In this paper we describe the many steps involved in building a production quality Machine Translation system for translating weather warnings between French and English. Although in principle this task may seem straightforward, the details, especially corpus preparation and final text presentation, involve many difficult aspects that are often glossed over in the literature. On top of the classic Statistical Machine Translation evaluation metric results, four manual evaluations have been performed to assess and improve translation quality. We also show the usefulness of the integration of out-of-domain information sources in a Statistical Machine Translation system to produce high quality translated text.

Modelling a customized view is a daunting task that takes into account several parameters, the most important being the user profile. In this paper we study many facets of modelisation and the issues that must be taken into account. We propose an approach in four steps to model a personalised visualization: extract data, guess user's needs and preferences, generate a visualization and finally improve it by user evaluation. It has been applied to the context of weather information in Canada.

The goal of our work is to propose models or methods to personalize the visualization of a large amount of weather information in a simple way and to make sure that a user can analyze all needed information. We personalize this visualization for each user according to an automatically detected profile based on clustering. Clustering is used to group users who are similar to current user and then set the visualization variables according to the visualizations of those users.

Abstract The user-generated Web content has been intensively analyzed in Information Extraction and Natural Language Processing research. Web-posted reviews of consumer goods are studied to find customer opinions about the products. We hypothesize that nonemotionally charged descriptions can be applied to predict those opinions. The descriptions may include indicators of product size (tall), commonplace (some), frequency of happening (often), and reviewer certainty (maybe). We first construct patterns of how the descriptions are used in consumer-written texts and then represent individual reviews through these patterns. We propose a semantic hierarchy that organizes individual words into opinion types. We run machine learning algorithms on five data sets of user-written product reviews: four are used in classification experiments, another one for regression and classification. The obtained results support the use of non-emotional descriptions in opinion learning.

Text prediction is a form of interactive machine translation that is well suited to skilled translators. In principle it can assist in the production of a target text with minimal disruption to a translator's normal routine. However, recent evaluations of a prototype prediction system showed that it significantly decreased the productivity of most translators who used it. In this paper, we analyze the reasons for this and propose a solution which consists in seeking predictions that maximize the expected benefit to the translator, rather than just trying to anticipate some amount of upcoming text. Using a model of a "typical translator" constructed from data collected in the evaluations of the prediction prototype, we show that this approach has the potential to turn text prediction into a help rather than a hindrance to a translator.

We present and evaluate SumUM, a text summarization system that takes a raw technical text as input and produces an indicative informative summary. The indicative part of the summary identifies the topics of the document, and the informative part elaborates on some of these topics according to the reader's interest. SumUM motivates the topics, describes entities, and defines concepts. It is a first step for exploring the issue of dynamic summarization. This is accomplished through a process of shallow syntactic and semantic analysis, concept identification, and text regeneration. Our method was developed through the study of a corpus of abstracts written by professional abstractors. Relying on human judgment, we have evaluated indicativeness, informativeness, and text acceptability of the automatic summaries. The results thus far indicate good performance when compared with other summarization technologies.

In this paper, we present a way to integrate bilingual lexicons into an operational probabilistic translation assistant (TransType). These lexicons could be any resource available to the translator (e.g. terminological lexicons) or any resource statistically derived from training material. We describe a bilingual lexicon acquisition process that we developped and we evaluate from a theoretical point of view its benefits to a translation completion task.

This paper argues for looking at Controlled Languages (CL) from a Natural Language Generation (NLG) perspective. We show that CLs are used in a normative environment in which different textual modules can be identified, each having its own set of rules constraining the text. These rules can be used as a basis for natural language generation. These ideas were tested in a proof of concept generator for the domain of aircraft maintenance manuals.

This paper discusses a fundamental problem in natural language generation: how to organize the content of a text in a coherent and natural way. In this research, we set out to determine the semantic content and the rhetorical structure of texts and to develop heuristics to perform this process automatically within a text generation framework. The study was performed on a specific language and textual genre: French instructional texts. From a corpus analysis of these texts, we determined nine senses typically communicated in instructional texts and seven rhetorical relations used to present these senses. From this analysis, we then developed a set of presentation heuristics that determine how the senses to be communicated should be organized rhetorically in order to create a coherent and natural text. The heuristics are based on five types of constraints: conceptual, semantic, rhetorical, pragmatic, and intentional constraints. To verify the heuristics, we developed the spin natural language generation system, which performs all steps of text generation but focuses on the determination of the content and the rhetorical structure of the text.

We show the design principles of an automatic indentation GNU Emacs mode for Haskell and Miranda(tm), functional languages using the ‘layout rule’ instead of the usual parenthetic structures for indentifying dependent program parts.

Graphics and text have to be well integrated in order to achieve their full potential.A picture shows but a text describes.In a statistical report, graphics show the data that is analyzed in the text.This paper describes a system, called PostGraphe, which generates a report integrating graphics and text from a single set of writer's intentions.The system is given the data in tabular form as might be found in a spreadsheet; also input is a declaration of the types of values in the columns of the table.The user chooses the intentions to be conveyed in the graphics (e.g.compare two variables, show the evolution of a set of variables ...) and the system generates a report in IgTEX with the appropriate PostScript graphic files.

