Easily Identifiable Discourse Relations
نویسندگان
چکیده
We present a corpus study of local discourse relations based on the Penn Discourse Tree Bank, a large manually annotated corpus of explicitly or implicitly realized relations. We show that while there is a large degree of ambiguity in temporal explicit discourse connectives, overall connectives are mostly unambiguous and allow high-accuracy prediction of discourse relation type. We achieve 93.09% accuracy in classifying the explicit relations and 74.74% accuracy overall. In addition, we show that some pairs of relations occur together in text more often than expected by chance. This finding suggests that global sequence classification of the relations in text can lead to better results, especially for implicit relations.
منابع مشابه
Factors Influencing the Implicitation of Discourse Relations across Languages
Relations that hold between discourse segments can, but need not, be made explicit by means of discourse connectives. Even though the explicit signaling of discourse relations is optional, not all relations can be easily conveyed implicitly. It has been proposed that readers and listeners have certain expectations about discourse and that discourse relations that are in line with these expectat...
متن کاملUsing A Probabilistic Model Of Discourse Relations To Investigate Word Order Variation
Like speakers of any natural language, speakers of English potentially have many different word orders in which to encode a single meaning. One key factor in speakers’ use of certain non-canonical word orders in English is their ability to contribute information about syntactic and semantic discourse relations. Explicit annotation of discourse relations is a difficult and subjective task. In or...
متن کاملآیندهپژوهیِ تبارشناسانه (رویکردی شایسته در آیندهپژوهیِ پدیدههای جغرافیایی)
This article tries to focus on the genealogy of Foucault, and by putting it in connection with future studies, try to introduce genealogical future studies as a qualified methodology in geographical research. Accordingly, if the geographic space, relational space, and scenes role playing of discourses and relations of power and knowledge is considered, we face the object and subject of a discou...
متن کاملRepresentation Learning for Text-level Discourse Parsing
Text-level discourse parsing is notoriously difficult, as distinctions between discourse relations require subtle semantic judgments that are not easily captured using standard features. In this paper, we present a representation learning approach, in which we transform surface features into a latent space that facilitates RST discourse parsing. By combining the machinery of large-margin transi...
متن کاملImplicit Discourse Relation Recognition by Selecting Typical Training Examples
Implicit discourse relation recognition is a challenging task in the natural language processing field, but important to many applications such as question answering, summarizat ion and so on. Previous research used either art ificially created implicit discourse relat ions with connectives removed from explicit relations or annotated implicit relat ions as training data to detect the possible ...
متن کامل