• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.329-334
• /
• 2021

한국어에서는 문장 내의 주어나 목적어가 자주 생략된다. 자연어 처리에서 이러한 문장을 그대로 사용하는 것은 정보 부족으로 인한 문제 난이도 상승으로 귀결된다. 생략복원은 텍스트에서 생략된 부분을 이전 문구에서 찾아서 복원해 주는 기술이며, 본 논문은 생략된 주어를 복원하는 방법에 대한 연구이다. 본 논문에서는 기존에 생략복원에 사용되지 않았던 다양한 입력 형태를 시도한다. 또한, 출력 레이어로는 finetuning layer(Linear, Bi-LSTM, MultiHeadAttention)와 생략복원 태스크 형태(BIO tagging, span prediction)의 다양한 조합을 실험한다. 국립국어원 무형 대용어 복원 말뭉치를 기반으로 생략복원이 불필요한 네거티브 샘플을 추가하여 ELECTRA 기반의 딥러닝 생략복원 모델을 학습시키고, 생략복원에 최적화된 조합을 검토한다.

• 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.

• Korean Journal of Cognitive Science
• /
• v.25 no.4
• /
• pp.417-433
• /
• 2014

This research examined whether Korean-learners of French were sensitive to discourse structure in anaphoric pronoun resolution. In the experiments, participants read three-sentenced stories and made judgements about how the last sentence of each story makes sense in relation to previous two sentences on a 7-point Likert scale. The stories differed in whether the subject of the last sentence continued the subject of the preceding sentence, and whether the subject of the last sentence was mentioned with a pronoun or a proper noun. The results from French participants replicated the patterns shown in previous studies. In contrast, Koreans exhibited greater difficulty in interpreting pronoun-subject sentences than noun-subject sentences regardless of subject continuity. These findings are discussed within the context of developmental perspective, which suggests the processing of co-referential interpretation may interact with language proficiency.

• Korean Journal of Cognitive Science
• /
• v.11 no.1
• /
• pp.9-24
• /
• 2000

This paper analyzes the distribution and classification of unrealized arguments of a predicate often called zero pronouns. in spoken Korean. Based on the transcript of a one-hour-Iong dialogue. recorded from public radio stations. I present the statistical data on argument ellipsis in Korean with respect to the frequency of zero ronouns as well as the nature of their antecedents. I go further to review some of the previous efforts to identify the discourse- theoretic functions of zero-pronouns in the framework of Centering Theory. and propose that the zero-pronouns in spoken Korean be divided into center-insensitive vs. center-sensitive classes. I also point out a couple of language-particular idiosyncrasies found in Korean, such as morpho-syntactic elements and encyclopaedic knowledge. that interact with center management in on-going discourse and often lead to difficulties in applying the centering rules and constraints to Korean.

• Annual Conference on Human and Language Technology
• /
• 1996.10a
• /
• pp.386-392
• /
• 1996

대용어(anaphor)는 한 문장이나 문장과 문장간에 같은 요소가 되풀이될 때 언어 사용의 경제성(language economy)을 위하여 잉여적 표현을 제거하는 방법으로, 좀 더 간략한 언어 표현으로 대치하여 쓰는 현상이다. 따라서 본 논문에서는 중심어 주도의 단방향 활성 차트 파싱을 이용하여 한국어 문장내에서 야기되는 문맥 대용어의 해결 방안에 대해 제안한다. 이는 자연어를 입력으로 하는 실용목적의 자연어처리 시스템 구축에 있어 필수적으로 요구되는 부분이다. 대용어 해결을 위해 먼저 전산학적인 대용어 정의를 내리고, 대용어와 선행어사이의 의미 분류 및 대용어 해결 과정에 필요한 처리 조건등을 설정하였다 또한 파서내에 대용어 처리를 위해 사전내 자질구조로 ANAPMAJ, ANAPMIN, PERSON, NUM, INDEX자질을 추가하였고, 대용어 해결을 위한 알고리즘을 제안하였으며, 기존에 개발된 HPSG 파서가 처리하는 모든 문장에서 야기된 문맥 대용을 해결하여 파서이후의 응용 시스템에서 이용할 수 있는 내적 표현을 보다 분명하게 형식화하였다.