{"type":"ScholarlyArticle","title":"Cold-Start Aware Deep Memory Network for Multi-Entity Aspect-Based Sentiment Analysis","authors":[{"name":"Kaisong Song","slug":"kaisong-song","given":"Kaisong","family":"Song","affiliation":"Alibaba Group , China"},{"name":"Wei Gao","slug":"wei-gao","given":"Wei","family":"Gao","affiliation":"Victoria University of Wellington , New Zealand"},{"name":"Lujun Zhao","slug":"lujun-zhao","given":"Lujun","family":"Zhao","affiliation":"Alibaba Group , China"},{"name":"Jun Lin","slug":"jun-lin","given":"Jun","family":"Lin","affiliation":"Alibaba Group , China"},{"name":"Changlong Sun","slug":"changlong-sun","given":"Changlong","family":"Sun","affiliation":"Alibaba Group , China"},{"name":"Xiaozhong Liu","slug":"xiaozhong-liu","given":"Xiaozhong","family":"Liu","affiliation":"Indiana University Bloomington , USA"}],"abstract":"Various types of target information have been considered in aspect-based sentiment analysis, such as entities and aspects. Existing research has realized the importance of targets and developed methods with the goal of precisely modeling their contexts via generating target-specific representations. However, all these methods ignore that these representations cannot be learned well due to the lack of sufficient human-annotated target-related reviews, which leads to the data sparsity challenge, a.k.a. cold-start problem here. In this paper, we focus on a more general multiple entity aspect-based sentiment analysis (ME-ABSA) task which aims at identifying the sentiment polarity of different aspects of multiple entities in their context. Faced with severe cold-start scenario, we develop a novel and extensible deep memory network framework with cold-start aware computational layers which use frequency-guided attention mechanism to accentuate on the most related targets, and then compose their representations into a complementary vector for enhancing the representations of cold-start entities and aspects. To verify the effectiveness of the framework, we instantiate it with a concrete context encoding method and then apply the model to the ME-ABSA task. Experimental results conducted on two public datasets demonstrate that the proposed approach outperforms state-of-the-art baselines on ME-ABSA task.","doi":"10.24963/ijcai.2019/722","url":"https://ijcai.org/proceedings/2019/722","pdf":"https://ijcai.org/proceedings/2019/0722.pdf","markdown":"https://ijcai.org/proceedings/2019/722.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/722","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Natural Language Processing","track":"Main track","number":722,"pages":{"first":5197,"last":5203},"keywords":["Natural Language Processing: Text Classification","Natural Language Processing: Sentiment Analysis and Text Mining"],"videos":[],"references":[{"position":1,"raw":"[Amplayo et al., 2018] Reinald Kim Amplayo, Jihyeok Kim, Sua Sung, and Seung-won Hwang. Cold-start aware user and product attention for sentiment classification. In Proceedings of the ACL, pages 2535-2544, 2018.","title":"Cold-start aware user and product attention for sentiment classification","authors":"Reinald Kim Amplayo, Jihyeok Kim, Sua Sung, Seung-Won Hwang","year":"2018","venue":"Proceedings of the ACL","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chen et al., 2017] Peng Chen, Zhongqian Sun, Lidong Bing, and Wei Yang. Recurrent attention network on mem- ory for aspect sentiment analysis. In Proceedings of the EMNLP, pages 452-461, 2017.","title":"Recurrent attention network on memory for aspect sentiment analysis","authors":"Peng Chen, Zhongqian Sun, Lidong Bing, Wei Yang","year":"2017","venue":"Proceedings of the EMNLP","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Feng et al., 2018] Shi Feng, Yaqi Wang, Kaisong Song, Daling Wang, and Ge Yu. Detecting multiple coexist- ing emotions in microblogs with convolutional neural net- works. Cognitive Computation, 10(1):136-155, 2018.","title":"Detecting multiple coexisting emotions in microblogs with convolutional neural networks","authors":"Yaqi Shi Feng, Kaisong Wang, Daling Song, Ge Wang, Yu","year":"2018","venue":"Cognitive Computation","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[He et al., 2018] Ruidan He, Wee Sun Lee, Hwee Tou Ng, and Daniel Dahlmeier. Exploiting document knowledge for aspect-level sentiment classification. In Proceedings of the ACL, pages 579-585, 2018.","title":"Exploiting document knowledge for aspect-level sentiment classification","authors":"He","year":"2018","venue":"Proceedings of the ACL","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Hochreiter and Schmidhuber, 1997] Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural Computation, 9(8):1735-1780, 1997.","title":"Long short-term memory","authors":"Schmidhuber Hochreiter, Sepp Hochreiter, Jürgen Schmidhuber","year":"1997","venue":"Neural Computation","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Jangid et al., 2018] Hitkul Jangid, Shivangi Singhal, Ra- jiv Ratn Shah, and Roger Zimmermann. Aspect-based fi- nancial sentiment analysis using deep learning. In Pro- ceedings of the WWW, pages 1961-1966, 2018.","title":"Aspect-based financial sentiment analysis using deep learning","authors":"Jangid","year":"2018","venue":"Proceedings of the WWW","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Kingma and Ba, 2014] Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. CoRR, abs/1412.6980, 2014.