Zygmunt Vetulani

An Algorithm for Building Lexical Semantic Network and Its Application to PolNet - Polish WordNet Project

This paper presents the PolNet - Polish WordNet project which aims at a linguistically oriented ontology for Polish compatible with Princeton WordNet. We present the headlines of its methodology as well as its implementation using the DEBVisDic tool for WordNet building. We present the results obtained so far and discuss a number of related problems.

An SMS-based System Architecture (Logical Model) to Support Management of Information Exchange in Emergency Stuations. poLINT-112-SMS PROJECT

In the paper we present the architecture of the POLINT-112-SMS system to support information management in emergency situations. The system interprets the text input in form of SMS messages, understands and interprets information provided by the human user. It is supposed to assist a human in taking decisions. The main modules of the system presented here are the following: the SMS gate, the NLP Module (processing Polish), the Situation Analysis Module (SAM) and the Dialogue Maintenance Module (DMM).

Natural language based communication between human users and the emergency center: POLINT-112-SMS

We present a prototype of the POLINT-112-SMS system intended to support information management and decision making in emergency situations. The system is able to interpret short message service (SMS) texts, and understands and processes information provided by the human user. We present the projects specific development methodology and the main modules of the system: SMS gate, NLP Module (processing Polish), Situation Analysis Module (SAM), Dialogue Maintenance Module (DMM), Visualizing Module (VIS) as well as some resources developed within the project (PolNet).

Decision making for a RoboCup multi-agent system

The aim of the paper is to propose a skeleton of a decision rules system for RoboCup teams composed of autonomous virtual soccer players. Decisions concerning action selection are considered.

Ontology of Spatial Concepts in a Natural Language Interface for a Mobile Robot

In this paper we present problems connected with the construction of a natural language (NL) interface for a mobile robot. We determine the spatial information that should be analysed in this kind of interface, as well as indicate which information can be omitted. This study is a contribution to our long-term research program on man-machine communication. Implementation of a virtual agent (ACALA) equipped with a natural language interface is important from a methodological point of view because it permits us to observe natural language interaction between the human user and the computer-controlled system.

Spatiotemporal Aspects of the Monitoring of Complex Events for Public Security Purposes

Abstract The proposals discussed in the paper are used for the development of a system providing assistance to the security staff during a large-scale event involving a large number of participants. A subsystem deals with the SMS messages sent by the security staff (observers) and processes the information they convey. The system provides the security personnel (analysts) with visualization facilities and suggestions for actions, and keeps track of the information exchanged for further use. The paper presents arguments in favor of the formalism called XRCDC (an extension of the Region Cardinal Direction Calculus) designed to represent events and spatiotemporal reasoning about them.

Representation of Uzbek Morphology in Prolog

In the paper we address issues related to the morphology of the Uzbek language. In Uzbek, as in many other agglutinative languages, some single text-words correspond to sentences in non-agglutinative languages. Morphological processing is therefore a crucial operation in the automatic processing of Uzbek. We approach the theory of Uzbek morphology in terms of morphotactic and morphophonemic rules. We present the UZMORPP system of automatic morphological parsing for the Uzbek language. The Prolog implementation of this system is provided.

On Bellert's proposal concerning quantificational universals

The aim of the paper is to formalize I. Bellerts (McGill) proposal to characterize distinct nonequivalent readings of quantificationally ambiguous sentences with help of two features: absoluteness and distributiveness. The formalisation makes use of set theoretical and model theoretical standard notions. Foundamental rules, proposed by Bellert, govering the interpretation of cooccurring quantifiers are quoted and outlines of proofs of important derived rules are given.

Saturation Tests in Application to Validation of Opinion Corpora: A Tool for Corpora Processing

Opinion processing has recently gained much interest among computational linguists, public relation experts, marketing companies, and politicians. Studies of the natural language expression of opinions, desires, emotions, and related phenomena require appropriate tools and methodologies. We propose tools for collection of empirical data in the form of a corpus, limiting our research field to customers’ written opinions about widely used on-line booking services in the area of hotel reservations (via Booking.com). In this paper, we present the corpus acquisition procedure and our data acquisition tool, as well as discuss our decisions about the selection of the source data. We also present some limitations of our proposal and propose a validation methodology for the resulting corpora.

Human Language Technology Challenges for Computer Science and Linguistics

In this contribution, we document the series of progress towards attaining a generic and replicable system that is applicable not only to Nigerian languages but also other African languages. The current system implements a state-of-the-art approach called the Hidden Markov Model (HMM) approach and aims at a hybridised version which front end components would serve other NLP tasks, as well as future research and developments. We continue to tackle the language specific problems and the ‘unity of purpose’ phenomenon for tone language systems and improve on the speech quality as an extension of our LTC’2011 paper. Specifically, we address issues bordering on tone modelling using syllables as basic synthesis units, with an ‘eye ball’ assessment of the synthesised speech quality. The results of this research offer hope for further improvements, and we envisage an unsupervised system to minimise the labour intensive aspects of the current design. Also, with the active collaboration network established in the course of this research, we are certain that a more robust system that would serve a wide variety of applications will evolve.