Wordnet.Br: An Exercise of Human Language Technology Research

This paper reports the ongoing project (since 2002) of developing a wordnet for Brazilian Portuguese (Wordnet.Br) from scratch. In particular, it describes the process of constructing the Wordnet.Br core database, which has 44,000 words organized in 18,500 synsets Accordingly, it briefly sketches the project overall methodology, its lexical resourses, the synset compilation process, and the Wordnet.Br editor, a GUI (graphical user interface) which aids the linguist in the compilation and maintenance of the Wordnet.Br. It concludes with the planned further work.

Discriminative spoken language understanding using word confusion networks

Current commercial dialogue systems typically use hand-crafted grammars for Spoken Language Understanding (SLU) operating on the top one or two hypotheses output by the speech recogniser. These systems are expensive to develop and they suffer from significant degradation in performance when faced with recognition errors. This paper presents a robust method for SLU based on features extracted from the full posterior distribution of recognition hypotheses encoded in the form of word confusion networks. Following [1], the system uses SVM classifiers operating on n-gram features, trained on unaligned input/output pairs. Performance is evaluated on both an off-line corpus and on-line in a live user trial. It is shown that a statistical discriminative approach to SLU operating on the full posterior ASR output distribution can substantially improve performance both in terms of accuracy and overall dialogue reward. Furthermore, additional gains can be obtained by incorporating features from the previous system output. © 2012 IEEE.

Licensing technology : negotiating and drafting technology transfer agreements [3rd ed.]

Part I of this book covers the commercial and contractual background to technology licensing agreements. Part II discusses the European Community's new regime on the application and enforcement of Article 81 to technology licensing agreements. EC Council Regulation 1/2003 replaced the Council Regulation 17/1962 and repealed the system under which restrictive agreements and practices could be notified to the EC Commission. A new Commission regulation on technology transfer agreements, Regulation 772/2004. These two enactments required consequential amendments to the chapters in Part III where the usual terms of technology licensing agreements are analysed and exemplified by reference to decided cases.

A programming language for software components

Component software has many benefits, most notably increased software re-use; however, the component software process places heavy burdens on programming language technology, which modern object-oriented programming languages do not address. In particular, software components require specifications that are both sufficiently expressive and sufficiently abstract, and, where possible, these specifications should be checked formally by the programming language. This dissertation presents a programming language called Mentok that provides two novel programming language features enabling improved specification of stateful component roles. Negotiable interfaces are interface types extended with protocols, and allow specification of changing method availability, including some patterns of out-calls and re-entrance. Type layers are extensions to module signatures that allow specification of abstract control flow constraints through the interfaces of a component-based application. Development of Mentok's unique language features included creation of MentokC, the Mentok compiler, and formalization of key properties of Mentok in mini-languages called MentokP and MentokL.

Integrating crowd-behavior modeling into military simulation using game technology

Crowds of noncombatants play a large and increasingly recognized role in modern military operations and often create substantial difficulties for the combatant forces involved. However, realistic models of crowds are essentially absent from current military simulations. To address this problem, the authors are developing a crowd simulation capable of generating crowds of noncombatant civilians that exhibit a variety of realistic individual and group behaviors at differing levels of fidelity. The crowd simulation is interoperable with existing military simulations using a standard, distributed simulation architecture. Commercial game technology is used in the crowd simulation to model both urban terrain and the physical behaviors of the human characters that make up the crowd. The objective of this article is to present the design and development process of a simulation that integrates commercially available game technology with current military simulations to generate realistic and believable crowd behavior.

Crowd modelling for military simulations using game technology

Crowds of non-combatants play a large and increasingly recognized role in modern military operations, and often create substantial difficulties for the combatant forces involved. However, realistic models of crowds are essentially absent from current military simulations. To address this problem we are developing a crowd simulation capable of generating crowds of non-combatant civilians that exhibit a variety of realistic individual and group behaviours at differing levels of fidelity. The crowd simulation is interoperable with existing military simulations using a standard distributed simulation architecture. Commercial game technology is utilized in the crowd simulation to model both urban terrain and the physical behaviours of the human characters that make up the crowd. The objective of this paper is to present the process involved with the design and development of a simulation that integrates commercially available game technology with current military simulations in order to generate realistic and believable crowd behaviour.

