Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute...

57
Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University

Transcript of Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute...

Page 1: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

Speech-to-Speech MT in the JANUS System

Lori Levin and Alon Lavie

Language Technologies Institute

Carnegie Mellon University

Page 2: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 2

Outline

• Design and Engineering of the JANUS/C-STAR speech-to-speech MT system– Fundamentals of our approach

– System overview

– Engineering a multi-domain system

• The C-STAR Travel Domain Interlingua (IF)• Evaluation and User Studies• Conclusions, Current and Future Research

Page 3: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 3

JANUS Speech Translation

• Translation via an interlingua representation

• Main translation engine is rule-based

• Semantic grammars

• Modular grammar design

• System engineered for multiple domains

• Incorporate alternative translation engines

Page 4: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 4

Multilingual Interlingual Machine Translation

Page 5: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 5

Advantages of Interlingua

• Avoid the n-sqared problem for all-ways translation.

• Mono-lingual grammar development teams.

• Add a new language easily and automatically get all-ways translation to all previous languages.

Page 6: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 6

The C-STAR Travel Planning Domain

General Scenario:

• Dialogue between one traveler and one or more travel agents

• Focus on making travel arrangements for a personal leisure trip (not business)

• Free spontaneous speech

Page 7: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 7

The C-STAR Travel Planning Domain

Natural breakdown into several sub-domains:

• Hotel Information and Reservation

• Transportation Information and Reservation

• Information about Sights and Events

• General Travel Information

• Cross Domain

Page 8: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 8

A Travel DialogueTranslated from Italian

A: Albergo Gabbia D’Oro. Good evening.

B: My name is Anna Maria DeGasperi. I’m calling from Rome. I wish to book two single rooms.

A: Yes.

B: From Monday to Friday the 18th, I’m sorry, to Monday the 21st.

A: Friday the 18th of June.

B: The 18th of July. I’m sorry.

A: Friday the 18th of July to, you were saying, Sunday.

B: No. Through Monday the 21st.

Page 9: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 9

A Travel Dialogue(Continued)

B: So with departure on Tuesday the 22nd.

A: Then leaving on the 22nd. Yes. We have two singles certainly.

B: Yes.

A: Would you like breakfast?

B: Is it possible to have all meals?

A: No. We serve meals only in the evening.

B: Ok. If you can do breakfast and dinner.

A: Ok.

B: Do you need a deposit?

Page 10: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 10

A Travel Dialogue(Continued)

A: You can give me your credit card number.

B: Ok. Just a moment. Ok. My name is Anna Maria DeGaperi. The card is 005792005792.

A: Good.

B: Expiration 2002.

A: 2002. Good. Thank you. We need a confirmation on the 18th of July before 6pm.

B: Goodbye.

A: Thanks. Goodbye.

B: Thanks. Goodbye.

Page 11: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 11

A Non-Task-Oriented Dialogue(We can’t translate this.)

A: Are you cooking?

B: My father is cooking. I’m cleaning. I just finished cleaning the bathroom.

A: Look. What do you know about Monica?

B: I don’t know anything. Look. I don’t know anything.

A: You don’t know anything? I wrote her three weeks ago, but if she hasn’t received the letter, they would have returned it. I hope she received it.

B: Because Celia told me that the address that Monica had given us was wrong. She said that if I was going to write to her, well, ….

Page 12: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 12

Semantic Grammars

• Describe structure of semantic concepts instead of syntactic constituency of phrases

• Well suited for task-oriented dialogue containing many fixed expressions

• Appropriate for spoken language - often disfluent and syntactically ill-formed

• Faster to develop reasonable coverage for limited domains

Page 13: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 13

Semantic Grammars

Hotel Reservation Example:

Input: we have two hotels available

Parse Tree:

[give-information+availability+hotel]

(we have [hotel-type]

([quantity=] (two)

[hotel] (hotels)

available)

Page 14: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 14

The JANUS-III Translation System

Page 15: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 15

The JANUS-III Translation System

Page 16: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 16

The SOUP Parser

• Specifically designed to parse spoken language using domain-specific semantic grammars

• Robust - can skip over disfluencies in input• Stochastic - probabilistic CFG encoded as a

collection of RTNs with arc probabilities• Top-Down - parses from top-level concepts of the

grammar down to matching of terminals• Chart-based - dynamic matrix of parse DAGs

indexed by start and end positions and head cat

Page 17: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 17

The SOUP Parser

• Supports parsing with large multiple domain grammars

• Produces a lattice of parse analyses headed by top-level concepts

• Disambiguation heuristics rank the analyses in the parse lattice and select a single best path through the lattice

