前言

第58届国际计算语言学协会年会（ACL，The Association for Computational Linguistics）将于2020年7月6号-8号线上举行。官网公布了ACL2020的论文收录名单，共计收录778篇论文，本次ACL大会共提交了3429篇论文，长文录取率为25%。作为自然语言处理（NLP）领域的顶会，其中有一些涉及NLP技术的推荐系统论文也会投稿于此。

第37届机器学习国际会议（ICML，International Conference on Machine Learning）将于2020年7月12日至18日线上举行。官网公布了ICML2020的论文收录名单，共计收录1088篇论文，本次ICML大会共提交了4990篇论文，录取率为21.8%。

推荐相关论文列表

本次ACL2020大会共整理出5篇关于推荐系统的论文，其中涉及到2篇对话推荐系统和3篇新闻推荐系统。值得注意的是，3篇新闻推荐系统论文均来自于MSRA谢幸老师团队，太强了(●'◡'●)。不难发现，由于ACL为自然语言处理相关的会议，所以推荐系统的比重较小，另外，接收的推荐系统论文中都涉及NLP相关的技术。

另外，本篇文章还整理出了ICML2020中关于推荐系统的论文4篇。其中涉及GCN、非负矩阵分解等技术。

由于在研究推荐系统的时候，也会用到图神经网络以及知识图谱相关的知识，因此后两部分也整理了相关的论文。

推荐系统-ACL2020

• Dynamic Online Conversation Recommendation

https://www.aclweb.org/anthology/2020.acl-main.305.pdf

https://github.com/zxshamson/dy-conv-rec

• Towards Conversational Recommendation over Multi-Type Dialogs

https://www.aclweb.org/anthology/2020.acl-main.98.pdf

https://github.com/PaddlePaddle/models/

• Fine-grained Interest Matching for Neural News Recommendation

https://www.aclweb.org/anthology/2020.acl-main.77.pdf

• Graph Neural News Recommendation with Unsupervised Preference Disentanglement

https://www.aclweb.org/anthology/2020.acl-main.392.pdf

• MIND: A Large-scale Dataset for News Recommendation

https://www.aclweb.org/anthology/2020.acl-main.331.pdf

https://github.com/zxshamson/dy-conv-rec

推荐系统-ICML2020

• Graph Convolutional Network for Recommendation with Low-pass Collaborative Filters

https://arxiv.org/abs/2006.15516.pdf

• Optimization and Analysis of the pAp@k Metric for Recommender Systems

• Optimizing Long-term Social Welfare in Recommender Systems: A Constrained Matching Approach

• Ordinal Non-negative Matrix Factorization for Recommendation

https://arxiv.org/pdf/2006.01034.pdf

网络表示学习&图神经网络相关

• Learning to Ask More: Semi-Autoregressive Sequential Question Generation under Dual-Graph Interaction.

• Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks.

• GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Media.

• Integrating Semantic and Structural Information with Graph Convolutional Network for Controversy Detection.

• Line Graph Enhanced AMR-to-Text Generation with Mix-Order Graph Attention Networks.

• Query Graph Generation for Answering Multi-hop Complex Questions from Knowledge Bases.

• A Graph Auto-encoder Model of Derivational Morphology.

• AMR Parsing via Graph-Sequence Iterative Inference.

• Semantic Graphs for Generating Deep Questions.

• A Novel Graph-based Multi-modal Fusion Encoder for Neural Machine Translation.

• Relational Graph Attention Network for Aspect-based Sentiment Analysis.

• Syntax-Aware Opinion Role Labeling with Dependency Graph Convolutional Networks.

• Entity-Aware Dependency-Based Deep Graph Attention Network for Comparative Preference Classification.

• Heterogeneous Graph Neural Networks for Extractive Document Summarization.

• Dependency Graph Enhanced Dual-transformer Structure for Aspect-based Sentiment Classification.

• Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension.

• Aligned Dual Channel Graph Convolutional Network for Visual Question Answering.

• Multimodal Neural Graph Memory Networks for Visual Question Answering.

• Fine-grained Fact Verification with Kernel Graph Attention Network

• Continuous Graph Neural Networks

知识图谱

• Query Graph Generation for Answering Multi-hop Complex Questions from Knowledge Bases.

• Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs.

• Can We Predict New Facts with Open Knowledge Graph Embeddings? A Benchmark for Open Link Prediction.

• The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents.

• Knowledge Graph Embedding Compression.

• Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph Embedding.

• Breaking Through the 80% Glass Ceiling: Raising the State of the Art in Word Sense Disambiguation by Incorporating Knowledge Graph Information.

• SEEK: Segmented Embedding of Knowledge Graphs.

• SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis.

• Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings.

• Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward.

• A Re-evaluation of Knowledge Graph Completion Methods.

• ReInceptionE: Relation-Aware Inception Network with Joint Local-Global Structural Information for Knowledge Graph Embedding.

• Connecting Embeddings for Knowledge Graph Entity Typing.

• Low-Dimensional Hyperbolic Knowledge Graph Embeddings.

「 更多干货，更多收获 」哔哩哔哩推荐策略分析与思考揭秘微信“看一看”如何精准挖掘你感兴趣的内容【回顾】推荐算法工程师技能树【免费下载】全网最全5G资料包（1300余份，持续更新）【白岩松大学演讲】：为什么读书？强烈建议静下心来认真看完
关注我们

一个「在看」，一段时光????