Maria Teresa Pazienza

Semantic turkey: a browser-integrated environment for knowledge acquisition and management

With the continued growth of online semantic information, the processes of searching and managing this massive scale and heterogeneous content have become increasingly challenging. In this work, we present PowerAqua, an ontologybased Question Answering system that is able to answer queries by locating and integrating information, which can be distributed across heterogeneous semantic resources. We provide a complete overview of the system including: the research challenges that it addresses, its architecture, the evaluations that have been conducted to test it, and an in-depth discussion showing how PowerAqua effectively supports users in querying and exploring Semantic Web content.Born four years ago as a Semantic Web extension for the web browser Firefox, Semantic Turkey pushed forward the traditional concept of links&folders-based bookmarking to a new dimension, allowing users to keep track of relevant information from visited web sites and to organize the collected content according to standard or personally defined ontologies. Today, the tool has broken the boundaries of its original intents and can be considered, under every aspect, an extensible platform for knowledge management and acquisition. The semantic bookmarking and annotation facilities of Semantic Turkey are now supporting just a part of a whole methodology where different actors, from domain experts to knowledge engineers, can cooperate in developing, building and populating ontologies while navigating the Web.

Information Extraction A Multidisciplinary Approach to an Emerging Information Technology

Information extraction as a core language technology.- Information extraction: Techniques and challenges.- Concepticons vs. lexicons: An architecture for multilingual information extraction.- Lexical acquisition and information extraction.- Technical terminology for domain specification and content characterisation.- Short query linguistic expansion techniques: Palliating one-word queries by providing intermediate structure to text.- Information retrieval: Still butting heads with natural language processing?.- Semantic matching: Formal ontological distinctions for information organization, extraction, and integration.- Machine learning for information extraction.- Modeling and querying semi-structured data.

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.

Conceptual graphs for the analysis and generation of sentences

A system for analyzing and generating Italian texts is under development at the IBM Rome Scientific Center. Detailed semantic knowledge on word-sense patterns is used to relate the linguistic structure of a sentence to a conceptual representation (a conceptual graph). Conceptual graphs are stored in a database and accessed by a natural-language query/answering module. The system analyzes a text supplied by a press-agency-release database. It consists of three modules: a morphological, a syntactic, and a semantic processor. The semantic analyzer uses a conceptual lexicon of word-sense descriptions, currently including about 850 entries. A description is an extended case frame providing the surface semantic patterns (SSP) of a word-sense w. SSPs express both semantic constraints and word-usage information, such as commonly found word patterns, idioms, and metaphoric expressions. SSPs are used by the semantic interpreter to build a conceptual graph of the sentence, which is then accessed by the query-answering and language-generation modules. This paper makes the claim that the SSP approach is viable and necessary to cope with language phenomena in unrestricted domains. Surface patterns are easily acquired inductively from the natural-language corpus rather than deductively from predefined conceptual structures. SSPs map quite complex sentences into surface semantic representations that can be generalized at a subsequent stage. In contrast, the current state of the art does not provide viable theory or methodology to go from superficial to deep structures. This issue is more extensively addressed in the body of the paper.

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.

An empirical symbolic approach to natural language processing

Empirical methods in the field of natural language processing (NLP) are usually based on a probabilistic model of language. These methods recently gained popularity because of the claim that they provide a better coverage of language phenomena. Though this claim is not entirely proved, empirical methods certainly outperform in this regard rationalist, or symbolic, methods. However, empirical methods provide a probabilistic, not conceptual, explanation of the analyzed linguistic phenomena. Probabilistic systems do “work” in real applications, and this is meritorious, but in our view they are intrinsically unable to provide insight into the mechanisms of human communication, because the output is represented by plain words, or word clusters, with attached probabilities. Eventually, a human analyst must make sense of these data. In the past few years, we explored the possibility of combining the advantages of empirical and rationalist approaches in NLP. Our objective was to define methods for lexical knowledge acquisition that are both scalable and linguistically “appealing”, that is, amenable to a theoretically founded analysis of language. In this paper we describe and evaluate the results of a large-scale lexical learning system, ARIOSTO_LEX, that uses a combination of probabilistic and knowledge-based methods for the acquisition of selectional restrictions of words in sublanguages. We present many experimental data obtained from different corpora in different domains and languages, and show that the acquired lexical data not only have practical applications in NLP, but they are indeed useful for a comparative analysis of sublanguages. Importantly, ARIOSTO_LEX shed light on recurrent linguistic phenomena that have a problematic impact on the large-scale applicability of commonly used NLP techniques.

Corpus-Driven Unsupervised Learning of Verb Subcategorization Frames

The behavior of verbs in sublanguages is highly specific and does not follow general principles of lexical decomposition. NLP applications require specific lexicons for tasks like surface parsing and shallow semantic interpretation. The reduced set of verbal senses specific to a given domain is more appropriate for efficient processing in real world tasks (e.g. information extraction and retrieval). In this paper a method for learning verb subcategorization patterns from corpora is proposed. Conceptual clustering techniques are applied to the results of surface parsing in order to extract relevant domain typical senses and automatically build a lexicon of subcategorization frames. The aim is to learn a core of lexico-grammatical knowledge suitable to support more sophisticated parsing strategies to be applied in a target NLP application. Results derived for the Italian language from several corpora are presented.

Semantic Turkey: A Semantic Bookmarking Tool (System Description)

In this work we introduce Semantic Turkey, a Semantic Extension for the popular web browser Mozilla Firefox. Semantic Turkey can be used to keep track of relevant information from visited web sites and organize collected content according to a personally defined ontology. Clear separation between knowledge data (the WHAT) and web links (the WHERE) is established into the knowledge model of the system, which allows for innovative navigation of both the acquired information and of the pages where it has been collected. This paper describes the architecture of the Semantic Turkey extension for Firefox, analyzes its development, shows its most interesting features and presents our plans for future improvements of the tool.

Computational Lexicons: the Neat Examples and the Odd Exemplars

When implementing computational lexicons it is important to keep in mind the texts that a NLP system must deal with. Words relate to each other in many different, often queer, ways: this information is rarely found in dictionaries, and it is quite hard to be invented a priori, despite the imagination that linguists exhibit at inventing esoteric examples.In this paper we present the results of an experiment in learning from corpora the frequent selectional restrictions holding between content words. The method is based on the analysis of word associations augmented with syntactic markers and semantic tags. Word pairs are extracted by a morphosyntactic analyzer and clustered according to their semantic tags. A statistical measure is applied to the data to evaluate the significance of a detected relation. Clustered association data render the study of word associations more interesting with several respects: data are more reliable even for smaller corpora, more easy to interpret, and have many practical applications in NLP.