In this paper we compare two Machine Learning approaches to the task of pronominal anaphora resolution: a conventional classification system based on C5.0 decision trees, and a novel perceptron-based ranker. We use coreference links annotated in the Prague Dependency Treebank 2.0 for training and evaluation purposes. The perceptron system achieves f-score 79.43% on recognizing coreference of pe...

The paper introduces Treex CR, a coreference resolution (CR) system not only for Czech. As its name suggests, it has been implemented as an integral part of the Treex NLP framework. The main feature that distinguishes it from other CR systems is that it operates on the tectogrammatical layer, a representation of deep syntax. This feature allows for natural handling of elided expressions, e.g. u...

Despite the popularity of coreference resolution as a research topic, the overwhelming majority of the work in this area focused so far on single antecedence coreference only. Multiple antecedent coreference (MAC) has been largely neglected. This can be explained by the scarcity of the phenomenon of MAC in generic discourse. However, in specialized discourse such as patents, MAC is very dominan...

Signed languages display a variety of pointing signs that serve the functions of deictic and anaphoric pronouns, possessive and reflexive pronouns, demonstratives, locatives, determiners, body part labels, and verb agreement. We consider criteria for determining the linguistic status of pointing signs. Among those criteria are conventionality, indexicality, phonological compositionality, being ...

This paper describes and evaluates the automatic grammatical annotation of a chat and an e-mail corpus of together 117 million words, using a modular Constraint Grammar system. We discuss a number of genre-specific issues, such as emoticons and personal pronouns, and offer a linguistic comparison of the two corpora with corresponding annotations of the Europarl corpus and the spoken and written...

In this paper, we investigate the acoustic prosodic marking of demonstrative and personal pronouns in taskoriented dialog. Although it has been hypothesized that acoustic marking affects pronoun resolution, we find that the prosodic information extracted from the data is not sufficient to predict antecedent type reliably. Interspeaker variation accounts for much of the prosodic variation that w...