Adapting and Extending Lexical Resources in a Dialogue System
نویسندگان
چکیده
$EVWUDFW This paper presents the adaptation and customization of two lexical resources: Brill tagger, Brill (1992), and EuroWordNet, Vossen et al. (1998), to be used in the ADVICE project devoted to build an intelligent virtual reality sales and service system that uses human language technology. The work described in this paper is comprised in the ADVICE 1 project, which consists of the development of a new interface for a craftsmanship tools e-commerce system. With the aim of providing full support to customers of online shops and to the users of electronic services on the Internet during the complete customer service lifecycle; the ADVICE system will provide: An advanced multimedia user interface supporting natural language text input and output, as well as an animated assistant, that ensures a high level of user-system interaction. A software environment for building intelligent sales assistants for two types of selling and marketing services: sales-service and after sales service. The virtual assistant supported by this application will be capable of interacting with the user in natural language, adapt its recommendations to the requirements and characteristics of the customers and provide explanations of the advised products as well as of the different interesting alternatives. The dialogue is focussed on accomplishing a specific task, ordering products in an e-commerce system as well as getting advice about those products. The complexity of this domain lies in the broad product range with specialization of the crafts for particular tasks and applications. One of the main aspects of the buying-selling interaction in the web is the capability of the web site of generating some kind of trust feeling in the buyer, just like a human shop assistant would do in a person-to-person interaction. Things like understanding the buyer needs, being able to give him technical advice, assisting him in the final decision are not easy things to achieve in a web selling site. Natural language (NL) techniques can play a crucial role in providing this kind of enhancements. Another good motivation to integrate natural language technology in this kind of sites is to make the interaction easy to those people less confident with the Internet or even computer technologies. Inexperienced users feel much more comfortable expressing themselves and receiving information in natural language rather than through the human standard ways. An ADVICE project objective is to build a generic language processing component following a language engineering approach, that is, to achieve …
منابع مشابه
Adapting Lexical Chaining to Summarize Conversational Dialogues
We present a system for summarizing transcripts of conversational dialogues based on lexical chaining. The experiments were carried out with twenty Switchboard dialogues (LDC, 1993). We designed and implemented four summarization methods employing lexical chains as their source representation. The summarization task is defined as extracting the most relevant utterances conveying the meaning of ...
متن کاملExperiments on Building Language Resources for Multi-Modal Dialogue Systems
The paper presents the experiments made to adapt and to synchronise the linguistic resources of the French language processing modules integrated in the MIAMM prototype, designed to handle multi-modal human-machine interactions. These experiments allowed us to identify a methodology for adapting multilingual resources for a dialogue system. In the paper, we describe the iterative joint process ...
متن کاملCombining Word Sense and Usage for Modeling Frame Semantics
Models of lexical semantics are core paradigms in most NLP applications, such as dialogue, information extraction and document understanding. Unfortunately, the coverage of currently available resources (e.g. FrameNet) is still unsatisfactory. This paper presents a largely applicable approach for extending frame semantic resources, combining word sense information derived fromWordNet and corpus...
متن کاملReuse of linguistic resources in MT
Machine translation (MT) draws more heavily on lexical resources than most other NLP applications. First, grammars of both source and target languages require lexicons. Second, some sort of mapping between lexicons is required in order to transfer information from a source to a target language. The MT system described here is based on Shake-and-Bake technology and uses lexical transfer as the i...
متن کاملDevelopment of Fluency, Accuracy, and Complexity in Productive Skills of EFL learners across Gender and Proficiency: A Chaos Complexity Approach
This study was an attempt to investigate the developmental rate of fluency, accuracy and complexity among 12 EFL learners within the framework of chaos complexity theory. To carry out this study, 6 female and 6 male participants in two levels of proficiency (pre-and upper-intermediate) were put in two classes taught by the same teacher and following the same course. Every two months (for a peri...
متن کاملMorphological parsing of Swahili using crowdsourced lexical resources
We describe a morphological analyzer for the Swahili language, written in an extension of XFST/LEXC intended for the easy declaration of morphophonological patterns and importation of lexical resources. Our analyzer was supplemented extensively with data from the Kamusi Project (kamusi.org), a user-contributed multilingual dictionary. Making use of this resource allowed us to achieve wide lexic...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2001