Multi-perspective evaluation of the FAME speech-to-speech translation system for Catalan, English and Spanish

Kapitel in diesem Buch

1. Prelim pages i
2. Table of contents v
3. Editors' Foreword ix
4. Part I. Computation for linguistics
5. Linguistic challenges for computationalists 1
6. Part II. Information extraction & indexing
7. NLP: An information extraction perspective 17
8. Semantic indexing using minimum redundancy cut in ontologies 25
9. Indexing and querying linguistic metadata and document content 35
10. Term representation with Generalized Latent Semantic Analysis 45
11. Part III. Parsing
12. Multilingual dependency parsing: A pipeline approach 55
13. How does treebank annotation influence parsing? Or how not to compare apples and oranges 79
14. The SenSem project: Syntactico-semantic annotation of sentences in Spanish 89
15. Part IV. Anaphora & referring expressions
16. Generating referring expressions: Past, present and future 99
17. A data-driven approach to pronominal anaphora resolution for German 115
18. Part V. Classification
19. Efficient spam analysis for weblogs through URL segmentation 125
20. Document classification using semantic networks with an adaptive similarity measure 137
21. Text summarization for improved text classification 147
22. Exploiting linguistic cues to classify rhetorical relations 157
23. Part VI. Textual entailment & question answering
24. Tree edit distance for textual entailment 167
25. A genetic algorithm for optimising information retrieval with linguistic features in question answering 177
26. Lexico-syntactic subsumption for textual entailment 187
27. A knowledge-based approach to text-to-text similarity 197
28. Part VII. Ontologies
29. A simple WWW-based method for semantic word class acquisition 207
30. Automatic building of Wordnets 217
31. Part VIII. Machine translation
32. Lexical transfer selection using annotated parallel corpora 227
33. Multi-perspective evaluation of the FAME speech-to-speech translation system for Catalan, English and Spanish 237
34. Parallel corpora for medium density languages 247
35. Part IX. Corpora
36. The role of data in NLP: The case for dataset profiling 259
37. Even very frequent function words do not distribute homogeneously 267
38. Exploiting parallel texts to produce a multilingual sense tagged corpus for word sense disambiguation 277
39. Detecting dangerous coordination ambiguities using word distribution 287
40. List and addresses of contributors 297
41. Index of subjects and terms 303