Finding the WRITE Stuff: Automatic Identification of Discourse Structure in Student Essays
IEEE Intelligent Systems
Unsupervised learning of dependency structure for language modeling
ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Representing discourse coherence: a corpus-based analysis
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
COLING-ACL '06 Proceedings of the COLING/ACL on Main conference poster sessions
Extended probabilistic HAL with close temporal association for psychiatric query document retrieval
ACM Transactions on Information Systems (TOIS)
Psychiatric document retrieval using a discourse-aware model
Artificial Intelligence
Proactive screening for depression through metaphorical and automatic text analysis
Artificial Intelligence in Medicine
| Hi-index | 0.00 |
Interactive psychiatric services aim to provide immediate consultation, assessment, and education for mental health care. The first step toward this goal is to know what kinds of depressive symptoms people are experiencing and the semantic relations between symptoms. In consultation records, depressive symptoms are embedded in a single sentence or a discourse segment. A framework integrating the semantic dependencies of a sentence (intrasentence) and the strength of lexical cohesion between sentences (intersentence) supports data-mining the symptoms in these records. In addition, a domain ontology helps to mine the semantic relations between extracted symptoms. Experimental results show that all the intrasentence dependency, intersentence dependency, and domain ontology are significant features in the mining task.This article is part of a special issue on data mining in bioinformatics.