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.     

Ontological and linguistic metamodelling revisited: A language use approach

ContextAlthough metamodelling is generally accepted as important for our understanding of software and systems development, arguments about the validity and utility of ontological versus linguistic metamodelling continue.ObjectiveThe paper examines the traditional, metamodel-focused construction of modelling languages in the context of language use, and particularly speech act theory. These concepts are then applied to the problems introduced by the “Orthogonal Classification Architecture” that is often called the ontological/linguistic paradox. The aim of the paper is to show how it is possible to overcome these problems.MethodThe paper adopts a conceptual–analytical approach by revisiting the published arguments and developing an alternative metamodelling architecture based on language use.ResultsThe analysis shows that when we apply a language use perspective of meaning to traditional modelling concepts, a number of incongruities and misconceptions in the traditional approaches are revealed – issues that are not evident in previous work based primarily on set theory. Clearly differentiating between the extensional and intensional aspects of class concepts (as sets) and also between objects (in the social world) and things (in the physical world) allows for a deeper understanding to be gained of the relationship between the ontological and linguistic views promulgated in the modelling world.ConclusionsWe propose that a viewpoint that integrates language use ideas into traditional modelling (and metamodelling) is vital, and stress that meaning is not inherent in the physical world; meaning, and thus socially valid objects, are constructed by use of language, which may or may not establish a one-to-one correspondence relationship between objects and physical things.     

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.     

Formalising natural language specifications using a cognitive linguistic/configuration based approach

This paper addresses the problem of transforming business specifications written in natural language into formal models suitable for use in information systems development. It proposes a method for transforming controlled natural language specifications based on the Semantics of Business Vocabulary and Business Rules standard. This approach is unique in combining techniques from Model-Driven Engineering (MDE), Cognitive Linguistics, and Knowledge-based Configuration, which allows the reliable semantic processing of specifications and integration with existing MDE tools to improve productivity, quality, and time-to-market in software development. The method first learns the vocabulary of the specification from glossary-like definitions then parses the rules of the specification and outputs the resulting formal SBVR model. Both aspects of the method are tested separately, with the system correctly learning 98% of the vocabulary and correctly interpreting 98% of the rules of an SBVR SE based example. Finally, the proposed method is compared to state-of-the-art approaches for creating formal models from natural language specifications, arguing that it meets the criteria necessary to fulfil the three goals of (1) shifting control of specification to non-technical business experts, (2) reducing the manual effort involved in formalising specifications, and (3) supporting business experts in creating well-formed sets of business vocabularies and rules.     

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.     

Knowledge-intensive natural language generation

The development of natural language interfaces to artificial intelligence systems is dependent on the representation of knowledge. A major impediment to building such systems has been the difficulty in adding sufficient linguistic and conceptual knowledge to extend and adapt their capabilities. This difficulty has been apparent in systems that perform the task of language production, i.e., the generation of natural language output to satisfy the communicative requirements of a system.A uniform, parsimonious representation of knowledge about language can increase extensibility and efficiency as well as simplify the generation process. The Ace framework applies knowledge representation fundamentals to the task of encoding knowledge about language. Within this framework, linguistic and conceptual knowledge are organized into hierarchies, and structured associations are used to join knowledge structures that are metaphorically related or otherwise used in linguistic expression. These structured associations permit specialized linguistic knowledge to derive partially from more abstract knowledge, facilitating the use of abstractions in generating specialized phrases. A simple generator called KING (Knowledge INtensive Generator) uses an Ace knowledge base to produce utterances from their conceptual representation.     

自然语言生成综述

自然语言生成(NLG)技术利用人工智能和语言学的方法来自动地生成可理解的自然语言文本.NLG降低了人类和计算机之间沟通的难度,被广泛应用于机器新闻写作、聊天机器人等领域,已经成为人工智能的研究热点之一.首先,列举了当前主流的NLG的方法和模型,并详细对比了这些方法和模型的优缺点;然后,分别针对文本到文本、数据到文本和图...     

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.     

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.     

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.     

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