Evaluation of Natural Language and Speech Tool for Italian

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.

Inhalt

The EVALITA Dependency Parsing Task: From 2007 to 2011.- Use of Semantic Information in a Syntactic Dependency Parser.- Parsit at Evalita 2011 Dependency Parsing Task.- An Ensemble Model for the EVALITA 2011 Dependency Parsing Task.- Tuning DeSR for Dependency Parsing of Italian.- Domain Adaptation for Dependency Parsing at Evalita 2011.- Experiments in Newswire-to-Law Adaptation of Graph-Based Dependency Parsers.- Domain Adaptation by Active Learning.- Named Entity Recognition on Transcribed Broadcast News at EVALITA 2011.- A Simple Yet Effective Approach for Named Entity Recognition from Transcribed Broadcast News.- The Tanl Tagger for Named Entity Recognition on Transcribed Broadcast News at Evalita 2011.- The News People Search Task at EVALITA 2011: Evaluating Cross-Document Coreference Resolution of Named Person Entities in Italian News.- Exploiting Background Knowledge for Clustering Person Names.- Description and Results of the SuperSense Tagging Task.- Super-Sense Tagging Using Support Vector Machines and Distributional Features.- Generative and Discriminative Learning in Semantic Role Labeling for Italian.- Structured Kernel-Based Learning for the Frame Labeling over Italian Texts.- The Lemmatisation Task at the EVALITA 2011 Evaluation Campaign.- The Vocapia Research ASR Systems for Evalita 2011.- The SPPAS Participation to the Forced-Alignment Task.- SAD-Based Italian Forced Alignment Strategies.