-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
International Workshop on Spoken Language Translation (IWSLT 2006)
-- Evaluation Campaign on Spoken Language Translation --
Second Call for Participants / Papers
November 27-28, 2006
Kyoto, Japan
http://www.slc.atr.jp/IWSLT2006
-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
Spoken language translation technologies attempt to cross the language
barriers between people having different native languages who each want
to engage in conversation by using their mother-tongue.
Spoken language translation has to deal with problems of automatic
speech recognition (ASR) and machine translation (MT).
One of the prominent research activities in spoken language translation is
the work being conducted by the Consortium for Speech Translation Advanced
Research (C-STAR III), which is an international partnership of research
laboratories engaged in automatic translation of spoken language. Current
members include ATR (Japan), CAS (China), CLIPS (France), CMU (USA), ETRI
(Korea), ITC-irst (Italy), and UKA (Germany).
A multilingual speech corpus comprised of tourism-related sentences (BTEC*)
has been created by the C-STAR members and parts of this corpus were already
used for previous IWSLT workshops focusing on the evaluation of MT results
based on text input (http://www.slc.atr.jp/IWSLT2004) and the translation
of ASR output (word lattices, N-best lists) using read speech as input
(http://penance.is.cs.cmu.edu/iwslt2005). The full BTEC* corpus consists
of 160K of sentence-aligned text data and parts of the corpus will be
provided to all evaluation campaign participants for training purposes.
In this workshop, we focus on the translation of spontaneous speech which
includes ill-formed utterances due to grammatical incorrectness, incomplete
sentences, and redundant expressions. The impact of spontaneity aspects
on the ASR and MT systems performance as well as the robustness of
state-of-the-art MT engines towards speech recognition errors will be
investigated in detail.
Two types of submissions are invited:
1) participants in the evaluation campaign of spoken language translation
technologies. Each participant in the evaluation campaign is requested
to submit a paper describing the utilized ASR and MT systems and
to report results using the provided test data.
2) technical papers on related issues.
An overview of the evaluation campaign is as follows:
=== Evaluation Campaign
Theme:
* Spontaneous speech translation
Translation Directions:
* Arabic/Chinese/Italian/Japanese into English (AE, CE, IE, JE)
Input Conditions:
* Speech (audio)
* ASR Output (word lattice or N-best list)
* Cleaned Transcripts (text)
Supplied Resources:
* training corpus:
o AE, IE:
+ 20,000 sentence pairs of BTEC*
+ three develop sets (3x500 sentence pairs, 16 multiple
references)
o CE, JE:
+ 40,000 sentence pairs of BTEC*
+ three develop sets (3x500 sentence pairs, 16 multiple
references)
* develop corpus:
o speech data, word lattices, N-best lists of 500 input sentences
with 7 reference translations for each translation direction
and input condition
* test corpus:
o speech data, word lattices, N-best lists of 500 input sentences
for each translation direction and input condition
=> word segmentations will be provided according to the output
of the provided ASR engines
Data Tracks:
The past IWSLT workshop results showed that the amount of BTEC* sentence
pairs used for training largely effects the performance of the MT
systems
on the given task. However, only CSTAR partners have access to the full
BTEC* corpus. In order to allow a fair comparison between the systems,
we decided to distinguish the following two data tracks:
* Open Data Track ("open" for everyone :->)
o no restrictions on training data of ASR engines
o any resources, besides the full BTEC* corpus and proprietary
data,
can be used as the training data of MT engines.
Concerning the BTEC* corpus and proprietary data, only the
Supplied
Resources (see above) are allowed to be used for training
purposes.
* C-STAR Data Track
o no restrictions on training data of ASR engines
o any resources (including the full BTEC* corpus and proprietary
data) can be used as the training data of MT engines.
