Proceedings of the Linguistic Annotation Workshop, 2007
... Multiple-step treebank conversion: from dependency to Penn format Cristina Bosco Dipartimento... more ... Multiple-step treebank conversion: from dependency to Penn format Cristina Bosco Dipartimento di Informatica, Universit`a di Torino Corso Svizzera 185 10149 Torino - Italia bosco@di.unito. it Abstract ... Proc. of LREC '06 F. Barsotti and R. Basili et al. 2001. ...
Proceedings of 12th European Summer School in …, 2000
... Building a Syntactically Annotated Corpus: the Praga De-pendency Treebank Issues of Valency .... more ... Building a Syntactically Annotated Corpus: the Praga De-pendency Treebank Issues of Valency ... Lombardo, V., Bosco, C., Vassallo, D., Lesmo, L., Treebank annotation and psycholinguistic ... 1993] Marcus, MP, Santorini, B., Marcinkiewicz, MA, Building a Large Annotated Corpus ...
... Cristina Bosco Dipartimento di Informatica Universitá di Torino Corso Svizzera 185 I-10149 To... more ... Cristina Bosco Dipartimento di Informatica Universitá di Torino Corso Svizzera 185 I-10149 Torino, Italy bosco@di.unito.it ... Grammatical relations (aka grammatical functions or thematic roles) encode the associations between the semantic predicate argument structures and their ...
Abstract In this paper we describe our current work on Senti–TUT, a novel Italian corpus for sent... more Abstract In this paper we describe our current work on Senti–TUT, a novel Italian corpus for sentiment analysis. This resource includes annotations concerning both sentiment and morpho-syntax, in order to make available several possibilities of further exploitation ...
The paper proposes a new evaluation exercise, meant to shed light on the syntax-semantics interfa... more The paper proposes a new evaluation exercise, meant to shed light on the syntax-semantics interface for the analysis of written Italian and resulting from the combination of the EVALITA 2014 dependency parsing and event extraction tasks. It aims at investigating the cross-fertilization of tasks, generating a new resource combining dependency and event annotations, and devising metrics able to evaluate the applicative impact of the achieved results.
The Italian discourse marker ‘allora’ ('then ') is investigated in various types of inter... more The Italian discourse marker ‘allora’ ('then ') is investigated in various types of interactions. The aim of the study is to check possible correlations between the discourse marker’s pragmatic functions (at the interactional, metatextual, and cognitive level), its semantic values (which may be consequential or correlative), and factors such as the goal of the interaction and conversational roles. All these elements are considered as acting together, and generating a 'global configuration ' of ‘allora’ in a given context. Data taken from a variety of corpora (documenting formal and informal settings) confirm the hypothesis of a tight relationship between the use of the discourse marker and the factors explicitly considered here, i.e. goal of the interaction and conversational roles. At the same time, the analysis shows the relevance of further factors such as the formal-informal parameter, the amount of interaction and negotiation, and the presence/absence of the int...
Semantic Processing of Legal Texts (SPLeT-2012) Workshop Programme
The 4th Workshop on “Semantic Processing of Legal Texts”(SPLeT–2012) presents the first multiling... more The 4th Workshop on “Semantic Processing of Legal Texts”(SPLeT–2012) presents the first multilingual shared task on Dependency Parsing of Legal Texts. In this paper, we define the general task and its internal organization into sub–tasks, describe the datasets and the domain–specific linguistic peculiarities characterizing them. We finally report the results achieved by the participating systems, describe the underlying approaches and provide a first analysis of the final test results. Keywords: Domain Adaptation, Dependency ...
As the interest of the NLP community grows to develop several treebanks also for languages other ... more As the interest of the NLP community grows to develop several treebanks also for languages other than English, we observe efforts towards evaluating the impact of different annotation strategies used to represent particular languages or with reference to particular tasks. This paper contributes to the debate on the influence of resources used for the training and development on the performance of parsing systems. It presents a comparative analysis of the results achieved by three different dependency parsers developed and tested with ...
In the recent research work on multi-media corpora the notion of context appears to be crucial bo... more In the recent research work on multi-media corpora the notion of context appears to be crucial both on the theoretical level and the applied level. The aim of this paper is to analyze the three levels which are relevant to the treatment of contextual information in multi-media corpora (i.e. annotation, storage, retrieval), and the different solutions which are resorted to in recently implemented systems to meet the need for a multi-layered, multi-linked annotation, and a hierarchically organized retrieval of contextual data.
