• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.125-132
• /
• 2022

Sentence compression is a natural language processing task that generates concise sentences that preserves the important meaning of the original sentence. For grammatically appropriate sentence compression, early studies utilized human-defined linguistic rules. Furthermore, while the sequence-to-sequence models perform well on various natural language processing tasks, such as machine translation, there have been studies that utilize it for sentence compression. However, for the linguistic rule-based studies, all rules have to be defined by human, and for the sequence-to-sequence model based studies require a large amount of parallel data for model training. In order to address these challenges, Deleter, a sentence compression model that leverages a pre-trained language model BERT, is proposed. Because the Deleter utilizes perplexity based score computed over BERT to compress sentences, any linguistic rules and parallel dataset is not required for sentence compression. However, because Deleter compresses sentences only considering perplexity, it does not compress sentences by reflecting the linguistic information of the words in the sentences. Furthermore, since the dataset used for pre-learning BERT are far from compressed sentences, there is a problem that this can lad to incorrect sentence compression. In order to address these problems, this paper proposes a method to quantify the importance of linguistic information and reflect it in perplexity-based sentence scoring. Furthermore, by fine-tuning BERT with a corpus of news articles that often contain proper nouns and often omit the unnecessary modifiers, we allow BERT to measure the perplexity appropriate for sentence compression. The evaluations on the English and Korean dataset confirm that the sentence compression performance of sentence-scoring based models can be improved by utilizing the proposed method.

• Speech Sciences
• /
• v.9 no.1
• /
• pp.173-184
• /
• 2002

The question of Korean rhythmic type is still a controversial issue (syllable-timed; stress-timed; word-timed). As a step toward solving the question, an experiment was carried out to examine compression effects in Korean. There has been a general belief that the increase of the number of following or preceding syllables causes compression of a vowel (or syllable) in many languages, and a marked anticipatory compression effect can be especially indicative of stress timing. The purpose of this research, therefore, was to obtain some evidence to determine whether or not Korean is stress-timed. The durations of the target vowel/a/ of the monosyllabic word /pap/ were measured at both word and sentence level. In general, marked anticipatory and backward compression effects on the target vowel were observed across one-, two- and three-syllable words in citation form, whereas the effects were neither marked nor consistent at sentence level. These results led us to claim that Korean is not stress-timed.

• The KIPS Transactions:PartB
• /
• v.12B no.6 s.102
• /
• pp.691-696
• /
• 2005

In this paper, we present a pilot system that tn compress a Korean sentence automatically using knowledge extracted from news articles and their headlines. A sot of compressed sentences can be presented as an abstraction of a document. As a compressed sentence is of headline-style, it could be easily displayed on small devices, such as mobile phones and other handhold devices. Our compressing system has shown to be promising through a preliminary experiment.

• Speech Sciences
• /
• v.9 no.4
• /
• pp.165-173
• /
• 2002

Strong compression effects in a stressed vowel due to the addition of syllables have been adopted as evidence for stress-timing. In relation to this, Yun (2002) investigated the compression effects of number of syllables on Korean vowel. The results generally revealed that Korean had neither significant nor consistent anticipatory or backwards compression effects, especially when it came to the sentence level. This led us to claim that Korean would not be a stress-timed language. But the language investigated in the study was only Korean, and further cross-linguistic research was needed to confirm the claim. In this study, Yun's (2002) sentence level data are compared with Fowler's (1981) English data. The comparison reveals that Korean seems to be similar to English in the backwards compression effect, whereas the two languages are markedly different in the anticipatory compression effect. Thus, if English is a stress-timed language and the strong anticipatory compression effect is evidence in favour of stress-timing as is claimed, the present cross-linguistic study confirms Yun's (2002) suggestion-Korean is unlikely to be stress-timed. On the other hand, compression effects are revisited: the differences in vowel compression between English and Korean are discussed from the syntactic and phonological points of view.

• The Journal of the Acoustical Society of Korea
• /
• v.32 no.5
• /
• pp.430-437
• /
• 2013

The present study examined whether sentence perception scores were changed under various conditions of time alteration (compression and/or expansion) and selective word stress in normal hearing listeners. Twenty young normal hearing adults (ten males) were participated. As stimuli, Korean standard-sentence list for adults (KS-SL-A) modified to semantically anomalous sentences was newly recorded by a female speaker. Seven different time-altered conditions (e.g., ${\pm}60%$, ${\pm}40%$, ${\pm}20%$, 0 %) were controlled. To see the effect of selective word stress (i.e., the emphasis of specific syllables in the sentence), all subjects were tested twice 2 weeks apart. The results showed 1) there was significantly different sentence perception scores among the different time-altered conditions, yet only in the 60 % compression condition; 2) there was no significant difference of the sentence perception scores in the effect of stress; however, there was a positive effect of the selective word stress in the sentences consisting of 6 ~ 7 syllables at the 40 % compression condition; 3) there was no significant gender difference. The pattern of results suggests that the combination of time compression and selective word stress is more effective to understand speech, instead of only using time expansion condition. However, further studies should be needed for standardization.

