机器之心Pro|7 Papers & Radios | 南加大游戏AI玩转《毁灭战士》；少样本NLP元学习综述( 四 )

针对这些问题，来自复旦大学的研究者出了一种在用户表示端与物品表示端协同应用（物品）属性级注意力机制的深度推荐模型，简称 ACAM（Attribute-level Co-Attention Model）。

本文插图
模型架构图。

本文插图
在 Douban movie 和 NetEase song 两项推荐任务上的性能比较结果。
推荐：该模型采用多任务学习框架训练损失函数，并融入知识（嵌入）表示学习的目标，从而可以学到更优的物品和物品属性表示。
ArXiv Weekly Radiostation
机器之心联合由楚航、罗若天发起的ArXiv Weekly Radiostation ，在 7 Papers 的基础上，精选本周更多重要论文，包括NLP、CV、ML领域各10篇精选，并提供音频形式的论文摘要简介，详情如下：
本周 10 篇 NLP 精选论文是：
1. Analogical Reasoning for Visually Grounded Language Acquisition. (from Shih-Fu Chang)
2. A Novel Graph-based Multi-modal Fusion Encoder for Neural Machine Translation. (from Jiebo Luo)
3. Connecting Embeddings for Knowledge Graph Entity Typing. (from Kang Liu)
4. Effects of Language Relatedness for Cross-lingual Transfer Learning in Character-Based Language Models. (from Mikko Kurimo)
5. Better Early than Late: Fusing Topics with Word Embeddings for Neural Question Paraphrase Identification. (from Maria Liakata)
6. XD at SemEval-2020 Task 12: Ensemble Approach to Offensive Language Identification in Social Media Using Transformer Encoders. (from Jinho D. Choi)
7. Will Your Forthcoming Book be Successful? Predicting Book Success with CNN and Readability Scores. (from Aminul Islam)
8. To Be or Not To Be a Verbal Multiword Expression: A Quest for Discriminating Features. (from Carlos Ramisch)
9. IITK-RSA at SemEval-2020 Task 5: Detecting Counterfactuals. (from Shashank Gupta)
10. BAKSA at SemEval-2020 Task 9: Bolstering CNN with Self-Attention for Sentiment Analysis of Code Mixed Text. (from Ashutosh Modi)
本周 10 篇 CV 精选论文是：
1. CrossTransformers: spatially-aware few-shot transfer. (from Andrew Zisserman)
2. Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval. (from Andrew Zisserman)
3. BSL-1K: Scaling up co-articulated sign language recognition using mouthing cues. (from Andrew Zisserman)
4. Shape and Viewpoint without Keypoints. (from Jitendra Malik)
5. NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search. (from Kalyanmoy Deb, Wolfgang Banzhaf)
6. BorderDet: Border Feature for Dense Object Detection. (from Jian Sun)
7. WeightNet: Revisiting the Design Space of Weight Networks. (from Xiangyu Zhang, Jian Sun)
8. Funnel Activation for Visual Recognition. (from Xiangyu Zhang, Jian Sun)
9. Uncertainty-Aware Weakly Supervised Action Detection from Untrimmed Videos. (from Cordelia Schmid)
10. Vision-based Estimation of MDS-UPDRS Gait Scores for Assessing Parkinson's Disease Motor Severity. (from Li Fei-Fei)

机器之心Pro|7 Papers &amp; Radios | 南加大游戏AI玩转《毁灭战士》；少样本NLP元学习综述( 四 )

机器之心Pro|7 Papers & Radios | 南加大游戏AI玩转《毁灭战士》；少样本NLP元学习综述( 四 )