Ebook: Evaluation of Natural Language and Speech Tools for Italian: International Workshop, EVALITA 2011, Rome, January 24-25, 2012, Revised Selected Papers

EVALITA (http://www.evalita.it/) is the reference evaluation campaign of both Natural Language Processing and Speech Technologies for the Italian language. The objective of the shared tasks proposed at EVALITA is to promote the development of language technologies for Italian, providing a common framework where different systems and approaches can be evaluated and compared in a consistent manner. This volume collects the final and extended contributions presented at EVALITA 2011, the third edition of the evaluation campaign. The 36 revised full papers were carefully reviewed and selected from a total of 87 submissions. The papers are organized in topical sections roughly corresponding to evaluation tasks: parsing - dependency parsing track, parsing - constituency parsing track, domain adaptation for dependency parsing, named entity recognition on transcribed broadcast news, cross-document coreference resolution of named person entities, anaphora resolution, supersense tagging, frame labeling over italian texts, lemmatisation, automatic speech recognition - large vocabulary transcription, forced alignment on spontaneous speech.

---

EVALITA (http://www.evalita.it/) is the reference evaluation campaign of both Natural Language Processing and Speech Technologies for the Italian language. The objective of the shared tasks proposed at EVALITA is to promote the development of language technologies for Italian, providing a common framework where different systems and approaches can be evaluated and compared in a consistent manner. This volume collects the final and extended contributions presented at EVALITA 2011, the third edition of the evaluation campaign. The 36 revised full papers were carefully reviewed and selected from a total of 87 submissions. The papers are organized in topical sections roughly corresponding to evaluation tasks: parsing - dependency parsing track, parsing - constituency parsing track, domain adaptation for dependency parsing, named entity recognition on transcribed broadcast news, cross-document coreference resolution of named person entities, anaphora resolution, supersense tagging, frame labeling over italian texts, lemmatisation, automatic speech recognition - large vocabulary transcription, forced alignment on spontaneous speech.

---

EVALITA (http://www.evalita.it/) is the reference evaluation campaign of both Natural Language Processing and Speech Technologies for the Italian language. The objective of the shared tasks proposed at EVALITA is to promote the development of language technologies for Italian, providing a common framework where different systems and approaches can be evaluated and compared in a consistent manner. This volume collects the final and extended contributions presented at EVALITA 2011, the third edition of the evaluation campaign. The 36 revised full papers were carefully reviewed and selected from a total of 87 submissions. The papers are organized in topical sections roughly corresponding to evaluation tasks: parsing - dependency parsing track, parsing - constituency parsing track, domain adaptation for dependency parsing, named entity recognition on transcribed broadcast news, cross-document coreference resolution of named person entities, anaphora resolution, supersense tagging, frame labeling over italian texts, lemmatisation, automatic speech recognition - large vocabulary transcription, forced alignment on spontaneous speech.
Content:
Front Matter....Pages -
The EVALITA Dependency Parsing Task: From 2007 to 2011....Pages 1-12
Use of Semantic Information in a Syntactic Dependency Parser....Pages 13-20
Parsit at Evalita 2011 Dependency Parsing Task....Pages 21-29
An Ensemble Model for the EVALITA 2011 Dependency Parsing Task....Pages 30-36
Tuning DeSR for Dependency Parsing of Italian....Pages 37-45
Looking Back to the EVALITA Constituency Parsing Task: 2007-2011....Pages 46-57
Domain Adaptation for Dependency Parsing at Evalita 2011....Pages 58-69
Experiments in Newswire-to-Law Adaptation of Graph-Based Dependency Parsers....Pages 70-76
Domain Adaptation by Active Learning....Pages 77-85
Named Entity Recognition on Transcribed Broadcast News at EVALITA 2011....Pages 86-97
A Simple Yet Effective Approach for Named Entity Recognition from Transcribed Broadcast News....Pages 98-106
A Combination of Classifiers for Named Entity Recognition on Transcription....Pages 107-115
The Tanl Tagger for Named Entity Recognition on Transcribed Broadcast News at Evalita 2011....Pages 116-125
The News People Search Task at EVALITA 2011: Evaluating Cross-Document Coreference Resolution of Named Person Entities in Italian News....Pages 126-134
Exploiting Background Knowledge for Clustering Person Names....Pages 135-145
Evalita 2011: Anaphora Resolution Task....Pages 146-155
UNIPI Participation in the Evalita 2011 Anaphora Resolution Task....Pages 156-165
Description and Results of the SuperSense Tagging Task....Pages 166-175
Super-Sense Tagging Using Support Vector Machines and Distributional Features....Pages 176-185
SuperSense Tagging with a Maximum Entropy Markov Model....Pages 186-194
Two Level Approach to SRL....Pages 195-204
Generative and Discriminative Learning in Semantic Role Labeling for Italian....Pages 205-211
Structured Kernel-Based Learning for the Frame Labeling over Italian Texts....Pages 212-219
The Lemmatisation Task at the EVALITA 2011 Evaluation Campaign....Pages 220-229
Italian Lemmatization by Rules with Getaruns....Pages 230-238
Data Driven Lemmatization and Parsing of Italian....Pages 239-248
The Tanl Lemmatizer Enriched with a Sequence of Cascading Filters....Pages 249-256
The AnIta-Lemmatiser: A Tool for Accurate Lemmatisation of Italian Texts....Pages 257-265
The Vocapia Research ASR Systems for Evalita 2011....Pages 266-273
The FBK ASR System for Evalita 2011....Pages 274-285
EVALITA 2011: Forced Alignment Task....Pages 286-294
The SPPAS Participation to the Forced-Alignment Task of Evalita 2011....Pages 295-304
SAD-Based Italian Forced Alignment Strategies....Pages 305-311
UNINA System for the EVALITA 2011 Forced Alignment Task....Pages 312-321
Back Matter....Pages 322-329
....Pages 330-337