• Speech Sciences
• /
• v.6
• /
• pp.181-195
• /
• 1999

This study proposes a method of recognizing postpositions and suffixes in Korean spoken language, using prosodic information. We detect grammatical boundaries automatically at first, by using prosodic information of the accentual phrase, and then we recognize grammatical function words by backward-tracking from the boundaries. The experiment employs 300 sentential speech data of 10 men's and 5 women's voice spoken in standard Korean, in which 1080 accentual phrases and 11 postpositions and suffixes are included. The result shows the recognition rate of postpositions in two cases. In one case in which only correctly detected boundaries are included, the recognition rate is 97.5%, and in the other case in which all detected boundaries are included, the recognition rate is 74.8%.

• Speech Sciences
• /
• v.6
• /
• pp.119-143
• /
• 1999

In this paper, the development of English Intonational Phonology is introduced. The existing representation systems of intonation are largely divided into the American structuralist school and the British school, which describe intonation by means of 'levels' and 'configurations' respectively. Both representation systems have some theory-internal problems, however. As for the American school, there is no way to represent pitches much lower than the reference line, while the system of intonation in the British school is limited in that intonation is described in a phonetic impressionistic way rather than from a phonological perspective. Intonational Phonology, a real phonological approach, which has grown out of the basic assumptions of autosegmental-metrical(AM) theory has been suggested by Pierrehumbert(1980). In her approach, an intonational tune is made up of one or more pitch accents, followed by an obligatory phrase accent and an obligatory boundary tone, and interestingly 22 combinations are possible. Intonational Phonology has been revised from Beckman & Pierrehumbert(1986) in developing ToBI(Tones & Break Indices), a proposed standard for labelling prosodic features of digital speech databases in English.

• Speech Sciences
• /
• v.13 no.1
• /
• pp.29-41
• /
• 2006

This study investigates the degree to which various prosodic cues at the boundaries of prosodic phrases in Korean contribute to word segmentation. Since most phonological words in Korean are produced as one Accentual Phrase (AP), it was hypothesized that the detection of acoustic cues at AP boundaries would facilitate word segmentation. The prosodic characteristics of Korean APs include initial strengthening at the beginning of the phrase and pitch rise and final lengthening at the end. A perception experiment utilizing an artificial language learning paradigm revealed that cues conforming to the aforementioned prosodic characteristics of Korean facilitated listeners' word segmentation. Results also indicated that duration and amplitude cues were more helpful in segmentation than pitch. Nevertheless, results did show that a pitch cue that did not conform to the Korean AP interfered with segmentation.

• Proceedings of the KSPS conference
• /
• 1996.10a
• /
• pp.323-332
• /
• 1996

The current speech technology has been aiming to acquire much clearer and more natural synthetic speech sound. The naturalness can be developed by an adequate phrasing of target sentence, of course, which seems to be strongly related to both syntactic and phonetic aspect simultaneously. The present study aims to describe, at one aspect, the relatedness between syntactic structure and prosodic phrasing through dialogue speech, and at the other, to establish a suitable phrasing pattern with respect to the purpose of acquiring more natural synthetic sound. The prosodic phrase, here, means a prosodic unit which can be clearly identified as having an evident break boundary at its final position in a sentence in the sense of both perceptual and acoustical viewpoint. The end of each prosodic phrase is, accordingly, marked as the point of major boundary in a sentence.

• MALSORI
• /
• no.63
• /
• pp.85-100
• /
• 2007

This paper aims to propose how to extract intonation patterns using Momel, a pitch stylization algorithm, and to present results of analyzing speech corpora in comparison with those in earlier researches. Two speech corpora are used: one is the sound files obtained from the K-ToBI web site, and the other consists of 80 passages pronounced by 4 speakers (2 male and 2 female). The results show that Momel provides significant pitch targets which can be labeled as H and L tones within prosodic units such as Accentual Phrase (AP) and Intonation Phrase (IP). The resulting AP patterns and IP boundary tone patterns correspond to those in earlier researches. Thus, this study will contribute to the study of intonation as well as to the development of automatic intonation labeling systems.