Evaluation Specification:
* ASR output
o (automatic) WER
* MT output
o (automatic) BLEU(*), NIST, METEOR
o (subjective) fluency(*), adequacy(*)
-> systems will be ranked according to the metrics marked '(*)'
-> human assessment will be carried out for the top-10 systems
(according to the BLEU metric) of the Chinese-to-English
Open Data Track (ASR Output condition).
=== Technical Paper:
The workshop also invites technical papers related to spoken language
translation.
Possible topics include, but are not limited to:
* Spontaneous speech translation
* Domain and language portability
* MT using comparable and non-parallel corpora
* Phrase alignment algorithms
* MT decoding algorithms
* MT evaluation measures
=== Important Dates
+ Evaluation Campaign
April 7, 2006 -- System Registration Open
May 12, 2006 -- Training Corpus Release
June 30, 2006 -- Develop Corpus Release
August 7, 2006 -- Test Corpus Release [00:01 JST]
August 9, 2006 -- Result Submission Due [23:59 JST]
September 15, 2006 -- Result Feedback to Participants 2006
September 29, 2006 -- Paper Submission Due
October 14, 2006 -- Notification of Acceptance
October 27, 2006 -- Camera-ready Submission Due
- system registrations will be accepted until release of
test corpus
- late result submissions will be treated as unofficial
result submissions
+ Technical Papers
September 15, 2006 -- Paper Submission Due [23:59 JST]
October 17, 2006 -- Notification of Acceptance
October 27, 2006 -- Camera-ready Submission Due
=== Application / Submission Guidelines / Updated Information
+ available at http://www.slc.atr.jp/IWSLT2006
=== Organizers
+ Satoshi Nakamura (ATR, Japan; Chair)
+ Herve Blanchon (CLIPS, France)
+ Gianni Lazzari (ITC-irst, Italy)
+ Youngjik Lee (ETRI, Korea)
+ Alex Waibel (CMU, USA / UKA, Germany)
+ Bo Xu (CAS, China)
=== Program Committee
+ Michael Paul (ATR, Japan; Evaluation Campaign Chair)
+ Marcello Federico (ITC-irst, Italy; Technical Paper Chair)
+ Nicola Bertoldi (ITC-irst, Italy)
+ Christian Boitet (CLIPS, France)
+ Genichiro Kikui (NTT, Japan)
+ Kevin Knight (ISI, USA)
+ Phillip Koehn (Univ. of Edinburgh, UK)
+ Sadao Kurohashi (Univ. of Tokyo, Japan)
+ Young-Suk Lee (IBM, USA)
+ Jose B. Marino (UPC, Spain)
+ Arul Menezes (Microsoft, USA)
+ Masaaki Nagata (NTT, Japan)
+ Hermann Ney (RWTH, Germany)
+ Seung-Shin Oh (ETRI, Korea)
+ Wade Shen (MIT, USA)
+ Stephan Vogel (CMU, USA)
+ Andy Way (Dublin City University, Ireland)
+ Chengqing Zong (CAS, China)
=== Local Arrangements
+ Genichiro Kikui (NTT, Japan)
=== Conference Venue
+ Paruru Plaza Kyoto (right in front of Kyoto Station)
=== Supporting Organizations
+ Advanced Telecommunication Research Institute International (ATR)
+ Association for Computational Linguistics (ACL)
+ Center for the Evaluation of Language and Communication Technologies
(Celct)
+ European Language Resources Association (ELRA)
+ International Speech Communication Association (ISCA)
=== Contact
Michael Paul
e-mail: michael.paul@atr.jp
ATR Spoken Language Communication Research Laboratories
2-2-2 Hikaridai, Keihanna Science City, Kyoto 619-0288 Japan
=== References
+ IWSLT 2005 (http://penance.is.cs.cmu.edu/iwslt2005)
+ IWSLT 2004 (http://www.slc.atr.jp/IWSLT2004)
+ C-STAR (http://www.c-star.org/)
-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
This archive was generated by hypermail 2b29 : Fri Jun 23 2006 - 17:15:17 MET DST