A multilingual FrameNet-based grammar and lexicon for controlled natural language

Berkeley FrameNet is a lexico-semantic resource for English based on the theory of frame semantics. It has been exploited in a range of natural language processing applications and has inspired the development of framenets for many languages. We present a methodological approach to the extraction and generation of a computational multilingual FrameNet-based grammar and lexicon. The approach leverages FrameNet-annotated corpora to automatically extract a set of cross-lingual semantico-syntactic valence patterns. Based on data from Berkeley FrameNet and Swedish FrameNet, the proposed approach has been implemented in Grammatical Framework (GF), a categorial grammar formalism specialized for multilingual grammars. The implementation of the grammar and lexicon is supported by the design of FrameNet, providing a frame semantic abstraction layer, an interlingual semantic application programming interface (API), over the interlingual syntactic API already provided by GF Resource Grammar Library. The evaluation of the acquired grammar and lexicon shows the feasibility of the approach. Additionally, we illustrate how the FrameNet-based grammar and lexicon are exploited in two distinct multilingual controlled natural language applications. The produced resources are available under an open source license.     

A case based reasoning model for multilingual language generation in dialogues

The process of Natural Language Generation for a Conversational Agent translates some semantic language to its surface form expressed in natural language. In this paper, we are going to show a Case Based Reasoning technique which is easily extensible and adaptable to multiple domains and languages, that generates coherent phrases and produces a natural outcome in the context of a Conversational Agent that maintains a dialogue with the user.     

A linguistic ontology of space for natural language processing

We present a detailed semantics for linguistic spatial expressions supportive of computational processing that draws substantially on the principles and tools of ontological engineering and formal ontology. We cover language concerned with space, actions in space and spatial relationships and develop an ontological organization that relates such expressions to general classes of fixed semantic import. The result is given as an extension of a linguistic ontology, the Generalized Upper Model, an organization which has been used for over a decade in natural language processing applications. We describe the general nature and features of this ontology and show how we have extended it for working particularly with space. Treaitng the semantics of natural language expressions concerning space in this way offers a substantial simplification of the general problem of relating natural spatial language to its contextualized interpretation. Example specifications based on natural language examples are presented, as well as an evaluation of the ontology's coverage, consistency, predictive power, and applicability.     

Dynamic context generation for natural language understanding: a multifaceted knowledge approach

We describe a comprehensive framework for text understanding, based on the representation of context. It is designed to serve as a representation of semantics for the full range of interpretive and inferential needs of general natural language processing. Its most distinctive feature is its uniform representation of the various simple and independent linguistic sources that play a role in determining meaning: lexical associations, syntactic restrictions, case-role expectations, and most importantly, contextual effects. Compositional syntactic structure from a shallow parsing is represented in a neural net-based associative memory, where it then interacts through a Bayesian network with semantic associations and the context or "gist" of the passage carried forward from preceding sentences. Experiments with more than 2000 sentences in different languages are included.     

Lexicalization in natural language generation: A survey

In natural language generation, a meaning representation of some kind is successively transformed into a sentence or a text. Naturally, a central subtask of this problem is the choice of words, orlexicalization. In this paper, we propose four major issues that determine how a generator tackles lexicalization, and survey the contributions that researchers have made to them. Open problems are identified, and a possible direction for future research is sketched.     

Integrating discourse pragmatics and propositional knowledge for multilingual natural language processing

We present an integrated knowledge representation system for natural language processing (NLP) whose main distinguishing feature is its emphasis on encoding not only the usual propositional structure of the utterances in the input text, but also capturing an entire complex of nonpropositional — discourse, attitudinal, and other pragmatic — meanings that NL texts always carry. The need for discourse pragmatics, together with generic semantic information, is demonstrated in the context of anaphoric and definite noun phrase resolution for accurate machine translation. The major types of requisite pragmatic knowledge are presented, and an extension of a frame-based formalism developed in the context of the TRANSLATOR system is proposed as a first-pass codification of the integrated knowledge base.     