• Cross-Cultural Studies
• /
• v.35
• /
• pp.339-368
• /
• 2014

In Teaching Chinese as a Foreign Language, phoneme-based pronunciation teaching such as tone, consonants, vowels is the most common teaching methods. Based on main character of Chinese grammar: 'lack of morphological change' in a narrow sense, was proposed by Lv Shuxiang and Zhu Dexi, I designed 'Communicative oriented Chinese pronunciation teaching method'. This teaching method is composed of seven elements: one kind is the 'structural elements': phoneme, word, phrase, sentence; another kind is the 'functional elements': listening, speaking and translation. This pronunciation teaching method has four kinds of practice methods: 1) phoneme learning method; 2) word based pronunciation practice; 3) phrase based pronunciation practice; 4) sentence based pronunciation practice. When the teachers use these practice methods, they can use the dialogue and Korean-Chinese translation. In particular, when the teachers use 'phoneme learning method', they must use Korean and Chinese phonetic comparison results. When the teachers try to correct learner's errors, they must first consider the speech communication.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.131-150
• /
• 2015

Omission of noun phrases for obligatory cases is a common phenomenon in sentences of Korean and Japanese, which is not observed in English. When an argument of a predicate can be filled with a noun phrase co-referential with the title, the argument is more easily omitted in Encyclopedia texts. The omitted noun phrase is called a zero anaphor or zero pronoun. Encyclopedias like Wikipedia are major source for information extraction by intelligent application systems such as information retrieval and question answering systems. However, omission of noun phrases makes the quality of information extraction poor. This paper deals with the problem of developing a system that can restore omitted noun phrases in encyclopedia documents. The problem that our system deals with is almost similar to zero anaphora resolution which is one of the important problems in natural language processing. A noun phrase existing in the text that can be used for restoration is called an antecedent. An antecedent must be co-referential with the zero anaphor. While the candidates for the antecedent are only noun phrases in the same text in case of zero anaphora resolution, the title is also a candidate in our problem. In our system, the first stage is in charge of detecting the zero anaphor. In the second stage, antecedent search is carried out by considering the candidates. If antecedent search fails, an attempt made, in the third stage, to use the title as the antecedent. The main characteristic of our system is to make use of a structural SVM for finding the antecedent. The noun phrases in the text that appear before the position of zero anaphor comprise the search space. The main technique used in the methods proposed in previous research works is to perform binary classification for all the noun phrases in the search space. The noun phrase classified to be an antecedent with highest confidence is selected as the antecedent. However, we propose in this paper that antecedent search is viewed as the problem of assigning the antecedent indicator labels to a sequence of noun phrases. In other words, sequence labeling is employed in antecedent search in the text. We are the first to suggest this idea. To perform sequence labeling, we suggest to use a structural SVM which receives a sequence of noun phrases as input and returns the sequence of labels as output. An output label takes one of two values: one indicating that the corresponding noun phrase is the antecedent and the other indicating that it is not. The structural SVM we used is based on the modified Pegasos algorithm which exploits a subgradient descent methodology used for optimization problems. To train and test our system we selected a set of Wikipedia texts and constructed the annotated corpus in which gold-standard answers are provided such as zero anaphors and their possible antecedents. Training examples are prepared using the annotated corpus and used to train the SVMs and test the system. For zero anaphor detection, sentences are parsed by a syntactic analyzer and subject or object cases omitted are identified. Thus performance of our system is dependent on that of the syntactic analyzer, which is a limitation of our system. When an antecedent is not found in the text, our system tries to use the title to restore the zero anaphor. This is based on binary classification using the regular SVM. The experiment showed that our system's performance is F1 = 68.58%. This means that state-of-the-art system can be developed with our technique. It is expected that future work that enables the system to utilize semantic information can lead to a significant performance improvement.

