Livio Robaldo

Sense annotation in the Penn discourse treebank

An important aspect of discourse understanding and generation involves the recognition and processing of discourse relations. These are conveyed by discourse connectives, i.e., lexical items like because and as a result or implicit connectives expressing an inferred discourse relation. The Penn Discourse TreeBank (PDTB) provides annotations of the argument structure, attribution and semantics of discourse connectives. In this paper, we provide the rationale of the tagset, detailed descriptions of the senses with corpus examples, simple semantic definitions of each type of sense tags as well as informal descriptions of the inferences allowed at each level.

Phrase detectives: Utilizing collective intelligence for internet-scale language resource creation

We are witnessing a paradigm shift in Human Language Technology (HLT) that may well have an impact on the field comparable to the statistical revolution: acquiring large-scale resources by exploiting collective intelligence. An illustration of this new approach is Phrase Detectives, an interactive online game with a purpose for creating anaphorically annotated resources that makes use of a highly distributed population of contributors with different levels of expertise. The purpose of this article is to first of all give an overview of all aspects of Phrase Detectives, from the design of the game and the HLT methods we used to the results we have obtained so far. It furthermore summarizes the lessons that we have learned in developing this game which should help other researchers to design and implement similar games.

Eunomos, a legal document and knowledge management system for the Web to provide relevant, reliable and up-to-date information on the law

This paper describes the Eunomos software, an advanced legal document and knowledge management system, based on legislative XML and ontologies. We describe the challenges of legal research in an increasingly complex, multi-level and multi-lingual world and how the Eunomos software helps users cut through the information overload to get the legal information they need in an organized and structured way and keep track of the state of the relevant law on any given topic. Using NLP tools to semi-automate the lower-skill tasks makes this ambitious project a realistic commercial prospect as it helps keep costs down while at the same time allowing greater coverage. We describe the core system from workflow and technical perspectives, and discuss applications of the system for various user groups.

Learning from syntax generalizations for automatic semantic annotation

Nowadays, there is a huge amount of textual data coming from on-line social communities like Twitter or encyclopedic data provided by Wikipedia and similar platforms. This Big Data Era created novel challenges to be faced in order to make sense of large data storages as well as to efficiently find specific information within them. In a more domain-specific scenario like the management of legal documents, the extraction of semantic knowledge can support domain engineers to find relevant information in more rapid ways, and to provide assistance within the process of constructing application-based legal ontologies. In this work, we face the problem of automatically extracting structured knowledge to improve semantic search and ontology creation on textual databases. To achieve this goal, we propose an approach that first relies on well-known Natural Language Processing techniques like Part-Of-Speech tagging and Syntactic Parsing. Then, we transform these information into generalized features that aim at capturing the surrounding linguistic variability of the target semantic units. These new featured data are finally fed into a Support Vector Machine classifier that computes a model to automate the semantic annotation. We first tested our technique on the problem of automatically extracting semantic entities and involved objects within legal texts. Then, we focus on the identification of hypernym relations and definitional sentences, demonstrating the validity of the approach on different tasks and domains.

Linking legal open data: breaking the accessibility and language barrier in european legislation and case law

In this paper we describe how the EUCases FP7 project is addressing the problem of lifting Legal Open Data to Linked Open Data to develop new applications for the legal information provision market by enriching structurally the documents (first of all with navigable references among legal texts) and semantically (with concepts from ontologies and classification). First we describe the social and economic need for breaking the accessibility barrier in legal information in the EU, then we describe the technological challenges and finally we explain how the EUCases project is addressing them by a combination of Human Language Technologies.

Semantic relation extraction from legislative text using generalized syntactic dependencies and support vector machines

In this paper we present a technique to automatically extract semantic knowledge from legislative text. Instead of using pattern matching methods relying on lexico-syntactic patterns, we propose a technique which uses syntactic dependencies between terms extracted with a syntactic parser. The idea is that syntactic information are more robust than pattern matching approaches when facing length and complexity of the sentences. Relying on a manually annotated legislative corpus, we transform all the surrounding syntax of the semantic information into abstract textual representations, which are then used to create a classification model by means of a standard Support Vector Machine system. In this work, we initially focus on three different semantic tags, achieving very high accuracy levels on two of them, demonstrating both the limits and the validity of the approach.

