260 likes | 384 Vues
This study presents a robust and portable analyzer specifically designed for task-oriented human-to-human speech, focusing on parsing utterances into Interlingua representations. Initially relying on full semantic grammars, we now enhance portability to various domains using a hybrid approach that combines grammar-based parsing and machine learning. The system utilizes semantic dialog units (SDUs) to train classifiers for identifying domain actions. Evaluation results indicate effective classification accuracy and highlight the system's capability to adapt to medical assistance contexts.
E N D
Parsing into the Interlingua Using Phrase-Level Grammars and Trainable Classifiers Alon Lavie, Chad Langley, Lori Levin, Dorcas Wallace,Donna Gates and Kay Peterson AFRL Visit, March 28, 2003
Our Parsing and Analysis Approach • Goal: A portable and robust analyzer for task-oriented human-to-human speech, parsing utterances into interlingua representations • Our earlier systems used full semantic grammars to parse complete DAs • Useful for parsing spoken language in restricted domains • Difficult to port to new domains • Current focus is on improving portability to new domains (and new languages) • Approach: Continue to use semantic grammars to parse domain-independent phrase-level arguments and train classifiers to identify DAs AFRL Visit
Interchange Format • Interchange Format (IF) is a shallow semantic interlingua for task-oriented domains • Utterances represented as sequences of semantic dialog units (SDUs) • IF representation consists of four parts • Speaker • Speech Act • Concepts • Arguments speaker : speech act +concept* +arguments* } Domain Action AFRL Visit
Hybrid Analysis Approach Use a combination of grammar-based phrase-level parsing and machine learning to produce interlingua (IF) representations AFRL Visit
Hybrid Analysis Approach Hello. I would like to take a vacation in Val di Fiemme. c:greeting (greeting=hello) c:give-information+disposition+trip (disposition=(who=i, desire), visit-spec=(identifiability=no, vacation), location=(place-name=val_di_fiemme)) AFRL Visit
Argument Parsing • Parse utterances using phrase-level grammars • SOUP Parser (Gavaldà, 2000): Stochastic, chart-based, top-down robust parser designed for real-time analysis of spoken language • Separate grammars based on the type of phrases that the grammar is intended to cover AFRL Visit
Domain Action Classification • Identify the DA for each SDU using trainable classifiers • Two TiMBL (k-NN) classifiers • Speech act • Concept sequence • Binary features indicate presence or absence of arguments and pseudo-arguments AFRL Visit
Using the IF Specification • Use knowledge of the IF specification during DA classification • Ensure that only legal DAs are produced • Guarantee that the DA and arguments combine to form a valid IF representation • Strategy: Find the best DA that licenses the most arguments • Trust parser to reliably label arguments • Retaining detailed argument information is important for translation AFRL Visit
Evaluation: Classification Accuracy • 20-fold cross-validation using the NESPOLE! travel domain database The database: Most Frequent Class: AFRL Visit
Evaluation: Classification Accuracy Classification Performance Accuracy AFRL Visit
Evaluation:End-to-End Translation • English-to-English and English-to-Italian • Training set: ~8000 SDUs from NESPOLE! • Test set: 2 dialogs, only client utterances • Uses IF specification fallback strategy • Three graders, bilingual English/Italian speakers • Each SDU graded as perfect, ok, bad, very bad • Acceptable translation = perfect+ok • Majority scores AFRL Visit
Evaluation:End-to-End Translation AFRL Visit
Evaluation:Data Ablation Experiment AFRL Visit
Domain Portability • Experimented with porting to a medical assistance domain in NESPOLE! • Initial medical domain system up and running, with reasonable coverage of flu-like symptoms and chest pain • Porting the interlingua, grammars and modules for English, German and Italian required about 6 person months in total • Interlingua development: ~180 hours • Interlingua annotation: ~200 hours • Analysis grammars, training: ~250 hours • Generation development: ~250 hours AFRL Visit
New Development Tools AFRL Visit
Questions? AFRL Visit
