Choong-Nyoung Seon

Review of Korean Speech Act Classification: Machine Learning Methods

To resolve ambiguities in speech act classification, various machine learning models have been proposed over the past 10 years. In this paper, we review these machine learning models and present the results of experimental comparison of three representative models, namely the decision tree, the support vector machine (SVM), and the maximum entropy model (MEM). In experiments with a goal-oriented dialogue corpus in the schedule management domain, we found that the MEM has lighter hardware requirements, whereas the SVM has better performance characteristics.

Improving domain action classification in goal-oriented dialogues using a mutual retraining method☆

Abstract To reduce lengthy and rigid interactions of menu-driven navigation and keyword searches, dialogue systems based on a natural language interface have been developed. Domain action classification is an essential part of a dialogue system because speakers’ intentions are determined through the classification process. Although a domain action consists of a tightly associated speech act and a concept sequence, previous studies have independently dealt with speech acts and concept sequences in order to simplify the models, and this simplification has caused a decrease in performance. A retraining method for improving the domain action classification performance is proposed in order to resolve this problem. The proposed method divides a domain action classification model into a speech act classification model and a concept sequence classification model. The speech act classification model repeatedly uses concept sequence classification model outputs as inputs during training. In the experiments with goal-oriented dialogues, the proposed method exhibited a higher accuracy of 0.6% and higher macro F1-measure of 1.7% compared to the SVM and ME models that dealt with speech acts and concept sequences separately. Based on the experimental results, it was determined that the proposed method can improve the performance of some representative machine learning models for domain action classification.

Efficient appointment information extraction from short messages in mobile devices with limited hardware resources

With the rapid evolution of the mobile environment, demand for information extraction from mobile devices is increasing. This paper proposes an information extraction system that is designed for mobile devices with limited hardware resources. The proposed system extracts temporal (dates and times) and named instances (locations and title) from Korean short messages in an appointment management domain. To efficiently extract temporal instances with limited numbers of surface forms, the proposed system uses well-refined finite state automata. To effectively extract various surface forms of named instances with limited hardware resources, the proposed system uses a modified hidden Markov model (HMM) based on character n-grams. In the experiment on instance boundary labeling, the proposed system showed comparable performances with representative conventional classifiers. The proposed system was implemented in a commercial mobile phone to test its ability to automatically extract appointment information from a short message and store the information into a schedule database. The system performed well with a reasonable response time.

TRANSLATION ASSISTANCE SYSTEM BASED ON SELECTIVE WEIGHTING AND CLUSTER-BASED SEARCHING METHODS

Visiting a foreign country is now much easier than it was in the past. This has led to a consequent increase in the need for translation services during these visits. To satisfy this need, a reliable translation assistance system based on sentence retrieval techniques is proposed. When a user inputs a sentence in his/her native language, the proposed system retrieves sentences similar to the input sentence from a pre-constructed bilingual corpus and returns pairs of sentences in the native and foreign languages. To reduce the lexical disagreement problems that inevitably occur in this sentence retrieval application, the proposed system uses multi-level linguistic information (i.e., keywords, sentence types, and concepts) with different weights as indexing terms. In addition, the proposed system uses clustering information from sentences with similar meanings to smooth the retrieval target sentences. In an experiment, the proposed system outperformed traditional IR systems. Based on various experiments, it was found that multi-level information was effective at alleviating critical lexical disagreement problems in sentence retrieval. It was also found that the proposed system was suitable for sentence retrieval applications such as translation assistance systems.

Unsupervised word sense disambiguation for Korean through the acyclic weighted digraph using corpus and dictionary

Word sense disambiguation (WSD) is meant to assign the most appropriate sense to a polysemous word according to its context. We present a method for automatic WSD using only two resources: a raw text corpus and a machine-readable dictionary (MRD). The system learns the similarity matrix between word pairs from the unlabeled corpus, and it uses the vector representations of sense definitions from MRD, which are derived based on the similarity matrix. In order to disambiguate all occurrences of polysemous words in a sentence, the system separately constructs the acyclic weighted digraph (AWD) for every occurrence of polysemous words in a sentence. The AWD is structured based on consideration of the senses of context words which occur with a target word in a sentence. After building the AWD per each polysemous word, we can search the optimal path of the AWD using the Viterbi algorithm. We assign the most appropriate sense to the target word in sentences with the sense on the optimal path in the AWD. By experiments, our system shows 76.4% accuracy for the semantically ambiguous Korean words.

Lightweight Named Entity Extraction for Korean Short Message Service Text

In this paper, we propose a hybrid method of Machine Learning (ML) algorithm and a rule-based algorithm to implement a lightweight Named Entity (NE) extraction system for Korean SMS text. NE extraction from Korean SMS text is a challenging theme due to the resource limitation on a mobile phone, corruptions in input text, need for extension to include personal information stored in a mobile phone, and sparsity of training data. The proposed hybrid method retaining the advantages of statistical ML and rule-based algorithms provides fully-automated procedures for the combination of ML approaches and their correction rules using a threshold-based soft decision function. The proposed method is applied to Korean SMS texts to extract person’s names as well as location names which are key information in personal appointment management system. Our proposed system achieved 80.53% in F-measure in this domain, superior to those of the conventional ML approaches.