Proceedings of the Linguistic Annotation Workshop, 2007
... Multiple-step treebank conversion: from dependency to Penn format Cristina Bosco Dipartimento... more ... Multiple-step treebank conversion: from dependency to Penn format Cristina Bosco Dipartimento di Informatica, Universit`a di Torino Corso Svizzera 185 10149 Torino - Italia bosco@di.unito. it Abstract ... Proc. of LREC '06 F. Barsotti and R. Basili et al. 2001. ...
Proceedings of 12th European Summer School in …, 2000
... Building a Syntactically Annotated Corpus: the Praga De-pendency Treebank Issues of Valency .... more ... Building a Syntactically Annotated Corpus: the Praga De-pendency Treebank Issues of Valency ... Lombardo, V., Bosco, C., Vassallo, D., Lesmo, L., Treebank annotation and psycholinguistic ... 1993] Marcus, MP, Santorini, B., Marcinkiewicz, MA, Building a Large Annotated Corpus ...
... Cristina Bosco Dipartimento di Informatica Universitá di Torino Corso Svizzera 185 I-10149 To... more ... Cristina Bosco Dipartimento di Informatica Universitá di Torino Corso Svizzera 185 I-10149 Torino, Italy bosco@di.unito.it ... Grammatical relations (aka grammatical functions or thematic roles) encode the associations between the semantic predicate argument structures and their ...
Abstract In this paper we describe our current work on Senti–TUT, a novel Italian corpus for sent... more Abstract In this paper we describe our current work on Senti–TUT, a novel Italian corpus for sentiment analysis. This resource includes annotations concerning both sentiment and morpho-syntax, in order to make available several possibilities of further exploitation ...
The paper proposes a new evaluation exercise, meant to shed light on the syntax-semantics interfa... more The paper proposes a new evaluation exercise, meant to shed light on the syntax-semantics interface for the analysis of written Italian and resulting from the combination of the EVALITA 2014 dependency parsing and event extraction tasks. It aims at investigating the cross-fertilization of tasks, generating a new resource combining dependency and event annotations, and devising metrics able to evaluate the applicative impact of the achieved results.
The Italian discourse marker ‘allora’ ('then ') is investigated in various types of inter... more The Italian discourse marker ‘allora’ ('then ') is investigated in various types of interactions. The aim of the study is to check possible correlations between the discourse marker’s pragmatic functions (at the interactional, metatextual, and cognitive level), its semantic values (which may be consequential or correlative), and factors such as the goal of the interaction and conversational roles. All these elements are considered as acting together, and generating a 'global configuration ' of ‘allora’ in a given context. Data taken from a variety of corpora (documenting formal and informal settings) confirm the hypothesis of a tight relationship between the use of the discourse marker and the factors explicitly considered here, i.e. goal of the interaction and conversational roles. At the same time, the analysis shows the relevance of further factors such as the formal-informal parameter, the amount of interaction and negotiation, and the presence/absence of the int...
Semantic Processing of Legal Texts (SPLeT-2012) Workshop Programme
The 4th Workshop on “Semantic Processing of Legal Texts”(SPLeT–2012) presents the first multiling... more The 4th Workshop on “Semantic Processing of Legal Texts”(SPLeT–2012) presents the first multilingual shared task on Dependency Parsing of Legal Texts. In this paper, we define the general task and its internal organization into sub–tasks, describe the datasets and the domain–specific linguistic peculiarities characterizing them. We finally report the results achieved by the participating systems, describe the underlying approaches and provide a first analysis of the final test results. Keywords: Domain Adaptation, Dependency ...
As the interest of the NLP community grows to develop several treebanks also for languages other ... more As the interest of the NLP community grows to develop several treebanks also for languages other than English, we observe efforts towards evaluating the impact of different annotation strategies used to represent particular languages or with reference to particular tasks. This paper contributes to the debate on the influence of resources used for the training and development on the performance of parsing systems. It presents a comparative analysis of the results achieved by three different dependency parsers developed and tested with ...
In the recent research work on multi-media corpora the notion of context appears to be crucial bo... more In the recent research work on multi-media corpora the notion of context appears to be crucial both on the theoretical level and the applied level. The aim of this paper is to analyze the three levels which are relevant to the treatment of contextual information in multi-media corpora (i.e. annotation, storage, retrieval), and the different solutions which are resorted to in recently implemented systems to meet the need for a multi-layered, multi-linked annotation, and a hierarchically organized retrieval of contextual data.
Uploads