NLP ) Task & Trends

NLP Task

Low-level parsing

• tokenization, stemming

word and phrase level

• Named entity recognition(NER)
• part-of-speech(POS) tagging
• noun-phrase chunking
• dependency parsing
• coreference resolution

Sentence level

• Sentiment analysis
• machine translation

Multi-sentence ans paragraph level

• Entailment prediction
• question answering
• dialog systems
• summarization

Text mining

• Extract useful information and insights from text and document data
  • analyzing the trends of keywords
• Document clustering
  • topic modeling
• Highly related to computational social science
  • analyzing the evolution of people's political tendency

Information retrieval

• Recommendation System 추천시스템(음악, 영상, 광고, 상품 등)

TRENDS OF NLP

word2vec or glove
-> RNN-family models (LSTM, GRU류)
-> attention modules and transformer models (self attention)
-> self-supervised training setting that dooes not require additional labels
-> transfer learning
-> 대기업 주도로 많은 데이터와 리소스로 발전 중