The Idiap NLP Group has participated in both DiscoMT 2015 sub-tasks: pronounfocused translation and pronoun prediction. The system for the first sub-task combines two knowledge sources: grammatical constraints from the hypothesized coreference links, and candidate translations from an SMT decoder. The system for the second sub-task avoids hypothesizing a coreference link, and uses instead a lar...

We extend Zhao and Ng's (2007) Chinese anaphoric zero pronoun resolver by (1) using a richer set of features and (2) exploiting the coreference links between zero pronouns during resolution. Results on OntoNotes show that our approach significantly outperforms two state-of-the-art anaphoric zero pronoun resolvers. To our knowledge, this is the first work to report results obtained by an end-toe...

Event anaphora resolution plays a critical role in discourse analysis. This paper proposes a tree kernel-based framework for event pronoun resolution. In particular, a new tree expansion scheme is introduced to automatically determine a proper parse tree structure for event pronoun resolution by considering various kinds of competitive information related with the anaphor and the antecedent can...

In a language that allows null pronouns, why would a speaker bother to use an overt pronoun at all? A traditional answer is that an overt pronoun contains agreement information necessary for the identification of its antecedent. But this cannot possibly be the answer in languages like Turkish, which has subject-verb agreement, but no gender; since the verb already indicates the person and numbe...

Kehler and Rohde (2013) proposed a Bayesian theory of pronoun interpretation where the influence of world knowledge emerges as effects on the prior and the influence of information structure as effects on the likelihood: P(referent|pronoun) μ P(pronoun|referent)P(referent). Here we present two experiments on Mandarin Chinese that allow us to test the generality of the theory for a language with...

There are two main approaches to the problem of donkey anaphora (e.g. John owns a donkey. He beats it). Proponents of Discourse Representation Theory (Kamp 1981, Heim 1982) revise quantification so as to allow an existential quantifier to bind a pronoun which is not within its syntactic scope which yields a formal link between the quantifier and the pronoun, as is illustrated in (1)a. By contra...

Online reference books may be thought of as knowledge bases. We describe here how information in the text of machine-readable dictionary entries can be processed to help determine the proper attachment of prepositional phrases and relative clauses; the resolution of some cases of pronoun reference; and the interpretation of dangling modifiers. This approach also suggests the possibility of bypa...

This paper applies resolution theorem proving to natural language semantics. The aim is to circumvent the computational complexity triggered by natural language ambiguities like pronoun binding, by interleaving pronoun binding with resolution deduction. To this end, disambiguation is only applied to expressions that actually occur during derivations. Given a set of premises and a conclusion, ou...

A computer grammar is described which includes most of the English relative-clause constructions. It is written in the form of a left-to-right phrase-structure grammar with discontinuous constituents and subscripts, which carry such syntactic restrictions as number and verb government category. The motivation for the hierarchy of syntactic choices and for the use of discontinuous constituents i...

For some language pairs, pronoun translation is a discourse-driven task which requires information that lies beyond its local context. This motivates the task of predicting the correct pronoun given a source sentence and a target translation, where the translated pronouns have been replaced with placeholders. For crosslingual pronoun prediction, we suggest a neural network-based model using pre...