MultiDPS - A multilingual Discourse Processing System
نویسنده
چکیده
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 resources for each tool for the desired language. In this paper is presented a brief description for each independent module, and a case study in which the system is adapted to five different languages for creating a multilingual summarization system.
منابع مشابه
Customizing 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 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 کاملMultilingual summarization system based on analyzing the discourse structure at MultiLing 2013
This paper describes the architecture of UAIC 1 ’s Summarization system participating at MultiLing – 2013. The architecture includes language independent text processing modules, but also modules that are adapted for one language or another. In our experiments, the languages under consideration are Bulgarian, German, Greek, English, and Romanian. Our method exploits the cohesion and coherence p...
متن کاملDiscourse Processing of Dialogues with Multiple Threads
In this paper we will present our ongoing work on a plan-based discourse processor developed in the context of the Enthusiast Spanish to English translation system as part of the JANUS multilingual speech-to-speech translation system. We will demonstrate that theories of discourse which postulate a strict tree structure of discourse on either the intentional or attentional level are not totally...
متن کامل