Abstract Although many studies modelled writing quality by analysing basic skills (spelling, grammar, etc.), few focused on top-down compositional strategies at the discourse level. We propose that using both narrative and argument modes in an argumentative essay (a multi-discourse mode [MDM] strategy) capitalizes their complementary advantages, yielding higher essays. tested whether MDM strate...

We propose an unsupervised Expectation Maximization approach to pronoun resolution. The system learns from a fixed list of potential antecedents for each pronoun. We show that unsupervised learning is possible in this context, as the performance of our system is comparable to supervised methods. Our results indicate that a probabilistic gender/number model, determined automatically from unlabel...

We describe a system for contextually appropriate anaphor and pronoun generation for Turkish. It uses Binding Theory and Centering Theory to model local and nonlocal reference. We describe the rules for Turkish, and their computational treatment. A cascaded method for anaphor and pronoun generation is proposed for handling pro-drop and discourse constraints on pronominalization. The system has ...

Abstract We investigate the hypothesis that a pronoun is used in discourse, when its antecedent is in the focus of the discourse. We create a corpus of ‘replaced anaphoric definite descriptions’, where occurrences of definite descriptions are replaced with a corresponding pronoun. We use the Lappin and Leass (1994) anaphora resolution algorithm on the new corpus, and obtain a much lower perform...

This paper presents baseline models for the cross-lingual pronoun prediction task and the pronoun-focused translation task at DiscoMT 2015. We present simple yet effective classifiers for the former and discuss the impact of various contextual features on the prediction performance. In the translation task we rely on the document-level decoder Docent and a cross-sentence target language-model o...

This thesis describes SwePron, an algorithm for automatic resolution of pronouns in Swedish, using Mitkov’s algorithm for pronoun resolution in English (MARS) as a starting point. There are several changes made to the algorithm in order to adapt it to the Swedish language. One key language difference is that Swedish has two “neutral” genders, whereas English only has one. A second important dif...

Haspelmath 1997 poses a challenge for current theories of indefinites. Extensive data from 40 languages show there are too many differences between indefinite pronoun series to account for with the usual machinery for indefinites. For instance, we can take Russian as an example: below are 4 main Russian indefinite pronoun series. There are at least 4 other series unlisted in (1), and Bylinina &...

This paper presents a supervised pronoun anaphora resolution system based on factorial hidden Markov models (FHMMs). The basic idea is that the hidden states of FHMMs are an explicit short-term memory with an antecedent buffer containing recently described referents. Thus an observed pronoun can find its antecedent from the hidden buffer, or in terms of a generative model, the entries in the hi...

We report on a written measure of multiplicative double counting (mDC), form children’s reasoning. Our aim is to apply theory students’ cognition validate for grade 3–8 students as proxy interviewing. The 4-item consists hint-free and hint-containing word-problems, following the fine-grain method that distinguishes prompt-dependent from prompt-independent stage. Using mixed methods, we analyzed...