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...

Even advanced Spanish speakers of second language English tend to confuse the pronouns ‘he’ and ‘she’, often without even noticing their mistake (Lahoz, 1991). A study by AntónMéndez (2010) has indicated that a possible reason for this error is the fact that Spanish is a pro-drop language. In order to test this hypothesis, we used an extension of Dual-path (Chang, 2002), a computational cogniti...

In order to produce coherent text, natural language generation systems must have the ability to generate pronouns in the appropriate places. In the past, pronoun usage was primarily investigated with respect to the accessibility of referents. That is, it was assumed that a pronoun should be generated whenever the referent was sufficiently accessible so as to make its resolution easy. We found t...

We present our submission to the crosslingual pronoun prediction (CLPP) shared task for English-German and EnglishFrench at the First Conference on Machine Translation (WMT16). We trained a Maximum Entropy (MaxEnt) classifier based on features from Wetzel et al. (2015), that we adapted to the new task and applied to a new language pair. Additional features such as n-grams of the pronoun context...

We used event-related functional magnetic resonance imaging (erfMRI) to investigate the neural basis of biological and syntactic gender integration during pronoun processing in German sentences about persons or things. German allows for separating both processes experimentally. Overall, syntactic processing activated areas adjacent to Broca's area (BA 44), whereas processing of the biological s...

Appeared in: N.V. Murray, editor, Automated Reasoning with Analytic Tableaux and Related Methods (TABLEAUX’99), Lecture Notes in Artificial Intelligence 1617, Springer, pages 247–262, 1999. We present a tableau calculus for reasoning in fragments of natural language. We focus on the problem of pronoun resolution and the way in which it complicates automated theorem proving for natural language ...