We apply a decision tree based approach to pronoun resolution in spoken dialogue. Our system deals with pronouns with NPand non-NP-antecedents. We present a set of features designed for pronoun resolution in spoken dialogue and determine the most promising features. We evaluate the system on twenty Switchboard dialogues and show that it compares well to Byron’s (2002) manually tuned system.

Pronoun resolution is an uncertain process in machine oriented natural language processing. There are many techniques to determine the referent of the pronoun. This paper addresses the resolution of two pronouns. "they" and "them". and looks at simplistic rules to improve the process of determining the referent, beyond simply deciding tm the basis of most recent plural noun.

traditional work on pro-drop languages identified a set of parametric values ‎associated with the availability of null subjects, including the presence of null ‎expletive subjects. in the same vein, but more within the framework of minimalist ‎program, i will discuss while referential subjects may optionally be overt or covert ‎in the persian, expletives are obligatorily null. in this regard, a...

The ultimate aim of the following pages is to explore the hypothesis that sentences containing a pronoun be analyzed as involving a topic pronoun doubling relation in a way that closely parallels the one overtly realized in Clitic Left Dislocation (CLLD) and Hanging Topic (HT) structures in Italian/Romance. In a nutshell: when a pronoun is present in the clause, a silent doubled non-overt topic...

A visual-world eye-tracking experiment investigated the influence of order of mention and grammatical role on resolution of ambiguous pronouns in Finnish. According to the first-mention account, general cognitive structure-building processes make the firstmentioned noun phrase the preferred antecedent of an ambiguous pronoun. According to the subject-preference account, the preferred antecedent...

Despite some promising early approaches, neural networks have by now received comparatively little attention as a machine learning model for robust, corpus-based anaphor resolution. The work presented in this paper is intended to fill the apparent gap in research. Based on a hybrid algorithm that combines manually knowledge-engineered antecedent filtering rules with machine-learned preference c...

Abstract Previous evidence has implicated personal relevance as a predictive factor in lexical access. Westbury (2014) showed that personally relevant words were rated having higher subjective familiarity than not relevant, suggesting are processed more fluently less words. Here we extend this work by defining measure of does rely on human judgments but is rather derived from first-order co-occ...

Abstract Coreference processing of Control constructions and their pronoun-containing counterparts can be studied experimentally using priming or interference paradigms. We replicate findings in a study on non-finite Norwegian (Larsen & Johansson, 2020) contrast them with finite effects grammatical maze (G-maze) design. asked participants to read sentences word-by-word select the grammatica...