Reversible logic grammars for natural language parsing and generation

The use of a single grammar in natural language parsing and generation is most desirable for a variety of reasons, including efficiency, perspicuity, integrity, robustness, and a certain amount of elegance. These characteristics have been noted before by several researchers, but it was only recently that more serious attention started to be paid to the problem of creating a bidirectional system for natural language processing. In this paper we discuss a somewhat more radical version of the problem: given a parser for a language, can we reverse it so that it becomes an efficient generator for the same language? Furthermore, since both the parser and the generator are based upon the same grammar, are there any normalization conditions upon the form of the grammar that must be met in order to assure the maximum efficiency of the reversed program? Can other grammars be transformed into the normal form? We describe the results of an experiment with PROLOG-based logic grammar which has been derived from a substantial-coverage string grammar for English. We present an alogorithm for automated inversion of a unification parser into an efficient unification generator, using the collections of minimal sets of essential arguments for predicates. We discuss the scope of the present version of the algorithm and then point out several possible avenues for extension. We also outline a preliminary solution to the question of grammar's “normal form” and suggest a handful of normalizing transformations that can be used to enhance the efficiency of the generator. This research interacts closely with a Japanese-English machine translation project at New York University, for which the first implementation of the inversion algorithm has been prepared.     

A prototyping language for real-time software

PSDL is a language for describing prototypes of real-time software systems. It is most useful for requirements analysis, feasibility studies, and the design of large embedded systems. PSDL has facilities for recording and enforcing timing constraints, and for modeling the control aspects of real-time systems using nonprocedural control constraints, operator abstractions, and data abstractions. The language has been designed for use with an associated prototyping methodology. PSDL prototypes are executable if supported by a software base containing reusable software components in an underlying programming language (e.g. Ada)     

An alternate reality game for language learning: ARGuing for multilingual motivation

Over the last decade, Alternate Reality Games (ARGs), a form of narrative often involving multiple media and gaming elements to tell a story that might be affected by participants’ actions, have been used in the marketing and promotion of a number of entertainment related products such as films, computer games and music. This paper discusses the design, development and evaluation of an ARG aimed at increasing the motivations of secondary school level students across Europe in the learning of modern foreign languages. The ARG was developed and implemented as part of a European Commission Comenius project and involved 6 project partners, 328 secondary school students and 95 language teachers from 17 European countries. The collaborative nature of ARGs provides a potentially useful vehicle for developing collaborative activities within an educational context. This paper describes the educational value of ARGs, in particular the ARG for supporting the teaching of modern European languages and the specific activities that were developed around Web 2.0 and gaming that underpinned the ARG and helped promote cooperation and learning within an educational environment. An evaluation of the ARG was conducted using an experimental design of pre-test → ARG intervention → post-test. 105 students completed the pre-test, 92 students completed the post-test and 45 students completed both the pre-test and post-test questionnaires. In general, student attitudes towards the ARG were very positive with evidence suggesting that the ARG managed to deliver the motivational experience expected by the students. The majority of students who completed the post-test either agreed or strongly agreed that they would be willing to play the game over a prolonged period of time as part of a foreign language course. In addition, through using the ARG, students believed that they obtained skills relating to cooperation, collaboration and teamwork.     

An approach for automatic generation of adaptive hypermedia in education with multilingual knowledge discovery techniques

This work describes a framework that combines techniques from Adaptive Hypermedia and Natural Language processing in order to create, in a fully automated way, on-line information systems from linear texts in electronic format, such as textbooks. The process is divided into two steps: an off-line processing step, which analyses the source text, and an on-line step, which executes when a user connects to the system with a web browser, moment at which the contents and hyperlinks are generated. The framework has been implemented as the Welkin system, which has been used to build three adaptive on-line information sites in a quick and easy way. Some controlled experiments have been performed with real users aimed to provide positive feedback on the implementation of the system.     

The semantic web as a Linguistic resource: Opportunities for natural language generation

This paper argues that, because the documents of the semantic web are created by human beings, they are actually much more like natural language documents than theory would have us believe. We present evidence that natural language words are used extensively and in complex ways in current ontologies. This leads to a number of dangers for the semantic web, but also opens up interesting new challenges for natural language processing. This is illustrated by our own work using natural language generation to present parts of ontologies.     

A statistical approach to the generation of a database for evaluating OCR software

In this paper we consider a statistical approach to augment a limited database of groundtruth documents for use in evaluation of optical character recognition software. A modified moving-blocks bootstrap procedure is used to construct surrogate documents for this purpose which prove to serve effectively and, in some regards, indistinguishably from groundtruth. The proposed method is validated through a rigorous statistical procedure. Received: March 30, 2000 / Revised: September 14, 2001     

Evaluation in the context of natural language generation

What role should evaluation play in the development of natural language generation ( ) techniques and systems? In this paper we describe what is involved in natural language generation, and survey how evaluation has figured in work in this area to date. We comment on the issues raised by this existing work and on how the problems of evaluation are different from the problems of evaluating work in natural languageunderstanding. The paper is concluded by suggesting a way forward by looking more closely at the component problems that are addressed in natural language generation research; a particular text generation application is examined and the issues that are raised in assessing its performance on a variety of dimensions are looked at.     

