Intelligent Chinese Language Pattern and Speech Processing

The following sections are included:

• INTRODUCTION

• CONTENTS

We are building a question-answering system to assist physicians obtaining information from a patient knowledge base. We were motivated to build this system by evidence that physicians are much more willing to use systems that provide interactive responses. Sager’s Linguistic String Parser is being used to generate responses from information formats. These responses combine information retrieved from the knowledge base with inferences made from that information.

This paper presents the design and implementation of a Chinese Expert System Shell which is based on a Chinese Prolog interpreter.

The system is divided into three parts: the knowledge acquisition module, the knowledge application module and the inference engine.

The knowledge engineer defines the syntax of the language to be used by himself and by the users when they interact with the system. The natural language interface is table driven and can be modified easily.

The system also caters for the case when the domain expert finds it difficult to articulate the rules, but is able to give examples. An inductive engine is included to extract rules from examples.

With the word-based theory of natural language processing, a word-based Chinese language understanding system has been developed. In the light of psychological language analysis and the features of the Chinese language, this theory of natural language processing is presented with the description of the computer programs based on it.

The heart of the system is to define a Total Information Dictionary and the World Knowledge Source used in the system. The purpose of this research is to develop a system which can understand not only Chinese sentences but also the whole text.

Since the end of last year, the researchers at the Institute of Systems Science (ISS) started to consider a more ambitious project as part of its multilingual programming objective. This project examines the domain of Chinese Business Letter Writing. With the problem defined as generating Chinese letters to meet business needs, investigations suggest an intersection of 3 possible approaches: knowledge engineering, form processing and natural language processing. This paper attempts to report some of the findings and document the design and implementation issues that have arisen and been tackled as prototyping work progresses.

This study purposes a method for recognizing the lexical tones in Mandarin speech. The method is based on Vector Quantization (VQ) and Hidden Markov Models (HMM). The pitch periods are extracted to derive the feature vectors which represent pitch height and pitch contour slope. One HMM is trained by the feature vectors of monosyllables for each tone. Then the HMMs are used to recognize the tone of monosyllables and disyllables. For the monosyllables, the accuracy rate can be 93.75% for speaker-independent cases. For the disyllables, the accuracy rates are 93% for the first syllables and 90% for the second syllables. It shows that the tone of the second syllable may be affected by the preceding syllable. This degradation also reveals the fact of tone variation in Mandarin speech.

The movement of constituents in natural language is a very common linguistic phenomenon—topicalization and relativization in Mandarin Chinese, for example. Any successful natural language processing system must be able to deal with these movements and, at the same time, justify them. However, it is difficult to achieve these goals due to the gaps in between the constituents. In this paper, a logic programming approach with Chomsky’s Government-Binding Theory (GB) attempts to solve this type of problems in Chinese language processing. According to GB, the rule of “move-α” moves anything anywhere, and the universal principles operate interactively to rule the illegal movements out. With this point of view, no specific movement constraints are specified in our logic programming approach. The universal principles are embedded in the logic grammars implicitly, and generated by a translator. The specific features of this approach enable grammar-writing to capture extrapositions in Chinese much easier than the other approaches.

A long-term research project toward Mandarin speech recognition techniques for very large vocabulary and unlimited text is considered. By carefully examining the special structures of Chinese language, the first-stage goal is set to be the design of efficient techniques to recognize the finals of Mandarin syllables. In this paper, three special approaches to do this are proposed. The Segmental Model Approach defines the final models by dividing the finals into several segments according to the acoustic structures of the speech signals. The Three-pass Approach uses three consecutive passes to classify the finals into small sets and improve the recognition efficiency. The Multi-section Vector Quantization (MSVQ) Approach, on the other hand, significantly reduces the necessary computation time by incorporating the branch-and-bound algorithm and common codebook concept with the MSVQ techniques. Extensive computer simulations are performed first to optimize each approach by choosing the best set of parameters then to compare the performance of the three approaches. It was found that all the three approaches are very efficient in terms of relatively high recognition rate and short computation time, and the MSVQ Approach provides the highest recognition rate at the shortest computation time, thus it is most attractive.

In this paper, we consider the problem of how to design a minimal perfect hashing function which is suitable for the Mandarin Phonetic Symbols system. Our main idea is inspired by Chang’s letter-oriented minimal perfect hashing scheme. By using our hashing function, 1303 Mandarin phonetic symbol transcriptions will be hashed to 1303 locations in the way of one-to-one correspondence.

The target of this recognition system is the set of handwritten Chinese characters input from tablet devices with stroke-sequence and stroke-count being free but within the constraint of normal writing.

A formalism based upon an initial stroke-sequence decision tree and position matching has been developed for recognizing handwritten Chinese characters. This formalism has the advantages of using the features of strokes, stroke-sequence, and geometric relations but avoids the disadvantages caused by the instability of all of the above features. With extensive training, it can be proven that this formalism may provide a very promising result even in handling erroneous writing such as missing a stroke, wrong writing sequence etc.

This paper describes a new approach to the recognition of multi-font printed Chinese characters. The basic idea is to encode a character in terms of two pre-defined stroke relations, namely, relative position relation and relative direction relation. The code-mapping method chosen in our system possesses two main advantages: the first is that the tree-like data base can be easily extended, and the second is that the processing time is independent of the amount of data base. Since the stability of the extracted strokes greatly affects the coding results, a new stroke merging method, which has been experimentally proven to extract strokes more steadily, is also proposed.

This article discusses some intelligence aspects of Chinese characters. Some basic concepts of two-dimensional pattern representation and artificial intelligence such as semantic networks, forward chaining, deduction and the resolution principle are used to analyze and interpret the syntactic structure, representation, semantics and evolution of Chinese characters. The concept of degrees of ambiguity and the principle of new characters are investigated. It is found that Chinese characters are actually not only artistically elegant and culturally rich but also semantically meaningful and intelligently sound. Finally some topics for future research such as intelligent pattern recognition for Chinese characters, automatic learning and translation, and knowledge-based Chinese language understanding are discussed.

We have developed a character recognition method for learning Kanji by CAL. Using this method, students can identify characters whose stroke order or stroke connection is incorrect, and identify which of the strokes has been written incorrectly. The system can recognize 99.7% of 120,000 test patterns with stroke order errors, stroke connection errors, or both. For correctly recognized characters, the error detection ratio was greater than 99.9%. The processing time was only 0.5 second/character when run on a 16-bit personal computer.