NLP The Return of NLP

1
???????????? NLP The Return of NLP

• ????? ??????????????
• ??????????????????????????????????
• ECTI-21 ???????????????????? 2543 NECTEC
• 22-25 ???????? 2543

2
Human Language Technology

• Spoken Language Input
• Written Language Input
• Language Analysis and Understanding
• Language Generation
• Spoken Language Output
• Document Processing

3
?????? - ???????? - ??????? (1)

• ??????
• ?????????????????????????? ????????????????
• ????????
• ???????????????????? ?????????????????????????????
  ???????????????
• ???????
• ??????????????????????????????????????, ???????,
  ?????????? ???????? ?????????????????????????????

Source Working Knowledge How Organisations
Manage What They Know, Harvard Business School
Press, 1998.
4
?????? - ???????? - ??????? (2)
5
??????????????????

• ??. ??. ??????? ???????????????????????????????
• ??. ?????? ???????????????????????????
• ?????????? ??????????????????? ????? ?????? ?????

6
eEurope

• Knowledge-based Economy and the Internet
• Language fragmentation
• Investing in digital content is a key to achieve
  the Lisbon summit goal to eContent

Turn Europe into the most competitive and
dynamic knowledge-based economy in the world.
7
Information Retrieval

• Cross language IR
• Query translation
• Document translation
• Mixture of the above provides better result
• Translingual IR

Fast MT is needed (probability n-gram)
8
Mono-lingual IR
English Doc
English Query
9
Query Translation
English Doc
English Query
Thai Query
10
Document Translation
Thai Doc
English Doc
Thai Query
11
Hybrid Model IR
Thai Doc
English Doc
English Query
Thai Query
12
Thailand Knowledge-based Economy

• eContent
• Open Source distributed architecture
• Language resources
• Digital Divide
• Speech-based Internet access
• Language Divide
• Multilingual access