CUBISM
Belief - Anomaly - Social Constructs

About


The CUBISM project aims to bring together research related to dialogue understanding along two different analytical dimensions, namely

(1) participants’ mental content, and

(2) participants’ social roles and relationships

With respect to mental content, we are extending the ViewGen belief ascription system (Wilks & Ballim, 1989) to maintain beliefs and other propositional attitudes for individuals and groups and to model the change and exchange of beliefs/attitudes within and amongst individuals and groups. We are populating this “belief engine” with semantic content extracted from dialogues and attributed to participants. To our knowledge, this will be the first time a belief engine has been combined with real content extracted from dialogue corpora.

Social relations such as ‘leader’ or ‘influences’, provide important social information about participant roles and relationships. Such social information is latent in dialogue and derivable via sociolinguistic features such as topic, sentiment, and notions of “distance” between dialogue participants by our project partners (Strzalkowski et al., 2013).

Publications


Yorick Wilks, Micah Clark, Tomas By, Adam Dalton and Ian Perera CUBISM: Belief, anomaly and social constructs, In Marjorie McShane (ed), Mental Model Ascription by Intelligent Agents. Special issue of Interaction Studies 15:3 (2014) pp. 388 – 403

Samira Shaikh, Rob Giarrusso, Veena Ravishankar, and Tomek Strzalkowski. 2014. The SUNY Albany Sentiment Slot Filling System. In Proceedings of the 2014 TAC KBP Workshop. NIST. Gaithersburg, Maryland.

Clark, M., Dalton, A., By, T., Wilks, Y., Shaikh, S., Lin, C., & Strzalkowski, T. (2014). Influence and Belief in Congressional Hearings. Participation paper for the 2014 NLP Unshared Task in PoliInformatics.

Shaikh, S., Strzalkowski, S., Giarrusso, J., & Ravishankar, V. (2014). SUNY-Albany Sentiment Extraction System at the TAC 2014 Sentiment Slot Filling Evaluation Track. To appear in Proceedings of the 2014 Text Analysis Conference. Gaithersburg, MD: NIST Press.

Chen, Y., & Wang, D. (2014). Knowledge Expansion over Probabilistic Knowledge Bases. Proceedings of the ACM SIGMOD International Conference on Management of Data (pp. 649–660). New York, NY: ACM Press.

Chen, Y., Petrovic, M., & Clark, M. (2014). SemMemDB: In-Database Knowledge Activation. To appear in Proceedings of the 27th International Conference of the Florida Artificial Intelligence Research Society. Menlo Park, CA: AAAI Press.

Nia, M. S., Grant, C., Peng, Y., Wang, D. Z., & Petrovic, M. (2014). Streaming Fact Extraction for Wikipedia Entities at Web-Scale. To appear in Proceedings of the 27th International Conference of the Florida Artificial Intelligence Research Society. Menlo Park, CA: AAAI Press.

Nia, M. S., Grant, C., Peng, Y., Wang, D. Z., & Petrovic, M. (2013). University of Florida Knowledge Base Acceleration Notebook. In The 22nd Text REtrieval Conference (TREC 2013) Proceedings (NIST Special Publication SP-500-302).