Welcome to the

1

• Welcome to the
• Center for Language and Speech Processing
• 2007 Summer Workshop
• Sponsored by the newly founded
• Johns Hopkins HLT-CoE
• DARPA and NSF

2
WS2007Fall Planning Session November
3 - 5, 2006 Mt. Washington Conference Center -
Baltimore, MD. 28 attendees from JHU, other
universities, government, industry. Several
Proposals Reviewed in 3 topic areas  MULTIDOCU
MENT, MULTILINGUAL ENTITY DISAMBIGUATION AUTOMAT
IC ADAPTATION OF SPEECH TECHNOLOGY TO NEW
DOMAINS SOCIAL NETWORKS AND LANGUAGE
3
Exploiting Lexical Encyclopedic Resources For
Entity Disambiguation The goal of the workshop
is to further the state of the art in entity
disambiguation by developing better techniques
for tracking entities and for extracting their
properties. A particular focus will be improving
entity tracking by using lexical and encyclopedic
knowledge extracted both from structured lexical
databases and from semi-structured repositories
such as Wikipedia. Lack of such knowledge is one
of the main problems with current entity tracking
methods, which typically cannot detect that 'the
Packwood proposal' and 'the Packwood plan' in the
following example refer to the same
entity.Recovery from Model Inconsistency in
Multilingual Speech RecognitionDuring the 2007
Summer Workshop we intend to focus on detection
and description of out-of-vocabulary and
mispronounced words in the 6 language Call-home
database. Additionally, in order to describe the
suspect parts of the message, we will work on
language-independent recognizer of speech sounds
that could be applied for phonetic transcription
of identified suspect parts of the recognized
message.
4
Participants 28 Total
Participants  12 Senior Researchers from
universities, including JHU10 graduate
students6 undergraduate students  This years
workshop participants are from various parts of
the world. 26 Males, 2 Females
5
Opening Day ProgramOpening remarks 0830
AM - Continental Breakfast 0900 AM -
Welcome, Frederick Jelinek, CLSP/JHU, Chair
WS'07 0910 AM - Remarks from Nick Jones,
Dean, Whiting School of Engineering 0915 AM
- Remarks from Workshop Sponsors 0925 AM -
Preworkshop Activities, Sanjeev Khudanpur
(JHU)Summary of goals and objectives for
teams 0940 AM - Exploiting Lexical
Encyclopedic Resources for Entity
Disambiguation 1010 AM - Discussion and
Questions 1020 AM - Recovering from Model
Inconsistency in Multilingual Speech
Recognition 1050 AM - Discussion and
Questions 1100 AM - Break, Adjourn and
proceed to Shaffer 100 for an Introduction to the
WS07 LaboratoryAdministrative and Technical
workshop information 1115 AM -
Administrative Information and WS07 Staff
Introductions, Monique Folk (CLSP/JHU) 1130
AM - Computing Infrastructure and System Staff
Introduction, Justin Martin and Joshua Paulik
(CLSP/JHU) 1200 PM - Lunch (on your
own) 0130 PM - Team Meetings Barton 114
Recovering from Model Inconsistency in
Multilingual Speech Recognition Shaffer 100
Exploiting Lexical Encyclopedic Resources for
Entity Disambiguation
6

Other WS Activities and Highlights

Tonight, Monday July 16
Opening Picnic 600 p.m.
On the lawn behind Clark Hall
Wednesdays Seminars 1030
a.m. in Shaffer 3 Catered
Lunch Team updates  
Thursdays Undergraduate
brown bag lunches Barton 320
Voluntary Group Dinner various locations  
Fridays Afternoon
Social Wednesday August 22
Closing Presentations
Closing Dinner 700 p.m. Evergreen Carriage
House