Research bed for unit selection based text to speech synthesis

The paper describes a modular, unit selection based TTS framework, which can be used as a research bed for developing TTS in any new language, as well as studying the effect of changing any parameter during synthesis. Using this framework, TTS has been developed for Tamil. Synthesis database consists of 1027 phonetically rich prerecorded sentences. This framework has already been tested for Kannada. Our TTS synthesizes intelligible and acceptably natural speech, as supported by high mean opinion scores. The framework is further optimized to suit embedded applications like mobiles and PDAs. We compressed the synthesis speech database with standard speech compression algorithms used in commercial GSM phones and evaluated the quality of the resultant synthesized sentences. Even with a highly compressed database, the synthesized output is perceptually close to that with uncompressed database. Through experiments, we explored the ambiguities in human perception when listening to Tamil phones and syllables uttered in isolation,thus proposing to exploit the misperception to substitute for missing phone contexts in the database. Listening experiments have been conducted on sentences synthesized by deliberately replacing phones with their confused ones.

Linked Data for sharing, discovery and re-use of Language Resources at a Web scale

Conferencia por invitación, impartida el 31 d mayo de 2014 en el Workshop on Language Technology Service Platforms: Synergies, Standards, Sharing at LREC2014

Aerospace spinoffs : twenty-five years of technology transfer.

Shipping list no.: 88-342-P.

SEQUENTIAL DECISIONS AND PREDICTIONS IN NATURAL LANGUAGE PROCESSING

Natural language processing has achieved great success in a wide range of ap- plications, producing both commercial language services and open-source language tools. However, most methods take a static or batch approach, assuming that the model has all information it needs and makes a one-time prediction. In this disser- tation, we study dynamic problems where the input comes in a sequence instead of all at once, and the output must be produced while the input is arriving. In these problems, predictions are often made based only on partial information. We see this dynamic setting in many real-time, interactive applications. These problems usually involve a trade-off between the amount of input received (cost) and the quality of the output prediction (accuracy). Therefore, the evaluation considers both objectives (e.g., plotting a Pareto curve). Our goal is to develop a formal understanding of sequential prediction and decision-making problems in natural language processing and to propose efficient solutions. Toward this end, we present meta-algorithms that take an existent batch model and produce a dynamic model to handle sequential inputs and outputs. Webuild our framework upon theories of Markov Decision Process (MDP), which allows learning to trade off competing objectives in a principled way. The main machine learning techniques we use are from imitation learning and reinforcement learning, and we advance current techniques to tackle problems arising in our settings. We evaluate our algorithm on a variety of applications, including dependency parsing, machine translation, and question answering. We show that our approach achieves a better cost-accuracy trade-off than the batch approach and heuristic-based decision- making approaches. We first propose a general framework for cost-sensitive prediction, where dif- ferent parts of the input come at different costs. We formulate a decision-making process that selects pieces of the input sequentially, and the selection is adaptive to each instance. Our approach is evaluated on both standard classification tasks and a structured prediction task (dependency parsing). We show that it achieves similar prediction quality to methods that use all input, while inducing a much smaller cost. Next, we extend the framework to problems where the input is revealed incremen- tally in a fixed order. We study two applications: simultaneous machine translation and quiz bowl (incremental text classification). We discuss challenges in this set- ting and show that adding domain knowledge eases the decision-making problem. A central theme throughout the chapters is an MDP formulation of a challenging problem with sequential input/output and trade-off decisions, accompanied by a learning algorithm that solves the MDP.

Semantic judgement of medical concepts : combining syntagmatic and paradigmatic information with the tensor encoding model

This paper outlines a novel approach for modelling semantic relationships within medical documents. Medical terminologies contain a rich source of semantic information critical to a number of techniques in medical informatics, including medical information retrieval. Recent research suggests that corpus-driven approaches are effective at automatically capturing semantic similarities between medical concepts, thus making them an attractive option for accessing semantic information. Most previous corpus-driven methods only considered syntagmatic associations. In this paper, we adapt a recent approach that explicitly models both syntagmatic and paradigmatic associations. We show that the implicit similarity between certain medical concepts can only be modelled using paradigmatic associations. In addition, the inclusion of both types of associations overcomes the sensitivity to the training corpus experienced by previous approaches, making our method both more effective and more robust. This finding may have implications for researchers in the area of medical information retrieval.