• Graphical grammar editor

Page 18: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 18

SOUP Disambiguation Heuristics

• Maximize coverage (of input)• Minimize number of parse trees (fragmentation)• Minimize number of parse tree nodes• Minimize the number of wild-card matches• Maximize the probability of parse trees• Find sequence of domain tags with maximal

probability given the input words: P(T|W), where T= t1,t2,…,tn is a sequence of domain tags

Page 19: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 19

Modular Grammar Design

• Grammar development separated into modules corresponding to sub-domains (Hotel, Transportation, Sights, General Travel, Cross Domain)

• Shared core grammar for lower-level concepts that are common to the various sub-domains (e.g. times, prices)

• Grammars can be developed independently (using shared core grammar)

• Shared and Cross-Domain grammars significantly reduce effort in expanding to new domains

• Separate grammar modules facilitate associating parses with domain tags - useful for multi-domain integration within the parser

Page 20: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 20

Translation with Multiple Domain Grammars

Page 21: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 21

Analysis with Multiple Domain Grammars

• Parser is loaded with all domain grammars

• Domain tag attached to grammar rules of each domain

• Previously developed grammars for other domains can also be incorporated

• Parser creates a parse lattice consisting of multiple analyses of the input into sequences of top-level domain concepts

• Parser disambiguation heuristics rank the analyses in the parse lattice and select a single best sequence of concepts

Page 22: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 22

A SOUP Parse Lattice

Page 23: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 23

Alternative Analysis Approach: SALT

SALT - Statistical Analyzer for Lang. Translation• Combines ML trainable and rule-based analysis

methods for robustness and portability• Rule-based parsing restricted to well-defined set of

argument-level phrases and fragments• Trainable classifiers (NN, Decision Trees, etc.) used to

derive the DA (speech-act and concepts) from the sequence of argument concepts.

• Phrase-level grammars are more robust and portable to new domains

Page 24: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 24

SALT Approach

• Example:Input: we have two hotels available

Arg-SOUP: [exist] [hotel-type] [available]

SA-Predictor: give-information

Concept-Predictor: availability+hotel

• Predictors using SOUP argument concepts and input words

• Preliminary results are encouraging

Page 25: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 25

Design Criteria of the Interchange Format

• Suitable for task oriented dialogue• Based on speaker’s intent, not literal meaning• Domain independent framework with domain-

specific parts• Simple and reliable enough to use:

– at multiple research sites. – with widely varying type of parsers and

generators

Page 26: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 26

Domain Actions: Extended, Domain-Specific Speech Acts

Examples:

c:request-information+availability+room

a:give-information+personal-data

c:give-information+temporal+arrival

Page 27: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 27

Task Oriented Sentences

• Perform an action in the domain.

• Are not descriptive.

• Contain fixed expressions that cannot be translated literally.

Page 28: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 28

Components of the Interchange Format

speaker a: a: (agent)

speech act give-informationgive-information

concept* +availability+room+availability+room

argument* (room-type=(single & double), (room-type=(single & double), time=md12)time=md12)

Page 29: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 29

Examples no that’s not necessary c:c:negatenegate

yes I am c:c:affirmaffirm

and I was wondering what you have in the way of rooms available during that time c:c:request-informationrequest-information+availability+room+availability+room

my name is alex waibel c:c:give-informationgive-information+personal-data+personal-data (person-name=(given-name=alex, family-(person-name=(given-name=alex, family-

name=waibel))name=waibel))

and how will you be paying for this a:a:request-informationrequest-information+payment+payment (method=question(method=question))

I have a mastercard c:c:give-informationgive-information+payment+payment (method=mastercard)(method=mastercard)

Page 30: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 30

Speaker Tag

Client says: Do you take credit cards?

c:request-information+payment (method=credit-card)

Agent says: Will you be paying with a credit card?

a:request-information+payment (method=credit-card)

Page 31: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 31

Size of IF

May 1999

Speech acts 54 Concepts 84 Arguments 118

Page 32: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 32

Speech Acts

acceptacknowledgeacknowledge-actionaffirmaffirm-actionapologizeclosingdelay-actionend-actiongive-certaintygive-information