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Liu et al., 2018a] Bing Liu, Yi Chang, Shuai Wang, Sahisnu Mazumder, and Mianwei Zhou. Target-sensitive memory networks for aspect sentiment classification. In Proceed- ings of ACL, pages 957-967, 2018.","title":"Target-sensitive memory networks for aspect sentiment classification","authors":"Liu","year":"2018","venue":"Proceedings of ACL","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Liu et al., 2018b] Qiao Liu, Haibin Zhang, Yifu Zeng, Ziqi Huang, and Zufeng Wu. Content attention model for aspect based sentiment analysis. In Proceedings of the WWW, pages 1023-1032, 2018.","title":"Content attention model for aspect based sentiment analysis","authors":"Liu","year":"2018","venue":"Proceedings of the WWW","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Ma et al., 2017] Dehong Ma, Sujian Li, Xiaodong Zhang, and Houfeng Wang. Interactive attention networks for aspect-level sentiment classification. In Proceedings of the IJCAI, pages 4068-4074, 2017.","title":"Interactive attention networks for aspect-level sentiment classification","authors":"Dehong Ma, Sujian Li, Xiaodong Zhang, Houfeng Wang","year":"2017","venue":"Proceedings of the IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/568"},{"position":11,"raw":"[Ma et al., 2018] Yukun Ma, Haiyun Peng, and Erik Cam- bria. Targeted aspect-based sentiment analysis via embed- ding commonsense knowledge into an attentive LSTM. In Proceedings of the AAAI, 2018.","title":"Targeted aspect-based sentiment analysis via embedding commonsense knowledge into an attentive LSTM","authors":"Yukun Ma, Haiyun Peng, Erik Cambria","year":"2018","venue":"Proceedings of the AAAI","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Mohammad et al., 2016] Saif Mohammad, Svetlana Kir- itchenko, Parinaz Sobhani, Xiao-Dan Zhu, and Colin Cherry. Semeval-2016 task 6: Detecting stance in tweets. In Proceedings of the NAACL-HLT, pages 31-41, 2016.","title":"Semeval-2016 task 6: Detecting stance in tweets","authors":"Saif Mohammad, Svetlana Kiritchenko, Parinaz Sobhani, Xiao-Dan Zhu, Colin Cherry","year":"2016","venue":"Proceedings of the NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Pang and Lee, 2005] Bo Pang and Lillian Lee. Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales. In Proceedings of ACL, pages 115-124, 2005.","title":"Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales","authors":"Lee ; Pang, Bo Pang, Lillian Lee","year":"2005","venue":"Proceedings of ACL","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Pang et al., 2002] Bo Pang, Lillian Lee, and Shivakumar Vaithyanathan. Thumbs up? sentiment classification using machine learning techniques. In Proceedings of EMNLP, pages 79-86, 2002.","title":"Thumbs up? sentiment classification using machine learning techniques","authors":"Bo Pang, Lillian Lee, Shivakumar Vaithyanathan","year":"2002","venue":"Proceedings of EMNLP","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Pennington et al., 2014] Jeffrey Pennington, Richard Socher, and Christopher D. Manning. Glove: Global vectors for word representation. In Proceedings of the EMNLP, pages 1532-1543, 2014.","title":"Glove: Global vectors for word representation","authors":"Jeffrey Pennington, Richard Socher, Christopher D Manning","year":"2014","venue":"Proceedings of the EMNLP","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Pontiki et al., 2016] Maria Pontiki, Dimitrios Galanis, Haris Papageorgiou, Suresh Manandhar Ion Androut- sopoulos, Mohammad AL-Smadi, Mahmoud Al-Ayyoub, Yanyan Zhao, Bing Qin, Orphée De Clercq, Véronique Hoste, Marianna Apidianaki, Xavier Tannier, Na- talia Loukachevitch, Evgeny Kotelnikov, Nuria Bel, Salud María Jiménez-Zafra, and Güls ¸en Eryigit. Semeval- 2016 task 5: Aspect based sentiment analysis. In Proceedings of SemEval-2016, pages 19-30, 2016.","title":"Semeval-2016 task 5: Aspect based sentiment analysis","authors":"Maria Pontiki, Dimitrios Galanis, Haris Papageorgiou, Suresh Manandhar Ion, Androutsopoulos, Al-Smadi Mohammad, Mahmoud