A natural language approach to content-based video indexing and retrieval for interactive e-learning

As a powerful and expressive nontextual media that can capture and present information, instructional videos are extensively used in e-learning (Web-based distance learning). Since each video may cover many subjects, it is critical for an e-learning environment to have content-based video searching capabilities to meet diverse individual learning needs. In this paper, we present an interactive multimedia-based e-learning environment that enables users to interact with it to obtain knowledge in the form of logically segmented video clips. We propose a natural language approach to content-based video indexing and retrieval to identify appropriate video clips that can address users' needs. The method integrates natural language processing, named entity extraction, frame-based indexing, and information retrieval techniques to explore knowledge-on-demand in a video-based interactive e-learning environment. A preliminary evaluation shows that precision and recall of this approach are better than those of the traditional keyword based approach.     

Generating model-based test cases from natural language requirements for space application software

Natural Language (NL) deliverables suffer from ambiguity, poor understandability, incompleteness, and inconsistency. Howewer, NL is straightforward and stakeholders are familiar with it to produce their software requirements documents. This paper presents a methodology, SOLIMVA, which aims at model-based test case generation considering NL requirements deliverables. The methodology is supported by a tool that makes it possible to automatically translate NL requirements into Statechart models. Once the Statecharts are derived, another tool, GTSC, is used to generate the test cases. SOLIMVA uses combinatorial designs to identify scenarios for system and acceptance testing, and it requires that a test designer defines the application domain by means of a dictionary. Within the dictionary there is a Semantic Translation Model in which, among other features, a word sense disambiguation method helps in the translation process. Using as a case study a space application software product, we compared SOLIMVA with a previous manual approach developed by an expert under two aspects: test objectives coverage and characteristics of the Executable Test Cases. In the first aspect, the SOLIMVA methodology not only covered the test objectives associated to the expert’s scenarios but also proposed a better strategy with test objectives clearly separated according to the directives of combinatorial designs. The Executable Test Cases derived in accordance with the SOLIMVA methodology not only possessed similar characteristics with the expert’s Executable Test Cases but also predicted behaviors that did not exist in the expert’s strategy. The key benefits from applying the SOLIMVA methodology/tool within a Verification and Validation process are the ease of use and, at the same time, the support of a formal method consequently leading to a potential acceptance of the methodology in complex software projects.     

A natural language generation approach to support understanding and traceability of multi-dimensional preferential sensitivity analysis in multi-criteria decision making

Multi-Criteria Decision Analysis (MCDA) enables decision makers (DM) and decision analysts (DA) to analyse and understand decision situations in a structured and formalised way. With the increasing complexity of decision support systems (DSSs), it becomes challenging for both expert and novice users to understand and interpret the model results. Natural language generation (NLG) techniques are used in various DSSs to cope with this challenge as they reduce the cognitive effort to achieve understanding of decision situations. However, NLG techniques in MCDA have so far mainly been developed for deterministic decision situations or one-dimensional sensitivity analyses. In this paper, a concept for the generation of textual explanations for a multi-dimensional preferential sensitivity analysis in MCDA is developed. The key contribution is a NLG approach that provides detailed explanations of the implications of preferential uncertainties in Multi-Attribute Value Theory (MAVT). It generates a report that assesses the influences of simultaneous or separate variations of inter-criteria and intra-criteria preferential parameters determined within the decision analysis. We explore the added value of the natural language report in an online survey. Our results show that the NLG approach is particularly beneficial for difficult interpretational tasks.     

Using a language independent domain model for multilingual information extraction

The volume of electronic text in different languages, particularly on the World Wide Web, is growing significantly, and the problem of users who are restricted in the number of languages they read obtaining information from this text is becoming more widespread. This article investigates some of the issues involved in achieving multilingual information extraction (IE), describes the approach adopted in the M-LaSIE-II IE system, which addresses these problems, and presents the results of evaluating the approach against a small parallel corpus of English/French newswire texts. The approach is based on the assumption that it is possible to construct a language independent representation of concepts relevant to the domain, at least for the small well-defined domains typical of IE tasks, allowing multilingual IE to be successfully carried out without requiring full machine translation.