Ki Chan

Context-based generic cross-lingual retrieval of documents and automated summaries

We develop a context-based generic cross-lingual retrieval model that can deal with different language pairs. Our model considers contexts in the query translation process. Contexts in the query as well as in the documents based on co-occurrence statistics from different granularity of passages are exploited. We also investigate cross-lingual retrieval of automatic generic summaries. We have implemented our model for two different cross-lingual settings, namely, retrieving Chinese documents from English queries as well as retrieving English documents from Chinese queries. Extensive experiments have been conducted on a large-scale parallel corpus enabling studies on retrieval performance for two different cross-lingual settings of full-length documents as well as automated summaries.

Semantic Expectation-Based Causation Knowledge Extraction: A Study on Hong Kong Stock Movement Analysis

Human beings generally analyze information with some kinds of semantic expectations. This not only speeds up the processing time, it also helps to put the analysis in the correct context and perspective. To capitalize on this type of intelligent human behavior, this paper proposes a semantic expectation-based knowledge extraction methodology (SEKE) for extracting causation relations from text. In particular, we study the application of a causation semantic template on the Hong Kong Stock market movement (Hang Seng Index) with English financial news from Reuters, South China Morning Post and Hong Kong Standard. With one-month data input and over a two-month testing period, the system shows that it can correctly analyzes single reason sentences with about 76% precision and 74% recall rates. If partial reason extraction (two out of one reason) is included and weighted by a factor of 0.5, the performance is improved to about 83% and 81% respectively. As the proposed framework is language independent, we expect cross lingual knowledge extraction can work better with this semantic expectation-based framework.

Gene ontology classification of biomedical literatures using context association

The functional annotation of gene products from biomedical literatures has become a pressing issue due to the huge human efforts involved and the evolving biomedical knowledge. In this paper, we propose an approach for facilitating this functional annotation to the Gene Ontology by focusing on a subtask of annotation, that is, to determine which of the Gene Ontology a literature is associated with. This subtask can be formulated as a document classification problem. A feature engineering approach using context association conveyed in the biomedical literatures, in particular, utilizing the proximity relationship between target gene(s) and term features is proposed. Our approach achieves an F-score of 60.24%, which outperforms the submission runs of TREC Genomics 2004 annotation hierarchy subtask. We show that incorporation of context association can enhance the performance of the annotation hierarchy classification problem.

Extracting Causation Knowledge from Natural Language Texts

SEKE2 is a semantic expectation-based knowledge extraction system for extracting causation relations from natural language texts. It is inspired by capitalizing the human behavior of analyzing information with semantic expectations. The framework of SEKE2 consists of different kinds of generic templates organized in a hierarchical fashion. All kinds of templates are domain independent. They are robust and enable flexible changes for different domains and expected semantics. By associating a causation semantic template with a set of sentence templates, SEKE2 can extract causation knowledge from complex sentences without full-fledged syntactic parsing. To demonstrate the flexibility of SEKE2 for different domains, we study the application of causation semantic templates on two domain areas of news stories, namely, Hong Kong stock market movement and global warming.

In-vitro nanodiagnostic platform through nanoparticles and DNA-RNA nanotechnology

Nanocomposites containing nanoparticles or nanostructured domains exhibit an even higher degree of material complexity that leads to an extremely high variability of nanostructured materials. This review introduces analytical concepts and techniques for nanomaterials and derives recommendations for a qualified selection of characterization techniques for specific types of samples, and focuses the characterization of nanoparticles and their agglomerates or aggregates. In addition, DNA nanotechnology and the more recent newcomer RNA nanotechnology have achieved almost an advanced status among nanotechnology researchers¸ therefore, the core features, potential, and significant challenges of DNA nanotechnology are also highlighted as a new discipline. Moreover, nanobiochips made by nanomaterials are rapidly emerging as a new paradigm in the area of large-scale biochemical analysis. The use of nanoscale components enables higher precision in diagnostics while considerably reducing the cost of the platform that leads this review to explore the use of nanoparticles, nanomaterials, and other bionanotechnologies for its application to nanodiagnostics in-vitro.

Coreference resolution using expressive logic models

Coreference resolution is regarded as a crucial step for acquiring linkages among pieces of information extracted. Traditionally, coreference resolution models make use of independent attribute-value features over pairs of noun phrases. However, dependency and deeper relations between features can more adequately describe the properties of coreference relations between noun phrases. In this paper, we propose a framework of coreference resolution based on first-order logic and probabilistic graphical model, the Markov Logic Network. The proposed framework enables the use of background knowledge and captures more complex coreference linkage properties through rich expression of conditions. Moreover, the proposed conditions can capture the structural pattern within a noun phrase as well as contextual information between noun phrases. Our experiments show improvement with the use of the expressive logic models and the use of pattern-based conditions.

Pronoun resolution with Markov logic networks

Pronoun resolution refers to the problem of determining the coreference linkages between the antecedents and the pronouns. We propose to employ a combined model of statistical learning and first-order logic, the Markov logic network (MLN). Our proposed model can more effectively characterize the pronoun coreference resolution process that requires conducting inference upon a variety of conditions. The influence of different types of constraints are also investigated.

Accommodating New Relations for e-Business Text Mining Applications

We investigate an approach of accommodating new logic relations, represented in Markov Logic Networks (MLN), from a source domain to a target domain automatically. One characteristic of this problem setting is that logic relations, which are expressed as logic formulae, previously prepared for the source domain dealing with a text mining application are not sufficient for the target domain. Therefore, new logic formulae for the target domain are automatically discovered by capturing the core logic relations for both domains and the candidate relations in the target domain using the unlabeled data in the target domain. Experimental results demonstrate that the new formulae discovered improve the performance on the target domain.

Adapting relational logic models using unlabeled data

We have developed a framework for tackling the problem of automatically adapting relational logic models, in particular, Markov Logic Network (MLN), from a source domain to a target domains solving the same task using only unlabeled data in the target domain. One characteristic of the problem is that since the data distributions of the two domains are different, there should be different tailor-made relational logic model for each domain. On the other hand, the relational logic models should share certain amount of similarities due to the same goal and similar nature of the data. Unlike ordinary MLN learning methods, which only consider the distribution of the labeled training examples in learning, we also consider the similarities and differences between the labeled examples from the source domain and the unlabeled examples from the target domain. One major idea of our framework is that we aim at maximizing the likelihood of the observations in the unlabeled data in the target domain, and at the same time, minimizing the difference in the model probability distributions between the source and target domains. As a result, the adapted MLN is tailored to the target domain, but it does not deviate far from the source MLN. We have conducted extensive experiments on two different text mining tasks, namely, pronoun resolution and citation matching, showing consistent improvements in the performance of our adapted model.

Discovering patterns from ontology-derived texts

We propose a framework for constructing semantic features for textual documents from tackling the problem of abstracting information in document representation. Semantic patterns are discovered from ontology-derived texts which provide rich contextual information regarding the concepts. The patterns represent the syntactic and semantic relationships implied in the textual documents which can help in extracting and representing the underlying concepts in texts. We also investigate the significance of using the patterns in automatic summarization of biomedical articles.