Coreference and antecedent representation across languages.

Coreference and antecedent representation across languages.

Previous studies have shown that speakers of languages such as German, Spanish, and French reactivate the syntactic gender of the antecedent of a pronoun to license gender agreement. As syntactic gender is assumed to be stored in the lexicon, this has motivated the claim that pronouns in these languages reactivate the lexical entry of their antecedent noun. In contrast, in languages without syn...

Metacognitive (Rending) Strategies Across Languages and Techniques

Coreference Resolution across Corpora: Languages, Coding Schemes, and Preprocessing Information

This paper explores the effect that different corpus configurations have on the performance of a coreference resolution system, as measured by MUC, B3, and CEAF. By varying separately three parameters (language, annotation scheme, and preprocessing information) and applying the same coreference resolution system, the strong bonds between system and corpus are demonstrated. The experiments revea...

Knowledge-lean projection of coreference chains across languages

Common technologies for automatic coreference resolution require either a language-specific rule set or large collections of manually annotated data, which is typically limited to newswire texts in major languages. This makes it difficult to develop coreference resolvers for a large number of the so-called low-resourced languages. We apply a direct projection algorithm on a multi-genre and mult...

Learning Anaphoricity and Antecedent Ranking Features for Coreference Resolution

We introduce a simple, non-linear mention-ranking model for coreference resolution that attempts to learn distinct feature representations for anaphoricity detection and antecedent ranking, which we encourage by pre-training on a pair of corresponding subtasks. Although we use only simple, unconjoined features, the model is able to learn useful representations, and we report the best overall sc...