Multilingual Discourse Processing
نویسندگان
چکیده
The goal of the work reported here is to provide a system for handling spoken dialogues which can be easily ported to new languages and new application areas. This work is being carried within the Dumas project, which aims to explore a number of approaches to this task. The particular approach described here involves involes constructing fairly traditional ‘logical forms’ on the basis of structural analyses of the input speech and then using a mixture of meaning postulates, which relate terms in the language to underlying concepts, and general domain knowledge in order to interpret and respond to what has been said.
منابع مشابه
MultiDPS - A multilingual Discourse Processing System
1 This paper presents an adaptable online Multilingual Discourse Processing System (MultiDPS), composed of four natural language processing tools: named entity recognizer, anaphora resolver, clause splitter and a discourse parser. This NLP Meta System allows any user to run it on the web or via web services and, if necessary, to build its own processing chain, by incorporating knowledge or reso...
متن کاملPragmatic Annotation of Discourse Markers in a Multilingual Parallel Corpus (Arabic- Spanish-English)
Discourse structure and coherence relations are one of the main inferential challenges addressed by computational pragmatics. The present study focuses on discourse markers as key elements in guiding the inferences of the statements in natural language. Through a rule-based approach for the automatic identification, classification and annotation of the discourse markers in a multilingual parall...
متن کاملCustomizing And Evaluating A Multilingual Discourse Module
In this papeh we first describe how we have customized our data-driven multilingu~fl discourse module within our text understanding system lor dill'erent lm~guages and for a particular NLP application by utilizing hierm'chic~dly organized discourse KB's. Then, we report qum~titalive and qmditative findings from ewduating the system both with and without discourse processing, ~md discuss how res...
متن کاملA Language-Independent Anaphora Resolution System for Understanding Multilingual Texts
This paper describes a new discourse module within our multilingual NLP system. Because of its unique data-driven architecture, the discourse module is language-independent. Moreover, the use of hierarchically organized multiple knowledge sources makes the module robust and trainable using discourse-tagged corpora. Separating discourse phenomena from knowledge sources makes the discourse module...
متن کاملNominal Expressions in Multilingual Corpora: Definites and Demonstratives
This paper presents the results of a multilingual corpus study on definite descriptions and demonstrative noun phrases. The analysis made on a parallel corpus (French and Portuguese) reinforces previous findings regarding the predominance of non-anaphoric uses of definite descriptions in English corpus. It is also shown that the use of demonstrative noun phrases, on the other hand, is more regu...
متن کاملExtracting Directional and Comparable Corpora from a Multilingual Corpus for Translation Studies
Translation studies rely more and more on corpus data to examine specificities of translated texts, that can be translated from different original languages and compared to original texts. In parallel, more and more multilingual corpora are becoming available for various natural language processing tasks. This paper questions the use of these multilingual corpora in translation studies and show...
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 2004