Grammars • Argument grammar • Identifies arguments defined in the IF s[arg:activity-spec=] (*[object-ref=any] *[modifier=good] [biking]) • Covers "any good biking", "any biking", "good biking", "biking", plus synonyms for all 3 words • Pseudo-argument grammar • Groups common phrases with similar meanings into classes s[=arrival=] (*is *usually arriving) • Covers "arriving", "is arriving", "usually arriving", "is usually arriving", plus synonyms AFRL Visit
Grammars • Cross-domain grammar • Identifies simple domain-independent DAs s[greeting] ([greeting=first_meeting] *[greet:to-whom=]) • Covers "nice to meet you", "nice to meet you donna", "nice to meet you sir", plus synonyms • Shared grammar • Contains low-level rules accessible by all other grammars AFRL Visit
Segmentation • Identify SDU boundaries between argument parse trees • Insert a boundary if either parse tree is from cross-domain grammar • Otherwise, use a simple statistical model AFRL Visit
Using the IF Specification • Check if the best speech act and concept sequence form a legal IF • If not, test alternative combinations of speech acts and concept sequences from ranked set of possibilities • Select the best combination that licenses the most arguments • Drop any arguments not licensed by the best DA AFRL Visit
Grammar Development and Classifier Training • Four steps • Write argument grammars • Parse training data • Obtain segmentation counts • Train DA classifiers • Steps 2-4 are automated to simplify testing new grammars • Translation servers include a development mode for testing new grammars AFRL Visit
Evaluation:IF Specification Fallback • 182 SDUs required classification • 4% had illegal DAs • 29% had illegal IFs • Mean arguments per SDU: 1.47 AFRL Visit
Evaluation:Data Ablation Experiment • 16-fold cross validation setup • Test set size (# SDUs): 400 • Training set sizes (# SDUs): 500, 1000, 2000, 3000, 4000, 5000, 6009 (all data) • Data from previous C-STAR system • No use of IF specification AFRL Visit
Future Work • Alternative segmentation models, feature sets, and classification methods • Multiple argument parses • Evaluate portability and robustness • Collect dialogues in a new domain • Create argument and full DA grammars for a small development set of dialogues • Assess portability by comparing grammar development times and examining grammar reusability • Assess robustness by comparing performance on unseen data AFRL Visit
References • Cattoni, R., M. Federico, and A. Lavie. 2001. Robust Analysis of Spoken Input Combining Statistical and Knowledge-Based Information Sources. In Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, Trento, Italy. • Daelemans, W., J. Zavrel, K. van der Sloot, and A. van den Bosch. 2000. TiMBL: Tilburg Memory Based Learner, version 3.0, Reference Guide. ILK Technical Report 00-01. http://ilk.kub.nl/~ilk/papers/ilk0001.ps.gz • Gavaldà, M. 2000. SOUP: A Parser for Real-World Spontaneous Speech. In Proceedings of the IWPT-2000, Trento, Italy. • Gotoh, Y. and S. Renals. Sentence Boundary Detection in Broadcast Speech Transcripts. 2000. In Proceedings on the International Speech Communication Association Workshop: Automatic Speech Recognition: Challenges for the New Millennium, Paris. • Lavie, A., F. Metze, F. Pianesi, et al. 2002. Enhancing the Usability and Performance of NESPOLE! – a Real-World Speech-to-Speech Translation System. In Proceedings of HLT-2002, San Diego, CA. AFRL Visit
References • Lavie, A., C. Langley, A. Waibel, et al. 2001. Architecture and Design Considerations in NESPOLE!: a Speech Translation System for E-commerce Applications. In Proceedings of HLT-2001, San Diego, CA. • Lavie, A., D. Gates, N. Coccaro, and L. Levin. 1997. Input Segmentation of Spontaneous Speech in JANUS: a Speech-to-speech Translation System. In Dialogue Processing in Spoken Language Systems: Revised Papers from ECAI-96 Workshop, E. Maier, M. Mast, and S. Luperfoy (eds.), LNCS series, Springer Verlag. • Lavie, A. 1996. GLR*: A Robust Grammar-Focused Parser for Spontaneously Spoken Language. PhD dissertation, Technical Report CMU-CS-96-126, Carnegie Mellon University, Pittsburgh, PA. • Munk, M. 1999. Shallow Statistical Parsing for Machine Translation. Diploma Thesis, Karlsruhe University. • Stevenson, M. and R. Gaizauskas. Experiments on Sentence Boundary Detection. 2000. In Proceedings of ANLP and NAACL-2000, Seattle. • Woszczyna, M., M. Broadhead, D. Gates, et al. 1998. A Modular Approach to Spoken Language Translation for Large Domains. In Proceedings of AMTA-98, Langhorne, PA. AFRL Visit