User:Dwijaya

Name: Derry Tanti Wijaya

Homepage: http://www.cs.cmu.edu/~dwijaya

I am a 2nd year PhD student at Language Technologies Institute.

My research interest is in the area of information retrieval, machine learning, and natural language processing. I am currently involved in the Read The Web project that builds a system called NELL which tries to learn overtime to 'read' (automatically extract facts and build a Knowledge Base of these facts) from the Web. Previously I was involved in the e-LICO project, specifically in the building of an ontology of data mining algorithms and models. I have also worked previously on the area of opinion mining and graph clustering.

Project:

Inferring Geographical Activity of Users from Tweets (Finding out who you are from where, when, what and with whom you tweet)

Wiki Writeups: (Theme: Temporal Information Extraction)

Problem

• Temporal Information Extraction (problem)
• Temporal ordering (problem)
• Narrative event chains (problem)

Dataset

• TimeBank Corpus (dataset)
• Gigaword Corpus (dataset)

Method

• Integer Linear Programming (method)
• Topics over Time (method)

Paper

• Chambers and Jurafsky, Jointly combining implicit constraints improves temporal ordering, EMNLP 2008 (paper)
• Yoshikawa et. al., Jointly Identifying Temporal Relations with Markov Logic, Proceedings of the 47th Annual Meeting of the ACL and the 4th IJCNLP of the AFNLP, 2009 (paper)
• Denis and Muller, Predicting Globally-Coherent Temporal Structures from Texts via Endpoint Inference and Graph Decomposition, IJCAI 2011 (paper)
• Das Sarma et. al., Dynamic Relationship and Event Discovery, WSDM 2011 (paper)
• Ling, X. and Weld, D. Temporal Information Extraction. AAAI-10 (paper)
• Chambers and Jurafsky, Unsupervised Learning of Narrative Event Chains, ACL 2008 (paper)