs/2005.09207

(2) ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT

Paper:https://arxiv.org/abs/2004.12832

(3) Finding the Best of Both Worlds: Faster and More Robust Top-k Document Retrieval

Paper: https://dl.acm.org/doi/pdf/10.1145/3397271.3401076

(4) Efficient Document Re-Ranking for Transformers by Precomputing Term Representations

Paper:https://arxiv.org/abs/2004.14255

(5) Training Curricula for Open Domain Answer Re-Ranking

Paper:https://arxiv.org/abs/2004.14269

(6) SetRank: Learning a Permutation-Invariant Ranking Model for Information Retrieval

Paper:https://arxiv.org/abs/1912.05891

(7) MarkedBERT: Integrating Traditional IR cues in pre-trained language models for passage retrieval

Paper: https://dl.acm.org/doi/pdf/10.1145/3397271.3401194

(8) Context-Aware Term Weighting For First-Stage Passage Retrieval

Paper: https://dl.acm.org/doi/pdf/10.1145/3397271.3401204

(9) Learning Term Discrimination

Paper: https://arxiv.org/abs/2004.11759

(10) Improving Document-Level Text Retrieval using Local Attention in the Transformer-Kernel Pooling Model

Paper: https://dl.acm.org/doi/pdf/10.1145/3397271.3401224

(11) Query-level Early Exit for Additive Learning-to-Rank Ensembles

Paper: https://arxiv.org/abs/2004.14641

(12) Efficiency Implications of Term Re-Weighting for Passage Retrieval

Paper: https://www.cs.cmu.edu/~zhuyund/papers/SIGIR2020DeepCT-efficiency.pdf

(13) Contextual Re-Ranking with Behavior Aware Transformers

Paper: http://ciir-publications.cs.umass.edu/getpdf.php?id=1383

(14) An analysis of BERT in document ranking

Paper: https://dl.acm.org/doi/pdf/10.1145/3397271.3401325

三、QA及阅读理解

(1) Open-Retrieval Conversational Question Answering

Paper: https://arxiv.org/abs/2005.11364

(2) A Pairwise Probe for Understanding BERT Fine-Tuning on Machine Reading Comprehension

Paper: https://arxiv.org/abs/2006.01346

(3) Reranking for Efficient Transformer-based Answer Selection

Paper:https://www.amazon.science/publications/reranking-for-efficient-transformer-based-answer-selection

(4) Read, Attend, and Exclude: Multi-Choice Reading Comprehension by Mimicking Human Reasoning Process

Paper: https://dl.acm.org/doi/pdf/10.1145/3397271.3401326

四、其他

(1) A Unified Dual-view Model for Review Summarization and Sentiment Classification with Inconsistency Loss

Paper:https://arxiv.org/abs/2006.01592

(2) Automatic Generation of Topic Labels

Paper:https://arxiv.org/abs/2006.00127

(3) Summarizing and Exploring Tabular Data in Conversational Search

Paper: https://arxiv.org/abs/2005.11490

(4) Bridging Hierarchical and Sequential Context Modeling for Question-driven Extractive Answer Summarization

Paper: https://dl.acm.org/doi/pdf/10.1145/3397271.3401208

(5) Chinese document classification with bi-directional convolutional language model

Paper: https://dl.acm.org/doi/pdf/10.1145/3397271.3401248

(6) CrossBERT with Triplet Neural Architecture for Entity Property Ranking

Paper: http://eprints.gla.ac.uk/216366/

(7) Read what you need: Controllable Aspect-based Opinion Summarization of Tourist Reviews

Paper: https://arxiv.org/abs/2006.04660

(8) G2T: Generating Fluent Descriptions for Knowledge Graph

Paper: https://www.researchgate.net/publication/341160523_G2T_Generating_Fluent_Descriptions_for_Knowledge_Graph

(9) Few-Shot Generative Conversational Query Rewriting

Paper: https://arxiv.org/abs/2006.05009


整理下来实属不易,还请大家多多点赞~~~

接下来,有可能会进一步进行解读,将论文摘要部分添加进来,给更多小伙伴提供方便。


广告时间,哈哈哈哈。

推荐几篇文章:

刘聪NLP:开源啦!开源啦!UNILM中文模型开源啦!

刘聪NLP:智能扩充机器人的“标准问”库之Query生成

刘聪NLP:短文本相似度算法研究

易学教程内所有资源均来自网络或用户发布的内容,如有违反法律规定的内容欢迎反馈
该文章没有解决你所遇到的问题?点击提问,说说你的问题,让更多的人一起探讨吧!