Researchers and industry are actively developing Software Agents (SAs), autonomous software that will assist users in achieving various tasks, collaborate with them, or even act on their behalf. To explore new interaction modes for SAs which need to be more sophisticated than simple exchanges of messages, we have analysed human conversations and elaborated an interaction approach for SAs based on a conversation model. Using this approach, we have developed a multi-agent system that simulates conversations involving SAs. We assume that SAs perform communicative acts to negotiate about mental states, such as beliefs and goals, turn-taking and special conversational sequences. We also assume that SAs respect communication protocols when they negotiate. In this paper, we describe the conceptual structure of communicative acts, the knowledge structures used to model a conversation, and the communication protocols. We show how an inference engine using ‘conversation-managing rules’ can be integrated in a conversational agent responsible for interpreting communicative acts, and we discuss the different kinds of rules that we propose. The prototype PSICO was implemented to simulate conversations on a computer platform.

Abstract This paper presents an application of functional programming in the field of molecular biology: exploring the conformations of nucleic acids. The Nucleic Acid three-dimensional structure determination problem (NA3D) and a constraint satisfaction algorithm are formally described. Prototyping and experimental development using the Miranda functional programming language, over the last four years, are discussed. A Prolog implementation has been developed to evaluate software engineering and performance criteria between functional and logic programming. A C++ implementation has been developed for distribution purpose and to solve large practical problems. This system, called MC-SYM for ‘Macromolecular Conformation by SYMbolic generation’, is used in more than 50 laboratories, including academic and government research centres and pharmaceutical companies.

This paper describes an original approach to semantics representation based on the use of a non‐strict functional programming language with polymorphic typing. This approach provides a unified formalism needing no preprocessing or postprocessing to the functional language itself: parsing and semantics are declared naturally using function definition and evaluation is done by lambda application along the lines of Montague. We show that by changing only the model we can, after parsing, compute either the truth value of a sentence or its parse tree.

Abstract This paper presents an application of functional programming: searching a domain for elements which satisfy certain constraints. We give a very general formulation of the problem and describe ‘generate and test’, ‘backtracking’ and ‘forward checking’ algorithms. We then introduce the concept of domain generating functions to capture a common optimization during the search process: using partial solutions to reduce the size of the search space. We compare the efficiency of the original algorithms and those using domain generating functions first with the ‘classical’ n -queens example, and then with a problem having larger domains to search which was inspired by an application in macromolecular structure determination. Using algorithms coded in Miranda, Haskell and Common Lisp, we show that a high order (lazy) functional language is a useful and efficient tool for prototyping search methods in large complex domains.

No abstract available.

A major difficulty in the evaluation of secondary and tertiary structures of nucleic acids is the lack of convenient methods for their construction and representation. As a first step in a study of the symbolic representation of biopolymers, we report the development of a structure editor written in Pascal, permitting model construction on the screen of a personal computer. The program calculates energies for helical regions, allows user-defined helices and displays the secondary structure of a nucleic acid based on a user-selected set of helices. Screen and printer outputs can be in the form of a backbone or the letters of the primary sequence. The molecule can then be displayed in a format which simulates its three-dimensional structure. Using appropriate glasses, the molecule can be viewed on the screen in three dimensions. Other options include the manipulation of helices and single-stranded regions which results in changes in the spatial relationship between different regions of the molecule. The editor requires an IBM or compatible PC, 640 kbyte memory and a medium or high resolution graphics card.

In order to study the dynamics of protein and nucleic acid conformations, a molecular folding-unfolding system (FUS written in Lisp) has been developed. Secondary structure features of protein and nucleic acids are graphically represented by cubes in a modified 'Blocks World' paradigm. Modeling of protein and nucleic acid unfolding (denaturation) and folding of their three-dimensional structure is possible by the use of high level 'block' operators which allow displacement of these structural features in space. Due to the flexible nature of this program, FUS is a useful tool for the rapid evaluation of user-defined rules governing conformational changes. The use of FUS to unfold three common proteins (prealbumin, flavodoxin and triose phosphate isomerase) and a tRNA is presented.

This paper describes our experience in using Ada as a vehicle for teaching Software Engineering concepts in a course for first year undergraduate students at the University of Montreal.

Abstract This paper describes the coupling of logic programming with Icon, which is a programming language aimed at string processing. Icon and Prolog have many similarities and their integration is feasible and desirable because the weaknesses of one can be compensated for by the strengths of the other. In our case, a Prolog interpreter was written as an Icon procedure that can be linked and called by an Icon program. This interpreter deals with all Icon data types and can be called in the context of the goal‐directed evaluation of Icon. We give an example showing the power of this symbiosis between these two languages where a Prolog call in Icon is a generator and an Icon call in a Prolog clause is a built‐in predicate.