I’ll take that, Sounds goodOkay, Sure, YeahHere you go, This is itYes, That is correctYes, please do, Go aheadSorry, I’m sorryBye, See you next weekI’ll get back to you on thatThat’s all for nowI’m sureI have 2 singles available

Page 33: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 33

Speech Acts

greetinggreeting-nice-meetgreeting-requestgreeting-response-badgreeting-response-goodgreeting-welcomeintroduce-selfintroduce-topicnegatenegate-actionnot-understand

Hello, Good morningNice to meet youHow are youI’m not goodI’m fineWelcome to PittsburghThis is Brian, Best WesternAbout that flight…NoNo, don’tI don’t understand

Page 34: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 34

Speech Acts offeroffer-informationoffer-repeatplease-waitreject (e.g., offer)

request-actionrequest-affirmationrequest-certaintyrequest-delay-actionrequest-informationrequest-introduce-self

How about it?Let me get you the informationLet me repeat thatJust a minute, Let me seeNo, I don’t want thatCan you reserve that for me?Is that correct?Are you sure?Can I get back to you later?Do you accept visa?Who am I speaking with?

Page 35: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 35

Speech Acts request-knowledgerequest-neg-affirmationrequest-repeatrequest-suggestionrequest-verificationreturn-from-delaysuggestthankverifywelcomex-exclamation

Do you know?Is that bad?Could you repeat that?Which hotel should I get?Right?, That was 40 dollars?I’m backHow about a single?Thank you very muchYes, that is 40 dollars.You’re welcomeThat is beautiful! (ETRI only)

Page 36: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 36

Meta-Demo Speech acts

testing

testing-problem

testing-start

testing-stop

testing-proceed

testing-request-proceed

testing-ready

testing-present

testing-request-present

Testing 1 2 3, This is a test

We have a problem

Let’s start

Let’s stop

Go ahead!

Would you go first

Ready here

We are here, CMU is on line

Are you there?

Page 37: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 37

Some Concepts

• Actions: change, reservation, confirmation, cancellation, help, purchase, view, display, preference

• Attributes: availability, price, temporal, price, location, size, features etc.

• Objects: room, hotel, flight, tour, event, attraction, web-page etc.

• Other: arrival, departure, numeral, expiration-date, payment

Page 38: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 38

Using Concepts to Represent Information Focus

Is there a hotel in Pittsburgh?

c:request-information+availability+hotel (location=pittsburgh)

Is the hotel in Pittsburgh?

c:request-information+location+hotel (location=pittsburgh)

Page 39: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 39

Topic vs Focus

The Hilton Hotel is in Verona.

a:give-information+location+hotel

(hotel-name=hilton, location=verona)

The hotel in Verona is the Hilton Hotel.

a:give-information+location+hotel

(hotel-name=hilton, location=verona)

Page 40: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 40

The Interchange Format Database

61.2.3 olang I lang I Prv IRST “telefono per prenotare delle stanze per quattro colleghi”

61.2.3 olang I lang E Prv IRST “I’m calling to book some rooms for four colleagues”

61.2.3 IF Prv IRST c:request-action+reservation+features+room (for-whom= (associate, quantity=4))

61.2.3 comments: dial-oo5-spkB-roca0-02-3

d.u.sdu olang X lang Y Prv Z “sdu-in-language-Y on one line”d.u.sdu olang X lang E Prv Z “sdu-in-English on one line”d.u.sdu IF Prv Z dialogue-act-on-one-lined.u.asdu comments: your commentsd.u.asdu comments: go here

Page 41: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 41

The Interchange Format Database

English Dialogues

English Sentences

Korean Dialogues

Korean Sentences

Italian Dialogues

Italian Sentences

Japanese Dialogues

Japanese Utterances

Distinct Dialogue Acts

36

2466

70

1142

5

233

124

5887

554 (310 agent, 244 client)

Page 42: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 42

Phenomena Not Covered

Relative Clauses

Plurality

Descriptive Sentences

Scope (negation and modifiers)

Comparative Constructions

Anaphora

Page 43: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 43

Expressivity vs Simplicity

• If it is not expressive enough, components of meaning will be lost.

• If it is not simple enough, it can’t be used reliably across sites.

Page 44: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 44

Coverage

• The database includes about 550 distinct dialogue acts.

• About 60 dialogue acts cover about 70% of the data.

• About 5% of unseen data wasn’t covered (as judged by human experts)

Page 45: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 45

Consistency of Use Across Sites

• Successful international demo.

• After testing English-Italian and English-Korean, Italian-Korean worked without extra effort.

