Geunbae Lee

Korean Combinatory Categorial Grammar and Statistical Parsing

Korean Combinatory Categorial Grammar (KCCG) is an extendedcombinatory categorial grammar formalism to capture thesyntax and interpretation of a relative freess word order, longdistance scrambling, and other specific characteristics of Korean.KCCG formalism can uniformly handle word order variations amongarguments and adjuncts within a clause, as well as in complexclauses and across clause boundaries, i.e. long distancescrambling. The approach we develop takes advantage of the ability of CCGfor type raising and composition along with the ability of variablecategories and unordered argument modeling for relatively freeword order treatment (Lee et al., 1994; Lee et al., 1997).We apply a probability model and heuristics using Koreancharacteristics to our KCCG parser.Results of the experiments on varioustext genre show that the KCCG parser performsat 87.67/87.03% constituent precision/recall.

Corpus-Based Learning of Compound Noun Indexing

In this paper, we present a corpus-based learning method that can index diverse types of compound nouns using rules automatically extracted from a large tagged corpus. We develop an efficient way of extracting the compound noun indexing rules automatically and perform extensive experiments to evaluate our indexing rules. The automatic learning method shows about the same performance compared with the manual linguistic approach but is more portable and requires no human efforts. We also evaluate the seven different filtering methods based on both the effectiveness and the efficiency, and present a new method to solve the problems of compound noun over-generation and data sparseness in statistical compound noun processing.

Multi-level post-processing for Korean character recognition using morphological analysis and linguistic evaluation

Most of the post-processing methods for character recognition rely on contextual information of character and word-fragment levels. However, due to linguistic characteristics of Korean, such low-level information alone is not sufficient for high-quality character-recognition applications, and we need much higher-level contextual information to improve the recognition results. This paper presents a domain independent post-processing technique that utilizes multi-level morphological, syntactic, and semantic information as well as character-level information. The proposed post-processing system performs three-level processing: candidate character-set selection, candidate eojeol (Korean word) generation through morphological analysis, and final single eojeol-sequence selection by linguistic evaluation. All the required linguistic information and probabilities are automatically acquired from a statistical corpus analysis. Experimental results demonstrate the effectiveness of our method, yielding an error correction rate of 80.46%, and improved recognition rate of 95.53% from the before-post-processing rate of 71.2% for single best-solution selection.

From natural language to shell script: A case-based reasoning system for automatic UNIX programming

Abstract We present a case-based approach for natural language interface to a UNIX system with automatic programming ability. Natural language commands are analyzed by case-based parsing and then transformed into UNIX shell-scripts by case-based planning with derivational analogy. Our system, a Dialogue Interface to uNIX (DINX) demonstrates that natural language parsing should be augmented with automatic programming to provide efficient and user friendly interfaces. We suggest case-based reasoning as a unifying framework to combine natural language parsing with automatic programming in a synergistic way.

Table-driven neural syntactic analysis of spoken Korean

A CYK-table-driven interactive relaxation parsing method of spoken Korean, integrated with the CYK-based morphological analysis is introduced. An extension of the Categorial Grammar is introduced to treat the free wordorder in Korean. The table-driven control of interactive relaxation gives efficiency in constituent searching and expectation generation. The lexical nature of the Categorial Grammar and the distributed nature of the interactive relaxation parsing together show a smooth integration of both bottom-up and top-down effects during the spoken language analysis.

Integrating connectionist, statistical and symbolic approaches for continuous spoken Korean processing

This paper presents a multi-strategic and hybrid approach for large-scale integrated speech and natural language processing, employing connectionist, statistical and symbolic techniques. The developed spoken Korean processing engine (SKOPE) integrates connectionist TDNN-based phoneme recognition technique with statistical Viterbi-based lexical decoding and symbolic morphological/phonological analysis techniques. The modular large-scale TDNNs are organized to recognize all 41 Korean phonemes using 10 component networks combined through 3 glue networks. In performance phase, continuously shifted TDNN outputs are integrated with HMM-based Viterbi decoding using a tree-structured lexicon. The Viterbi beam search is integrated with Korean morphotactics and phonological modeling, and produces a morpheme-graph for high-level parsing module. Currently. SKOPE shows average 76.2% phoneme spotting performance for all 41 Korean phonemes (including silence) from continuous speech signals and exhibits average 92.6% morpheme spotting performance from erroneous TDNN outputs after morphological analysis. Other extensive experiments verify that the multi-strategic approaches are promising for complex integrated speech and natural language processing, and the approaches can be extended to other morphologically-complex agglutinative languages such as Japanese.