Abstract
Lately, discourse structure has received considerable attention due to the benefits its application offers in several NLP tasks such as opinion mining, summarization, question answering, text simplification, among others. When automatically analyzing texts, discourse parsers typically perform two different tasks: i) identification of basic discourse units (text segmentation) ii) linking discourse units by means of discourse relations, building structures such as trees or graphs. The resulting discourse structures are, in general terms, accurate at intra-sentence discourse-level relations, however they fail to capture the correct inter-sentence relations. Detecting the main discourse unit (the Central Unit) is helpful for discourse analyzers (and also for manual annotation) in improving their results in rhetorical labeling. Bearing this in mind, we set out to build the first two steps of a discourse parser following a top-down strategy: i) to find discourse units, ii) to detect the Central Unit. The final step, i.e. assigning rhetorical relations, remains to be worked on in the immediate future. In accordance with this strategy, our paper presents a tool consisting of a discourse segmenter and an automatic Central Unit detector.
Highlights
Our linguistic understanding about how to exploit the discourse properties of a text has grown in many ways, as described by [1]
Some disagreements in relations are a consequence of a lack of agreements in the attachment locus which happens to be greater at inter-sentential level
With the future objective of developing a complete discourse parser, this work aims to build and evaluate automatic discourse segmentation and Central Unit detector based on neural networks, in order to use this partial parser in different NLP tasks: i) summarization [2], ii) complex question answering [3] iii) opinion mining [4] and sentiment analysis [5,6,7] iv) evaluation of scholars’ summaries [34]
Summary
Our linguistic understanding about how to exploit the discourse properties of a text has grown in many ways, as described by [1]. Discourse parsing is a very challenging task and several authors have shown that discourse structure is crucial in obtaining a better understanding of texts. Exploiting discourse structure information adequately could be the key to improving different NLP tasks such as: i) summarization [2], ii) complex question answering [3] iii) opinion mining [4] and sentiment analysis [5,6,7]. Our approach to discourse here follows Rhetorical Structure Theory (RST) [8], a discourse theory that describes coherence of a text with rhetorical relations between text-spans forming a hierarchical discourse tree (RS-tree).
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