Dependency tree semantics

This paper presents Dependency Tree Semantics (DTS), an underspecified logic for representing quantifier scope ambiguities. DTS features a direct interface with a Dependency grammar, an easy management of partial disambiguations and the ability to represent branching quantifier readings. This paper focuses on the syntax of DTS, while does not take into account the model-theoretic interpretation of its well-formed structures.

Independent Set Readings and Generalized Quantifiers

Several authors proposed to devise logical structures for Natural Language (NL) semantics in which noun phrases yield referential terms rather than standard Generalized Quantifiers. In this view, two main problems arise: the need to refer to the maximal sets of entities involved in the predications and the need to cope with Independent Set (IS) readings, where two or more sets of entities are introduced in parallel. The article illustrates these problems and their consequences, then presents an extension of the proposal made in Sher (J Philos Logic 26:1–43, 1997) in order to properly represent the meaning of IS readings involving NL quantifiers. The solution proposed here allows to uniformly deal with both standard linear and IS readings, regardless of their actual existence in NL or quantifiers’ monotonicity. Sentences featuring nested quantifications are particularly problematic. By avoiding parallel nested quantification in the formulae, the proper true values are achieved.

On the Identification of Quantifiers' Witness Sets: A Study of Multi-quantifier Sentences

Natural language sentences that talk about two or more sets of entities can be assigned various readings. The ones in which the sets are independent of one another are particularly challenging from the formal point of view. In this paper we will call them ‘Independent Set (IS) readings’. Cumulative and collective readings are paradigmatic examples of IS readings. Most approaches aiming at representing the meaning of IS readings implement some kind of maximality conditions on the witness sets involved. Two kinds of maximization have been proposed in the literature: ‘Local’ and ‘Global’ maximization. In this paper, we present an online questionnaire whose results appear to support Local maximization. The latter seems to capture the proper interplay between the semantics and the pragmatics of multi-quantifier sentences, provided that witness sets are selected on pragmatic grounds.

The European Taxonomy Syllabus: A multi-lingual, multi-level ontology framework to untangle the web of European legal terminology

The final publication is available at IOS Press through http://dx.doi.org/10.3233/AO-170174. This paper describes a new concept of legal ontology together with an ontology development tool, called European Legal Taxonomy Syllabus (ELTS). The tool is used to model the legal terminology created by the Uniform Terminology project on EU consumer protection law as an ontology. ELTS is not a formal ontology in the standard sense, i.e., an axiomatic ontology formalized, for instance, in description logic. Rather, it is a lightweight ontology, i.e. a knowledge base storing low-level legal concepts, connected via low-level semantic relations, and related to linguistic patterns that denote legal concepts in several languages spoken in the European Union (EU). In other words, ELTS is a multi-lingual and multi-jurisdictional terminological vocabulary enriched with concepts denoted by vocabulary entries, with semantic relations between different concepts. The choice of such an architecture is based on past studies in comparative law and is motivated by the need to reveal the differences between national systems within the EU. Past literature in comparative law highlights that axiomatic ontologies freeze legal knowledge in an unreal steadiness, i.e., they render it disconnected from legal practice. Much more flexibility is needed to make the knowledge base acceptable to legal practitioners. ELTS was developed together with legal practitioners on the basis of the comparative view of European law. The ontology framework is designed to help professionals study the meaning of national and European legal terms and how they inter-relate in the transposition of European Directives into national laws. The structure and user interface of ELTS is suitable for building multi-lingual, multi-jurisdictional legal ontologies in a bottom-up and collaborative manner, starting from the description of legal terms by legal experts. It also takes into account the interpretation of norms, the dynamic character of norms and the contextual character of legal concepts in that they are linked to their legal sources (legislation, case law and doctrine).