<div id="readability-page-1" class="page"><div id="dkContent" role="main">

					

					
						<h2>sohyunwriter</h2>
					

					
						


						
							
							

							<div> Academic Disciplines related to NLP

1. natural language processing (major conference : ACL, EMNLP, NAACL)
1) low level parsing
-Tokenization
e.g. 나는 학교를 간다 -&gt; 나, 는, 학교, 를, 가, ㄴ, 다
-stemming (어근 추출)
e.g. study -&gt; studying, studied / 맑다 -&gt; 맑은데, 맑지만, 맑고

2) word and phrase level
-Named entity recognition (NER)
e.g. 뉴욕타임즈
-part-of-speech(POS) tagging
e.g. 주어/본동사/목적어/부사구/형용사구 등 구분
-noun-phrase chunking
-dependency parsing
-coreference resolution

3) sentence level
-Sentiment analysis
e.g. 긍정/부정 구분
-machine translation
e.g. I study math. -&gt; 나는 수학을 공부한다.

4) Multi-sentence and paragraph level
-entailment prediction
e.g. 어제 한 번도 결혼하지 않았다. 어제 존이 결혼했다. -&gt; 두 문장은 모순 관계
-question answering
e.g. where did napoleon die?-&gt; 단순 키워드가 들어간 텍스트를 검색하는게 아니라 이 질문에 대한 대답을 반환
-dialogue systems
e.g. 챗봇과 같은 대화를 수행
-summarization
e.g. 뉴스 문서 한줄 요약

2. Text mining (major conferences : KDD, The WebConf (formerly, WWW), WSDM, CIKM, ICWSM)
-Extract useful information and insights from text and document data
e.g. analyzing the trends of AI-related keywords from massive news data
-Document clustering (e.g. topic modeling)
e.g. clustering news data and grouping into different subjects
-Highly related to computational social science
e.g. analyzing the evolution of people's political tendency based on social media data

3. Information retrieval (major conferences: SIGIR, WSDM, CIKM, RecSys)
-Highly related to computational social science
-&gt; This area is not actively studied now
-&gt; It has evolved into a recommendation system, which is still an active area of research



<div data-ke-type="moreLess" data-text-more="더보기" data-text-less="닫기"><a>더보기</a>출처 : 부스트캠프 AI Week4 Day 16, 주재걸 교수님 강의
</div>
 
</div>
							

							
								
							

							


						
					

					

					

					

					

					

					
						
					
				</div></div>

sohyunwriter

Academic Disciplines related to NLP
 
1. natural language processing (major conference : ACL, EMNLP, NAACL)
1) low level parsing
-Tokenization
e.g. 나는 학교를 간다 -> 나, 는, 학교, 를, 가, ㄴ, 다
-stemming (어근 추출)
e.g. study -> studying, studied / 맑다 -> 맑은데, 맑지만, 맑고
 
2) word and phrase level
-Named entity recognition (NER)
e.g. 뉴욕타임즈
-part-of-speech(POS) tagging
e.g. 주어/본동사/목적어/부사구/형용사구 등 구분
-noun-phrase chunking
-dependency parsing
-coreference resolution
 
3) sentence level
-Sentiment analysis
e.g. 긍정/부정 구분
-machine translation
e.g. I study math. -> 나는 수학을 공부한다.
 
4) Multi-sentence and paragraph level
-entailment prediction
e.g. 어제 한 번도 결혼하지 않았다. 어제 존이 결혼했다. -> 두 문장은 모순 관계
-question answering
e.g. where did napoleon die?-> 단순 키워드가 들어간 텍스트를 검색하는게 아니라 이 질문에 대한 대답을 반환
-dialogue systems
e.g. 챗봇과 같은 대화를 수행
-summarization
e.g. 뉴스 문서 한줄 요약
 
2. Text mining (major conferences : KDD, The WebConf (formerly, WWW), WSDM, CIKM, ICWSM)
-Extract useful information and insights from text and document data
e.g. analyzing the trends of AI-related keywords from massive news data
-Document clustering (e.g. topic modeling)
e.g. clustering news data and grouping into different subjects
-Highly related to computational social science
e.g. analyzing the evolution of people's political tendency based on social media data
 
3. Information retrieval (major conferences: SIGIR, WSDM, CIKM, RecSys)
-Highly related to computational social science
-> This area is not actively studied now
-> It has evolved into a recommendation system, which is still an active area of research
 
 
 
더보기
출처 : 부스트캠프 AI Week4 Day 16, 주재걸 교수님 강의

자연어처리 각 분야들 (NLP tasks)

댓글