• Inter-coder agreement for each component of IF individually (speech acts, concepts, arguments) around 85%

• Cross-site evaluation same as intra-site evaluation: 60% spoken; 75% transcribed.

Page 46: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 46

User Studies• We conducted three sets of user tests• Travel agent played by experienced system user• Traveler is played by a novice and given five

minutes of instruction• Traveler is given a general scenario - e.g., plan a trip

to Heidelberg• Communication only via ST system, multi-modal

interface and muted video connection • Data collected used for system evaluation, error

analysis and then grammar development

Page 47: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 47

Evaluations

• Accuracy Based Evaluation– Translation preserves original meaning

• Task Based Evaluation– goal success or failure– user effort: how many attempts before

succeeding or giving up

Page 48: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 48

Accuracy Based Evaluation

• End-to-end evaluations conducted at the SDU (sentence) level

• Multiple bilingual graders compare the input with translated output and assign a grade of: Perfect, OK or Bad

• OK = meaning of SDU comes across• Perfect = OK + fluent output• Bad = translation incomplete or incorrect

Page 49: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 49

Task Based Evaluation

I would like to reserve #1s a single room #2frequest-action+reservation+hotel (room-type=single)

Translation: I would like to reserve a seating room.

Page 50: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 50

Task Based Evaluation

Scoring Scheme:For goals that succeed: 1/n

For goals that fail: -(1-1/n)

where n is the number of attempts

Overall score: average for all goals

Page 51: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 51

August-99 Evaluation

• Data from latest user study - traveler planning a trip to Japan

• 132 utterances containing one or more SDUs, from six different users

• SR word error rate 14.7%

• 40.2% of utterances contain recognition error(s)

Page 52: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 52

Accuracy and Task Based Evaluations

Agent Traveler All

ABE 58.7% 44.7% 51.8%

TBE score .75 .56 .65

TBEsuccess

82.8% 64.7% 73.8%

Page 53: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 53

Accuracy Based Evaluation

Method OutputLanguage

PercentAcceptable

Grader Number ofGraders

1. Speech Rec. English 78% CMU 32. Transcr. English 74% CMU 33. Rec. English 59% CMU 34. Transcr. Japanese 77% CMU 25. Rec. Japanese 62% CMU 26. Transcr. German 70% CMU 27. Rec. German 58% CMU 28. Transcr. German 67% IRST 29. Rec. German 59% IRST 210. Transcr. Italian 73% IRST 611. Rec. Italian 61% IRST 6

Page 54: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 54

Evaluation - Progress Over Time

Method OK+Perfect Perfect

Jan-99 Transcribed 69% 46%

Apr-99 Transcribed 70% 49%

Aug-99 Transcribed 74% 54%

Jan-99 Recognition 55% 36%

Apr-99 Recognition 57% 38%

Aug-99 Recognition 59% 42%

Page 55: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 55

Current and Future Work• Expanding the travel domain: covering descriptive

as well as task-oriented sentences• Development of the SALT statistical approach and

expanding it to other domains• Full integration of multiple MT approaches:

SOUP, SALT, Pangloss• Disambiguation: improved sentence-level

disambiguation; applying discourse contextual information for disambiguation

Page 56: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 56

Conclusions• We started skeptically with tools that we thought

were too simple: context-free parser, semantic grammar, interlingua based on domain actions.

• We were surprised that they worked adequately for some types of task oriented dialogue.

• We improved portability.• We are now working on embedding the simple

task-oriented system into a more complete system.

Page 57: Speech-to-Speech MT in the JANUS System Lori Levin and Alon Lavie Language Technologies Institute Carnegie Mellon University.

4/24/00 UMD Seminar 57

The JANUS/C-STAR Team

• Project Leaders: Lori Levin, Alon Lavie, Monika Woszczyna, Alex Waibel

• Grammar and Component Developers: Donna Gates, Dorcas Wallace, Taro Watanabe, Boris Bartlog, Ariadna Font-Llitjos, Marsal Gavalda,Chad Langley, Marcus Munk, Klaus Ries, Klaus Zechner,Detlef Koll, Michael Finke, Eric Carraux, Celine Morel,Alexandra Slavkovic, Susie Burger, Laura Tomokiyo,Takashi Tomokiyo, Kavita Thomas, Mirella Lapata,Matthew Broadhead, Cortis Clark, Christie Watson,Daniella Mueller, Sondra Ahlen