Identifying Distributional Perspectives from Colingual Groups

Discrepancies exist among different cultures or languages. A lack of mutual understanding among different colingual groups about the perspectives on specific values or events may lead to uninformed decisions or biased opinions. Thus, automatically understanding the group perspectives can provide essential back-ground for many natural language processing tasks. In this paper, we study colingual groups and use language corpora as a proxy to identify their distributional perspectives. We present a novel computational approach to learn shared understandings, and benchmark our method by building culturally-aware models for the English, Chinese, and Japanese languages. Ona held out set of diverse topics, including marriage, corruption, democracy, etc., our model achieves high correlation with human judgements regarding intra-group values and inter-group differences

[1]  David B. Bracewell,et al.  The Language of Power and its Cultural Influence , 2012, COLING.

[2]  Dan Sperber,et al.  The cognitive foundations of cultural stability and diversity , 2004, Trends in Cognitive Sciences.

[3]  Rada Mihalcea,et al.  Identifying Cross-Cultural Differences in Word Usage , 2016, COLING.

[4]  Takehito Utsuro,et al.  Visualizing Cross-Lingual/Cross-Cultural Differences in Concerns in Multilingual Blogs , 2009, ICWSM.

[5]  Kathy McKeown,et al.  I Couldn't Agree More: The Role of Conversational Structure in Agreement and Disagreement Detection in Online Discussions , 2015, SIGDIAL Conference.

[6]  Ilya Sutskever,et al.  Language Models are Unsupervised Multitask Learners , 2019 .

[7]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[8]  Julie Khaslavsky,et al.  Integrating culture into interface design , 1998, CHI Conference Summary.

[9]  Seung-won Hwang,et al.  Mining Cross-Cultural Differences and Similarities in Social Media , 2018, ACL.

[10]  Chris Callison-Burch,et al.  Seeing Things from a Different Angle:Discovering Diverse Perspectives about Claims , 2019, NAACL.

[11]  Hung-Yu Kao,et al.  Probing Neural Network Comprehension of Natural Language Arguments , 2019, ACL.

[12]  J. Heckman.  Sample Selection Bias as a Specification Error (with an Application to the Estimation of Labor Supply Functions) , 1977 .

[13]  James R. Foulds,et al.  Joint Models of Disagreement and Stance in Online Debate , 2015, ACL.

[14]  Benno Stein,et al.  Modeling Frames in Argumentation , 2019, EMNLP.

[15]  D. Bar-Tal.  Shared Beliefs in a Society: Social Psychological Analysis , 2000 .

[16]  Kathleen McKeown,et al.  IMHO Fine-Tuning Improves Claim Detection , 2019, NAACL.

[17]  Susan A. Gelman,et al.  How language shapes the cultural inheritance of categories , 2017, Proceedings of the National Academy of Sciences.

[18]  Myle Ott,et al.  Facebook FAIR’s WMT19 News Translation Task Submission , 2019, WMT.

[19]  Aristides Gionis,et al.  Quantifying Controversy on Social Media , 2018, ACM Trans. Soc. Comput..

[20]  Diyi Yang,et al.  That’s So Annoying!!!: A Lexical and Frame-Semantic Embedding Based Data Augmentation Approach to Automatic Categorization of Annoying Behaviors using #petpeeve Tweets , 2015, EMNLP.

[21]  Vincent Ng,et al.  Why are You Taking this Stance? Identifying and Classifying Reasons in Ideological Debates , 2014, EMNLP.

[22]  Mohammad Fazleh Elahi,et al.  An Examination of Cross-Cultural Similarities and Differences from Social Media Data with respect to Language Use , 2012, LREC.

[23]  Susan C. Herring,et al.  Cultural bias in Wikipedia content on famous persons , 2011, J. Assoc. Inf. Sci. Technol..

[24]  Gerard de Melo,et al.  Detecting Cross-Cultural Differences Using a Multilingual Topic Model , 2016, TACL.