Fabio Massimo Zanzotto

Terminology Extraction: An Analysis of Linguistic and Statistical Approaches

Are linguistic properties and behaviors important to recognize terms? Are statistical measures effective to extract terms? Is it possible to capture a sort of termhood with computation linguistic techniques? Or maybe, terms are too much sensitive to exogenous and pragmatic factors that cannot be confined in computational linguistic? All these questions are still open. This study tries to contribute in the search of an answer, with the belief that it can be found only through a careful experimental analysis of real case studies and a study of their correlation with theoretical insights.

Building the Italian Syntactic-Semantic Treebank

The paper reports on the design and construction of a multi-layered corpus of Italian, annotated at the syntactic and lexico-semantic levels, whose development is supported by dedicated software augmented with an intelligent interface. The issue of evaluating this type of resource is also addressed.

A machine learning approach to textual entailment recognition

Designing models for learning textual entailment recognizers from annotated examples is not an easy task, as it requires modeling the semantic relations and interactions involved between two pairs of text fragments. In this paper, we approach the problem by first introducing the class of pair feature spaces, which allow supervised machine learning algorithms to derive first-order rewrite rules from annotated examples. In particular, we propose syntactic and shallow semantic feature spaces, and compare them to standard ones. Extensive experiments demonstrate that our proposed spaces learn first-order derivations, while standard ones are not expressive enough to do so.

Automatic Learning of Textual Entailments with Cross-Pair Similarities

In this paper we define a novel similarity measure between examples of textual entailments and we use it as a kernel function in Support Vector Machines (SVMs). This allows us to automatically learn the rewrite rules that describe a non trivial set of entailment cases. The experiments with the data sets of the RTE 2005 challenge show an improvement of 4.4% over the state-of-the-art methods.

Parsing engineering and empirical robustness

Robustness has been traditionally stressed as a general desirable property of any computational model and system. The human NL interpretation device exhibits this property as the ability to deal with odd sentences. However, the difficulties in a theoretical explanation of robustness within the linguistic modelling suggested the adoption of an empirical notion. In this paper, we propose an empirical definition of robustness based on the notion of performance. Furthermore, a framework for controlling the parser robustness in the design phase is presented. The control is achieved via the adoption of two principles: the modularisation, typical of the software engineering practice, and the availability of domain adaptable components. The methodology has been adopted for the production of CHAOS, a pool of syntactic modules, which has been used in real applications. This pool of modules enables a large validation of the notion of empirical robustness, on the one side, and of the design methodology, on the other side, over different corpora and two different languages (English and Italian).

Fast and effective kernels for relational learning from texts

In this paper, we define a family of syntactic kernels for automatic relational learning from pairs of natural language sentences. We provide an efficient computation of such models by optimizing the dynamic programming algorithm of the kernel evaluation. Experiments with Support Vector Machines and the above kernels show the effectiveness and efficiency of our approach on two very important natural language tasks, Textual Entailment Recognition and Question Answering.

Discovering Asymmetric Entailment Relations between Verbs Using Selectional Preferences

In this paper we investigate a novel method to detect asymmetric entailment relations between verbs. Our starting point is the idea that some point-wise verb selectional preferences carry relevant semantic information. Experiments using Word-Net as a gold standard show promising results. Where applicable, our method, used in combination with other approaches, significantly increases the performance of entailment detection. A combined approach including our model improves the AROC of 5% absolute points with respect to standard models.

Shallow Semantic in Fast Textual Entailment Rule Learners

In this paper, we briefly describe two enhancements of the cross-pair similarity model for learning textual entailment rules: 1) the typed anchors and 2) a faster computation of the similarity. We will report and comment on the preliminary experiments and on the submission results.

Ontology-based question answering in a federation of university sites: The MOSES case study

This paper deals with a new approach to ontology-based QA in which users ask questions in natural language to knowledge bases of facts extracted from a federation of Web sites and organised in topic map repositories. Our approach is being investigated in the context of the EU project MOSES.

Efficient Graph Kernels for Textual Entailment Recognition

One of the most important research area in Natural Language Processing concerns the modeling of semantics expressed in text. Since foundational work in Natural Language Understanding has shown that a deep semantic approach is still not feasible, current research is focused on shallow methods combining linguistic models and machine learning techniques. The latter aim at learning semantic models, like those that can detect the entailment between the meaning of two text fragments, by means of training examples described by specific features. These are rather difficult to design since there is no linguistic model that can effectively encode the lexico-syntactic level of a sentence and its corresponding semantic models. Thus, the adopted solution consists in exhaustively describing training examples by means of all possible combinations of sentence words and syntactic information. The latter, typically expressed as parse trees of text fragments, is often encoded in the learning process using graph algorithms. In this paper, we propose a class of graphs, the tripartite directed acyclic graphs (tDAGs), which can be efficiently used to design algorithms for graph kernels for semantic natural language tasks involving sentence pairs. These model the matching between two pairs of syntactic trees in terms of all possible graph fragments. Interestingly, since tDAGs encode the association between identical or similar words (i.e. variables), it can be used to represent and learn first-order rules, i.e. rules describable by first-order logic. We prove that our matching function is a valid kernel and we empirically show that, although its evaluation is still exponential in the worst case, it is extremely efficient and more accurate than the previously proposed kernels.