Al-Ayyoub, Yanyan Zhao, Bing Qin, Orphée De Clercq, Véronique Hoste, Marianna Apidianaki, Xavier Tannier, Natalia Loukachevitch, Evgeny Kotelnikov, Nuria Bel, Salud María Jiménez-Zafra, Güls ¸en Eryigit","year":"2016","venue":"Proceedings of SemEval-2016","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Song et al., 2015] Kaisong Song, Shi Feng, Wei Gao, Dal- ing Wang, Ge Yu, and Kam-Fai Wong. Personalized sen- timent classification based on latent individuality of mi- croblog users. In Proceedings of the IJCAI, pages 2277- 2283, 2015.","title":"Personalized sentiment classification based on latent individuality of microblog users","authors":"Kaisong Song, Shi Feng, Wei Gao, Daling Wang, Ge Yu, Kam-Fai Wong","year":"2015","venue":"Proceedings of the IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2015/322"},{"position":18,"raw":"[Song et al., 2017] Kaisong Song, Wei Gao, Shi Feng, Dal- ing Wang, Kam-Fai Wong, and Chengqi Zhang. Recom- mendation vs sentiment analysis: A text-driven latent fac- tor model for rating prediction with cold-start awareness. In Proceedings of the IJCA, pages 2744-2750, 2017.","title":"Recommendation vs sentiment analysis: A text-driven latent factor model for rating prediction with cold-start awareness","authors":"Song","year":"2017","venue":"Proceedings of the IJCA","doi":null,"url":null,"internal_url":"/proceedings/2017/382"},{"position":19,"raw":"[Tang et al., 2014] Duyu Tang, Furu Wei, Nan Yang, Ming Zhou, Ting Liu, and Bing Qin. Learning sentiment- specific word embedding for twitter sentiment classifica- tion. In Proceedings of the ACL, pages 1555-1565, 2014.","title":"Learning sentimentspecific word embedding for twitter sentiment classification","authors":"Tang","year":"2014","venue":"Proceedings of the ACL","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Tang et al., 2016a] Duyu Tang, Bing Qin, Xiaocheng Feng, and Ting Liu. Effective lstms for target-dependent senti- ment classification. In Proceedings of the COLING, pages 3298-3307, 2016.","title":"Effective lstms for target-dependent sentiment classification","authors":"Tang","year":"2016","venue":"Proceedings of the COLING","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Tang et al., 2016b] Duyu Tang, Bing Qin, and Ting Liu. As- pect level sentiment classification with deep memory net- work. In Proceedings of EMNLP, pages 214-224, 2016.","title":"Aspect level sentiment classification with deep memory network","authors":"Tang","year":"2016","venue":"Proceedings of EMNLP","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Tay et al., 2018] Yi Tay, Luu Anh Tuan, and Siu Cheung Hui. Learning to attend via word-aspect associative fu- sion for aspect-based sentiment analysis. In Proceedings of the AAAI, 2018.","title":"Learning to attend via word-aspect associative fusion for aspect-based sentiment analysis","authors":"Yi Tay, Anh Luu, Siu Tuan, Hui Cheung","year":"2018","venue":"Proceedings of the AAAI","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wang et al., 2016] Yequan Wang, Minlie Huang, Xiaoyan Zhu, and Li Zhao. Attention-based LSTM for aspect-level sentiment classification. In Proceedings of EMNLP, pages 606-615, 2016.","title":"Attention-based LSTM for aspect-level sentiment classification","authors":"Wang","year":"2016","venue":"Proceedings of EMNLP","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wang et al., 2018] Shuai Wang, Guangyi Lv, Sahisnu Mazumder, Geli Fei, and Bing Liu. Lifelong learning memory networks for aspect sentiment classification. In Proceedings of Big Data, pages 861-870, 2018.","title":"Lifelong learning memory networks for aspect sentiment classification","authors":"Shuai Wang, Guangyi Lv, Sahisnu Mazumder, Geli Fei, Bing Liu","year":"2018","venue":"Proceedings of Big Data","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Yang et al., 2018] Jun Yang, Runqi Yang, Chongjun Wang, and Junyuan Xie. Multi-entity aspect-based sentiment analysis with context, entity and aspect memory. In Pro- ceedings of AAAI, 2018.","title":"Multi-entity aspect-based sentiment analysis with context, entity and aspect memory","authors":"Jun Yang, Runqi Yang, Chongjun Wang, Junyuan Xie","year":"2018","venue":"Proceedings of AAAI","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhang et al., 2014] Mi Zhang, Jie Tang, Xuchen Zhang, and Xiangyang Xue. Addressing cold start in recommender systems: a semi-supervised co-training algorithm. In Pro- ceedings of the SIGIR, pages 73-82, 2014.","title":"Addressing cold start in recommender systems: a semi-supervised co-training algorithm","authors":"Mi Zhang, Jie Tang, Xuchen Zhang, Xiangyang Xue","year":"2014","venue":"Proceedings of the SIGIR","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}