• Journal of KIISE:Software and Applications
• /
• v.35 no.5
• /
• pp.313-324
• /
• 2008

A sentence reduction is the information compression process which removes extraneous words and phrases and retains basic meaning of the original sentence. Most researches in the sentence reduction have required a large number of lexical and syntactic resources and focused on extracting or removing extraneous constituents such as words, phrases and clauses of the sentence via the complicated parsing process. However, these researches have some problems. First, the lexical resource which can be obtained in loaming data is very limited. Second, it is difficult to reduce the sentence to languages that have no method for reliable syntactic parsing because of an ambiguity and exceptional expression of the sentence. In order to solve these problems, we propose the sentence reduction method which uses templates and POS(part of speech) information without a parsing process. In our proposed method, we create a new sentence using both Sentence Reduction Templates that decide the reduction sentence form and Grammatical POS-based Reduction Rules that compose the grammatical sentence structure. In addition, We use Viterbi algorithms at HMM(Hidden Markov Models) to avoid the exponential calculation problem which occurs under applying to Sentence Reduction Templates. Finally, our experiments show that the proposed method achieves acceptable results in comparison to the previous sentence reduction methods.

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.870-878
• /
• 2019

In this paper, we propose an Attention-based BLSTM for predicting the video compression standard of a video. Recently, in NLP, many researches have been studied to predict the next word of sentences, classify and translate sentences by their semantics using the structure of RNN, and they were commercialized as chatbots, AI speakers and translator applications, etc. LSTM is designed to solve the gradient vanishing problem in RNN, and is used in NLP. The proposed algorithm makes video compression standard prediction possible by applying BLSTM and Attention algorithm which focuses on the most important word in a sentence to a bitstream of a video, not an sentence of a natural language.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1985.10a
• /
• pp.68-71
• /
• 1985

In this paper, Sentence-Sip E Il Ka Gi Seo U1 E Gan Da was spoken by 4 men and 3 see sound is used for the experiment. A/D conversion time is 30 sec. Data are obtained using the microcomputer and compressed by ADPCM Rate of compression is 1/8. Data compressed by ADPCM are synthesized and compared to the original sound. Rate of speech identification is analysed using the sound pressure, white noise. Coding of ADPCM is done for 5bit. As the result of fixing starting voltage by 2.6V. It is acertained that variable value increases in initial speech signal and then process is made by minimum value "3". From the result of processing, synthesized sound is almost eaual to original sound. Minimum values cause distorition, Dummy Head System is used in this experiment.xperiment.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.389-392
• /
• 2021

문장 압축은 원본 문장의 중요한 의미를 보존하는 짧은 길이의 압축 문장을 생성하는 자연어처리 태스크이다. 문장 압축은 사용자가 텍스트로부터 필요한 정보를 빠르게 획득할 수 있도록 도울 수 있어 활발히 연구되고 있지만, 기존 연구들은 사람이 직접 정의한 압축 규칙이 필요하거나, 모델 학습을 위해 대량의 데이터셋이 필요하다는 문제점이 존재한다. 사전 학습된 언어 모델을 통한 perplexity 기반의 문장 점수 측정을 통해 문장을 압축하여 압축 규칙과 모델 학습을 위한 데이터셋이 필요하지 않은 연구 또한 존재하지만, 문장 점수 측정에 문장에 속한 단어들의 의미적 중요도를 반영하지 못하여 중요한 단어가 삭제되는 문제점이 존재한다. 본 논문은 언어 정보 중 품사 정보, 의존관계 정보, 개체명 정보의 중요도를 수치화하여 perplexity 기반의 문장 점수 측정에 반영하는 방법을 제안한다. 또한 제안한 문장 점수 측정 방법을 활용하였을 때 문장 점수 측정 기반 문장 압축 모델의 문장 압축 성능이 향상됨을 확인하였으며, 이를 통해 문장에 속한 단어의 언어 정보를 문장 점수 측정에 반영하는 것이 의미적으로 적절한 압축 문장을 생성하는 데 도움이 될 수 있음을 보였다.

• Journal of Biomedical Engineering Research
• /
• v.31 no.5
• /
• pp.385-394
• /
• 2010

Automatic gain control(AGC) is used in hearing aids to compensate for the hearing level as to reduced dynamic range. AGC is consisted of the main 4 factors which are compression threshold, compression ratio, attack time, and release time. This study especially focus on each individual need for optimum release time parameters that can be changed within 7 certain range such as 12, 64, 128, 512, 2094, and 4096ms. To estimate the effect of various release time in AGC, twelve normal hearing and twelve hearing impaired listeners are participated. The stimuli are used by one syllable and sentence which have the same acoustic energy respectively. Then, each of score of the word recognition score is checked in quiet and noise conditions. As a result, it is verified that most people have the different best recognition score on specific release time. Also, if hearing aids is set by the optimum release time in each person, it is helpful in speech recognition and discrimination.