Huan Zhao

Word Polarity Disambiguation Using Bayesian Model and Opinion-Level Features

Contextual polarity ambiguity is an important problem in sentiment analysis. Many opinion keywords carry varying polarities in different contexts, posing huge challenges for sentiment analysis research. Previous work on contextual polarity disambiguation makes use of term-level context, such as words and patterns, and resolves the polarity with a range of rule-based, statistics-based or machine learning methods. The major shortcoming of these methods lies in that the term-level features sometimes are ineffective in resolving the polarity. In this work, opinion-level context is explored, in which intra-opinion features and inter-opinion features are finely defined. To enable effective use of opinion-level features, the Bayesian model is adopted to resolve the polarity in a probabilistic manner. Experiments with the Opinmine corpus demonstrate that opinion-level features can make a significant contribution in word polarity disambiguation in four domains.

Cannabis_TREATS_cancer: Incorporating Fine-grained Ontological Relations in Medical Document Ranking

The previous work has justified the assumption that docu- ment ranking can be improved by further considering the coarse-grained relations in various linguistic levels (e.g., lexical, syntactical and seman- tic). To the best of our knowledge, little work is reported to incorpo- rate the fine-grained ontological relations (e.g., ) in document ranking. Two contributions are worth noting in this work. First, three major combination models (i.e., summation, mul- tiplication, and amplification) are designed to re-calculate the query- document relevance score considering both the term-level Okapi BM25 relevance score and the relation-level relevance score. Second, a vector- based scoring algorithm is proposed to calculate the relation-level rel- evance score. A few experiments on medical document ranking with CLEF2013 eHealth Lab medical information retrieval dataset show that the proposed document ranking algorithms can be further improved by incorporating the fine-grained ontological relations.

Normalization of Chinese Informal Medical Terms Based on Multi-field Indexing

Healthcare data mining and business intelligence are attracting huge industry interest in recent years. Engineers encounter a bottleneck when applying data mining tools to textual healthcare records. Many medical terms in the healthcare records are different from the standard form, which are referred to as informal medical terms in this work. Study indicates that in Chinese healthcare records, a majority of the informal terms are abbreviations or typos. In this work, a multi-field indexing approach is proposed, which accomplishes the term normalization task with information retrieval algorithm with four level indices: word, character, pinyin and its initial. Experimental results show that the proposed approach is advantageous over the state-of-the-art approaches.

Using Word Sense as a Latent Variable in LDA Can Improve Topic Modeling

Since proposed, LDA have been successfully used in modeling text documents. So far, words are the common features to induce latent topic, which are later used in document representation. Observation on documents indicates that the polysemous words can make the latent topics less discriminative, resulting in less accurate document representation. We thus argue that the semantically deterministic word senses can improve quality of the latent topics. In this work, we proposes a series of word sense aware LDA models which use word sense as an extra latent variable in topic induction. Preliminary experiments on benchmark datasets show that word sense can indeed improve topic modeling.