• Journal of Korean Classical Literature and Education
• /
• no.38
• /
• pp.139-173
• /
• 2018

In the study of Guunmong, which is one of the representative classical $17^{th}$ century novels of the Joseon Dynasty, interpretations through The Book of Change(Juyeok) have recently emerged. It is necessary to more concretely investigate the themes of the research. The writer Kim man-jung wrote the work in an exile situation. In that time he composed a poem using Chinese letters with meaning connected to The book of Change. In particular, the discourse of Bok-gwae(復卦, ䷗) concentrating on the meaning of recovery might be a basis to construct the inner world of the work. The sentence of 'Bok goes well' in The Book of Change suitably match up with the hero's life in Guunmong. In addition the sentences of 'There is no illness in going and coming. So it will be no faults if friends arriver' can be applied to the meeting between the hero and heroines of Guunmong. The general declarations of The Book of Change are appropriate for explaining the contents of Guunmong. There are six Hyos that make up Gwae. The Hyos, from the first one at the bottom to the fifth one up above, connect to the characters of Guunmong. The phrase of 'Not going far away' regarding to the first Yang Hyo can be connected to Yang So-yu, hero of Guunmong. The phrase of 'Recovering beautifully' with regard to the second Eum Hyo can also be realized in the life of Jeong Gyeong-pae and Ga Chunun, two heroines of the work. The phrase of 'Danger owing to frequently recovering' regarding the third Eum Hyo can be applied to the position of Gye Seom-weol and Jeok Gyeong-hong. The phrase of 'Going middle with recovering alone' regarding the forth Eum Hyo can be matched with Sim Yo-yeon and Baek Reung-pa. The phrase of 'No regrets during an intense recovery' with regard to the fifth Eum Hyo is applicable to Yi So-hwa and Jin Chae-bong. The phrase of 'Boding of a confused recovering' regarding the sixth Eum Hyo is related to the writer's situation. The boding of confused recovering is owing to anti-royal road. The contrast between the royal road and the anti-royal road reflects Confucianism and Buddhism, dream and reality, and Yang So-yu in a dream and Seong Jin, who is same hero, in reality. Moreover, the structure of Guunmong which is organized in the form of reality-dream-reality, has a basis in this contrast. Considering these relationships, we can say the classical novel Guunmong is a fable of Bok-gwae. The work is a hopeful narration of an effective recovery that the writer anticipated in exile.

• The KIPS Transactions:PartB
• /
• v.14B no.7
• /
• pp.559-566
• /
• 2007

Subjective sentences express opinions, emotions, evaluations and other subjective ideas relevant to products or events. These expressions sometimes can be seen in only part of a sentence, thus extracting features from a full-sentence can degrade the performance of subjective-sentence-classification. This paper presents a method for improving the performance of a subjectivity classifier by combining two classifiers generated from the different representations of an input sentence. One representation is a sentimental phrase that represents an automatically identified subjective expression or objective expression and the other representation is a full-sentence. Each representation is used to extract modified n-grams that are composed of a word and its contextual words' polarity information. The best performance, 79.7% accuracy, 2.5% improvement, was obtained when the phrase-level classifier and the sentence-level classifier were merged.

• Journal of Digital Contents Society
• /
• v.17 no.3
• /
• pp.203-210
• /
• 2016

Korean is free of omission of sentence elements and modifying scope, so managing it on morphological analyzer is better than parser. In this paper, we propose functional expansion methods of the morphological analyzer to ease the burden of parsing. This method is a longest phrase matching method. When the series of several morpheme have one syntax category by processing of Unknown-words, Compound verbs, Compound nouns, Numbers and Symbols, our method combines them into a syntactic unit. And then, it is to treat by giving them a semantic features as syntax unit. The proposed morphological analysis method removes unnecessary morphological ambiguities and deceases results of morphological analysis, so improves accuracy of tagger and parser. By empirical results, we found that our method deceases 73.4% of Parsing tree and 52.4% of parsing time on average.