Humanhuman Communication and Knowledge Management

1
Human-human Communication and Knowledge Management

• Kazuo Sumita
• Corporate RD Center
• TOSHIBA Corp.

2
Agenda

• Toshibas NLP RD activities
• Toshibas knowledge management system
• Shortage of the current KM system
• New approaches
• GroupScribe for group communication management
• MKIDS for multi-modal knowledge sharing
• Future work

3
TOSHIBA NLP RD activities 1/3

• Machine translation
• English-Japanese MT Dictionary tuning using
  large corpora
• Chinese-Japanese MT Hybrid framework using
  rule- and statistics-based approaches
• English-Chinese MT Prototyping using the
  framework for EJMT
• Japanese-English speech translation Prototyping
• MT products
• The Honyaku (PKG software), MT server (Japan
  Infoseek, lycos, excite, _at_nifty, Japan Patent
  Offices IPDL, ), Engine License to other
  companies

4
TOSHIBA NLP RD activities 2/3

• Information retrieval and knowledge mining
• Natural language based information retrieval
• Question answering
• Cross language information retrieval
• Text mining document clustering, categorization,
  information extraction
• Knowledge mining products
• KnowledgeMeister KM software which can work
  with several other systems (IBM WebSphere portal,
  Oracle9iAS Portal, Livelink, Fuji Xerox
  DocuCentre, Microsoft SharePointPortal server,
  Exchange, )
• NewsWatch Information filtering of news articles

5
TOSHIBA NLP RD activities 3/3

• Speech processing
• Speech synthesis Provide human voice quality and
  naturalness, multi-lingual(American English,
  British English, Chinese, Dutch, French, German,
  Italian, Spanish and Japanese), small memory and
  low computational power
• Robust speech recognition High performance
  under noisy environments, multi-lingual
• Japanese speech dictation Speaker independent,
  high recognition rate without enrolment
• Speech processing products
• Middleware for car navigation systems, mobile
  equipments, game software, LaLaVoice(PKG software)

6
Knowledge sharing system
KnowledgeMeisterTM Chishiki-kyouyuu knowledge
sharing

• Features
• NLP based information retrieval
• Hierarchical clustering of accumulated documents
• Categorizing newly input document
• Various functions for knowledge sharing

7
Knowledge sharing system
Questioner
Tell me how to write an equipment plan.
Language/ intention understanding Information re
trieval
Office knowledge
Intranet
Personal know-how
Experienced person
8
Semantic Roles Example 1/2
Examples of search requests from a knowledge
sharing in TOSHIBA corporate RD center (English
translations) When do we have to leave the
dormitory? Who can apply for a child-care
leave? Where can we have Chinese food in
Kawasaki?
Extracted semantic roles time, person, place
9
Semantic Roles Example 2/2

• Example request from customer support
  (English translation)
• I am a dynabook XX user. Ive just pressed the
  power button without shutting it down. Now it
  displays an error message XXX.
• Extracted semantic roles
• Background Action Symptom

10
Insufficiency of the current KM systems

• Treatment of knowledge exchange in human-human
  communication
• Knowledge and information exchanged by e-mail ?
  GroupScribe
• Multi-modal knowledge such as video and speech ?
  MKIDS

11
Convert human-human communication to sharable
knowledge
Sharable knowledge
Communication
Reusable knowledge
E-mail
Interactive e-Learning
Multi-modal knowledge sharing
F2F dialogue
Education
Office
New communication
12
CIKLE Community Knowledge WareCommunity-based
Interactive Knowledge Leveraging Environment

• Drive communication-knowledge cycle
• Extract and leverage knowledge from/through
  communication
• Find and recommend knowledge to activate
  communication

Knowledgebase (Stock-type)
Flow-Stock combination structure
Linkeddocument
Extract / Edit
Messagethread
Extract and leverageknowledge
Bind
Find and recommendknowledge
Comment / Post
Communication (Flow-type)
13
The CIKLE solution delivers

• Collaborative knowledge leveraging
• Edit knowledge with a community consensus
• Create knowledge with dialogue summarization
  engine
• Publish sharable knowledge from even closed
  communities
• Provide dual view knowledge and its context
• Retrieval of relevant knowledge in a natural way
• Accept natural language queries
• Give priority to documents than messages

14
Information extraction (GroupScribe)
Enhancement of the summarization function of CIKLE
15
Rule based extraction

• Surface expressions in each message
• Reference relations between messages

16
Knowledge sharing practice in TOSHIBA corp.
CIKLE 07/2000 05/2003 CIKLEgs 05/2003
17
Multi-modal knowledge sharing system (MKIDS)
Experienced person (Answerer)
Questioner
How should I do to manage the when ?? ?
The way of managing is
How should I do to manage the when ?? ?
The way of managing is
?
Question and Answer
?
?
Retrieval and reuse of the accumulated knowledge

• Accumulation of the answering video image
• Refinement of the knowledge

Knowledge DB
???????
??? R2-5 ??? ?
Authoring tool
18
Multi-modal knowledge sharing
Questioners side
Answerers side
19
System configuration
Answerer side Media capture
Questioner side Media capture
Video dialogue
Semantic role analysis
Authoring tool
Knowledge DB
Native XML database
20
Snapshot of a dialogue
Questioner
Answerer
Ano kikitai no desuga (Ur, I have a question.)
Hai nande shou (Hello! May I help you?)
Semantic role analysis result
2question
2nodding
Speech recognition result
Ano hito no tamedakedo (For that person.)
Haittande nao (Something entered.)
21
Future work

• Application of the systems to several real works
  and the evaluation
• Improvement of the scalability and robustness
• Adoption of more natural language techniques such
  as IE of named entities for generating effective
  summary