Thatsanee Charoenporn

Infrastructure for Standardization of Asian Language Resources

As an area of great linguistic and cultural diversity, Asian language resources have received much less attention than their western counterparts. Creating a common standard for Asian language resources that is compatible with an international standard has at least three strong advantages: to increase the competitive edge of Asian countries, to bring Asian countries to closer to their western counterparts, and to bring more cohesion among Asian countries. To achieve this goal, we have launched a two year project to create a common standard for Asian language resources. The project is comprised of four research items, (1) building a description framework of lexical entries, (2) building sample lexicons, (3) building an upper-layer ontology and (4) evaluating the proposed framework through an application. This paper outlines the project in terms of its aim and approach.

Improving translation quality of rule-based machine translation

This paper proposes machine learning techniques, which help disambiguate word meaning. These methods focus on considering the relationship between a word and its surroundings, described as context information in the paper. Context information is produced from rule-based translation such as part-of-speech tags, semantic concept, case relations and so on. To automatically extract the context information, we apply machine learning algorithms which are C4.5, C4.5rule and RIPPER. In this paper, we test on ParSit, which is an interlingual-based machine translation for English to Thai. To evaluate our approach, an verb-to-be is selected because it has increased in frequency and it is quite difficult to be translated into Thai by using only linguistic rules. The result shows that the accuracy of C4.5, C4.5rule and RIPPER are 77.7%, 73.1% and 76.1% respectively whereas ParSit give accuracy only 48%.

Thai WordNet Construction

This paper describes semi-automatic construction of Thai WordNet and the applied method for Asian wordNet. Based on the Princeton WordNet, we develop a method in generating a WordNet by using an existing bi-lingual dictionary. We align the PWN synset to a bilingual dictionary through the English equivalent and its part-of-speech (POS), automatically. Manual translation is also employed after the alignment. We also develop a web-based collaborative workbench, called KUI (Knowledge Unifying Initiator), for revising the result of synset assignment and provide a framework to create Asian WordNet via the linkage through PWN synset.

Construction of Thai Lexicon from Existing Dictionaries and Texts on the Web

A lexicon is an important linguistic resource needed for both shallow and deep language processing. Currently, there are few machine-readable Thai dictionaries available, and most of them do not satisfy the computational requirements. This paper presents the design of a Thai lexicon named the TCLs Computational Lexicon (TCLLEX) and proposes a method to construct a large-scale Thai lexicon by re-using two existing dictionaries and a large number of texts on the Internet. In addition to morphological, syntactic, semantic case role and logical information in the existing dictionaries, a sort of semantic constraint called selectional preference is automatically acquired by analyzing Thai texts on the web and then added into the lexicon. In the acquisition process of the selectional preferences, the so-called Bayesian Information Criterion (BIC) is applied as the measure in a tree cut model. The experiments are done to verify the feasibility and effectiveness of obtained selection preferences.

Query Expansion using LMF-Compliant Lexical Resources

This paper reports prototype multilingual query expansion system relying on LMF compliant lexical resources. The system is one of the deliverables of a three-year project aiming at establishing an international standard for language resources which is applicable to Asian languages. Our important contributions to ISO 24613, standard Lexical Markup Framework (LMF) include its robustness to deal with Asian languages, and its applicability to cross-lingual query tasks, as illustrated by the prototype introduced in this paper.

Collaborative platform for multilingual resource development and intercultural communication

In the present borderless information society, we need a lot of fundamental linguistic tools as well as the standard reference resources to facilitate our daily communications across the languages and cultures for better understanding or smoothing the communications. Online collaborative works are efficiently conducted among expert groups via many existing services such as Sourceforge, Wiki or Weblog. However, in the process of multilingual resource development and intercultural communication we still need to fulfill the requirements in well-structured design of the database, and communication tools that provide necessary linkages between records of intention to particular assertions, and functions to realize selectional preference in case that there are more than one assertion. In this paper, we propose a new platform, called Knowledge Unifying Initiator (KUI). We conducted a study on multilingual medical text collaborative translation and the initiative in Asian WordNet development to evaluate our proposed platform.

A cross system machine translation

The rapid growth of Internet Technology, especially user friendliness approach, helps increase the number of Internet users and the amount of information in the cyberspace. There is a countless amount of information in languages. This has spread developments of MT systems. The focus of our approach is to increase the reusability of those MT systems by using Cross System machine translation. Using natural language as an intermediate language, such as English, will help us use the information in Internet qualitatively. In this paper, we point out some problems that may cause the efficiency to decrease when a sentence is translated from a second language to a third language. A novel method is proposed to solve this problem.

The study of feature vector in HMM-based Wii application for Thai sword dance

In beginning to classify gestures, a Wii remote is used as the primary tool for collecting raw data. Next, the Hidden Markov Model method is used to classify the gestures. The performance of this classification method is reliant on the feature vector used. In this paper, we will propose an appropriate feature vector for classifying gestures used in Thai sword dancing. The feature vectors are evaluated for their accuracy of classification based on their receptivity to acceleration, velocity, and displacement.

An EM-Based Approach for Mining Word Senses from Corpora

Manually collecting contexts of a target word and grouping them based on their meanings yields a set of word senses but the task is quite tedious. Towards automated lexicography, this paper proposes a word-sense discrimination method based on two modern techniques; EM algorithm and principal component analysis (PCA). The spherical Gaussian EM algorithm enhanced with PCA for robust initialization is proposed to cluster word senses of a target word automatically. Three variants of the algorithm, namely PCA, sGEM, and PCA-sGEM, are investigated using a gold standard dataset of two polysemous words. The clustering result is evaluated using the measures of purity and entropy as well as a more recent measure called normalized mutual information (NMI). The experimental result indicates that the proposed algorithms gain promising performance with regard to discriminate word senses and the PCA-sGEM outperforms the other two methods to some extent.

Selection model for communication performance of the bus tracking system

In this paper, we proposed a model for bus tracking system using Bluetooth Low Energy in order to run in a university. The proposed system used elemental electronic development boards for minimizing the development cost. The comparison of ESP8266-ESP-01 and NodeMCU depicted that fail and critical fail request of NodeMCU are less than ESP-01. The overall analysis, design and development for university campus bus tracking are depicted and satisfaction statistics are also provided.