• The KIPS Transactions:PartB
• /
• v.19B no.2
• /
• pp.135-148
• /
• 2012

This paper proposes a model for recognizing sentential paraphrases through Predicate-Argument Tuple (PAT)-based approximate alignment between two texts. We cast the paraphrase recognition problem as a binary classification by defining and applying various alignment features which could effectively express the semantic relatedness between two sentences. Experiment confirmed the potential of our approach and error analysis revealed various paraphrase patterns not being solved by our system, which can help us devise methods for further performance improvement.

• Korean Journal of Logic
• /
• v.14 no.1
• /
• pp.77-102
• /
• 2011

This paper is about the problems that Quine's criterion of ontological commitment creates for Nominalists. Quine's clear criterion of ontological commitment, summarized as "to be is to be the value of a variable", means that when we accept a sentence to be true, we are committed to the existence of things that must exist for the sentence to be true. The criterion causes problems for Nominalists. According to Quine's criterion, Nominalists who consider "Humility is a virtue" as true should accept the existence of the property, humility. However, Nominalists are reluctant to accept that properties such as humility exist, although they wish to accept what is meant by "humility is a virtue". The way out of this predicament is presenting a paraphrase which delivers what Nominalists wanted to say through the original sentence without ontological commitment to the property. Several attempts were made to paraphrase such sentences, only to fail. In this paper, successful paraphrases will be presented to cope with previously discussed difficulties. Beforehand, several issues involved in the Quine's criterion will be clarified. Also, Lewis's critical objection that we should give up the business of paraphrase will be discussed.

• International Journal of Advanced Culture Technology
• /
• v.9 no.1
• /
• pp.183-189
• /
• 2021

This study examines the effects of Korean college students' English proficiency and the English text types on their paraphrases. Korean college students with three groups of English proficiency (high, mid, and low) read two types of English texts, causal texts, and argumentative texts, and paraphrased them in English. Students' paraphrase text was evaluated in terms of content (idea exposition, idea development, and wrap up), organization (coherence and cohesion) and language use (grammatical accuracy), and analyzed by MANOVA. As a result, it was found that there was a significant difference in their paraphrase performance according to the participants' English proficiency levels rather than the types of English texts. The results of this study have educational implications for English paraphrase education to prevent plagiarism for Korean university students.

• Korean Journal of Cognitive Science
• /
• v.22 no.1
• /
• pp.57-78
• /
• 2011

Paraphrasing is the act of writing a text using other words without altering the meaning. Paraphrases can be used in many fields of natural language processing. In particular, paraphrases can be incorporated in machine translation in order to improve the coverage and the quality of translation. Recently, the approaches on paraphrase extraction utilize bilingual parallel corpora, which consist of aligned sentence pairs. In these approaches, paraphrases are identified, from the word alignment result, by pivot phrases which are the phrases in one language to which two or more phrases are connected in the other language. However, the word alignment is itself a very difficult task, so there can be many alignment errors. Moreover, the alignment errors can lead to the problem of selecting incorrect pivot phrases. In this study, we propose a method in paraphrase extraction that discriminates good pivot phrases from bad pivot phrases. Each pivot phrase is weighted according to its reliability, which is scored by considering the lexical and part-of-speech information. The experimental result shows that the proposed method achieves higher precision and recall of the paraphrase extraction than the baseline. Also, we show that the extracted paraphrases can increase the coverage of the Korean-English machine translation.

• Annual Conference on Human and Language Technology
• /
• 2012.10a
• /
• pp.175-180
• /
• 2012

기술용어 패러프레이즈 (Terminological Paraphrase, TP)는 학술 문헌 내에서 기술 용어의 개념 및 정의를 다른 형태로 풀어서 알기 쉽게 서술적 문구 (descriptive expression) 를 의미한다. 이러한 TP들에 대한 효율적인 식별과 추출은 학술 정보에 대한 개념적 접근이나 학술 정보 검색의 재현율 향상에 매우 중요하다. 본 논문은 생명 공학 분야의 논문에 나타나는 다양한 형태의 TP들을 효율적으로 추출하기 위한 정보 검색 기반의 추출 방법론을 제시하고 총 여섯 가지의 추출 랭킹 모델을 기반으로 이를 결합함으로써 TP추출의 확장 가능성에 대한 실험적 연구를 수행한다. 실험 결과, 활용된 랭킹 모델이 서로 상호 보완적인 관계에 있음을 알 수 있었으며, 랭킹 결합에 의한 성능 개선 효과를 얻을 수 있었다.

• Language and Information
• /
• v.5 no.2
• /
• pp.9-20
• /
• 2001

Barker (1997) has argued that all the three approaches to anaphora, namely, E-type theories, Discourse Representation Theory, and Dynamic Semantics, are faced with the so-called 'double-bind' problem in the quantifier/variable-binding model of anaphora. Recently, in the same journal, Slater (2000) has claimed that the so-called epsilon account (Slater 1991, 1993, 1994, 1997) handles the problem without any difficulty. However, it will be proposed in this paper that the epsilon account has its own problems in handling the quantifier/variable-binding, and that as argued in Yoon (1998), the so-called‘conjunctive paraphrase’account is the correct solution to the problem, which is intuitively supported as well.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.465-469
• /
• 2019

자연어 처리를 위해서 두 문장의 의미 유사성을 분석하는 것은 아주 중요하다. 이 논문은 패러프레이즈 검출 태스크를 수행하기 위한 Paraphrase-BERT를 제안한다. 우선 구글이 제안한 사전 학습된 BERT를 그대로 이용해서 패러프레이즈 데이터 (MRPC)를 가지고 파인 튜닝하였고 추가적으로 최근에 구글에서 새로 발표한 Whole Word Masking 기술을 사용하여 사전 학습된 BERT 모델을 새롭게 파인 튜닝하였다. 그리고 마지막으로 다중 작업 학습을 수행하여 성능을 향상시켰다. 구체적으로 질의 응답 태스크와 패러프레이즈 검출 태스크를 동시에 학습하여 후자가 더 잘 수행될 수 있도록 하였다. 결과적으로 점점 더 성능이 개선되었고 (11.11%의 정확도 향상, 7.88%의 F1 점수 향상), 향후 작업으로 파인 튜닝하는 방법에 대해서 추가적으로 연구할 계획이다.

• ETRI Journal
• /
• v.30 no.1
• /
• pp.155-157
• /
• 2008

This letter introduces a new method to automatically acquire paraphrases using bilingual corpora. It utilizes the bilingual dependency relations obtained by projecting a monolingual dependency parse onto the other language's sentence based on statistical alignment techniques. Since the proposed paraphrasing method can clearly disambiguate the sense of the original phrases using the bilingual context of dependency relations, it would be possible to obtain interchangeable paraphrases under a given context. Through experiments with parallel corpora of Korean and English language pairs, we demonstrate that our method effectively extracts paraphrases with high precision, achieving success rates of 94.3% and 84.6%, respectively, for Korean and English.

• Journal of Ecology and Environment
• /
• v.32 no.4
• /
• pp.217-220
• /
• 2009

The year of 2009 marks the $200^{th}$ anniversary of Charles Darwin's birth and the 150th anniversary of the publication of his book, On the Origin of Species. Having survived the 150 years of hardening and tempering, Darwin's theory of natural selection is now more comprehensive and powerful than ever. It casts its shadow over nearly all academic disciplines and societal sectors. It truly revolutionized the way we look at the world and ourselves. In the midst of Darwinian revolution, however, Korea remains as a backward country as far as the understanding of Darwin and his theory is concerned. A variety of intellectual activities organized to celebrate the Year of Darwin is helping to narrow the gap. This article summarizes the kinds of such activities held in Korea this year and explains how Darwin made all this possible. To paraphrase the famous quotation by Theodosius Dobzhansky, I now dare to say, "Nothing in life makes sense except in the light of evolution".

• Annual Conference on Human and Language Technology
• /
• 2014.10a
• /
• pp.255-258
• /
• 2014

본 논문에서는 semantic parsing과 사전 정의된 어휘-의미 패턴 질의 템플릿 방법론을 결합하여 자연어 질의로부터 RDF 지식베이스에 질의하기 위한 SPARQL 쿼리를 생성하는 방법을 제안한다. semantic parsing 접근법은 문장의 표현과 분리된 형식적 의미표현만을 포착해내므로, paraphrase 혹은 의미 변화와 무관한 어순의 변화에 강인하지만, 일부 자연어 질의문장에는 단순한 의미 및 구조를 갖는 문장도 적합한 형식적 의미표현을 생성하지 못하는 단점이 있다. 따라서 이 연구에서는 이러한 단순한 문장에 있어서는 사전 정의된 질의 템플릿을 사용하여 적합한 쿼리를 생성하되, 적합한 템플릿을 선택하는데 있어 해당 질의문장의 어휘-의미적 유형을 포착하고 해당 정보를 이용하는 방법을 이용하였으며 이를 통해 주 방법론의 약점을 보완하는 제한적인 효과를 얻을 수 있었다.