We describe the design, the evaluation setup, and the results of the DiscoMT 2015 shared task, which included two subtasks, relevant to both the machine translation (MT) and the discourse communities: (i) pronoun-focused translation, a practical MT task, and (ii) cross-lingual pronoun prediction, a classification task that requires no specific MT expertise and is interesting as a machine learni...

In Korean, in order to generate a coherent text, a redundantly prominent noun should be replaced by a non-zero pronoun or zero pronoun. Otherwise, the text becomes unnatural. Specifically, a redundant noun in Korean is frequently omitted while a redundant noun in English is replaced by a pronoun. This paper proposes a generation algorithm of the zero pronoun, using a Cost-based Centering Model ...

An embodied language-learning system is presented that can learn the correct deictic meanings for the words “I” and “you.” The system uses contextual clues from already understood words and sensory information from its environment to determine the most likely grounding for a new word. The system also serves as a model for the phenomenon of pronoun reversal among congenitally blind children, as ...

Some interpersonal verbs, such as admire and amaze, describe an action or property of one person (the reactor) that is necessarily a response to an action or property of another (the initiator). We hypothesized that these verbs make the initiator relatively more accessible in a comprehender's discourse model and that this change in relative accessibility aids identification of the referent of a...

Beginning with the observation that syntactic and semantic information often coincide (i.e., subjects are often agents, objects often patients), this study investigates the possibility that preference to resolve a sentence-initial pronoun to a syntactically prominent antecedent might actually be better explained in terms of preference for resolving to a semantically prominent antecedent. The st...

The production and interpretation of pronouns involves the identification of a mental referent and, in connected speech or text, a discourse antecedent. One of the few overt signals of the relationship between a pronoun and its antecedent is agreement in features such as number and grammatical gender. To examine how speakers create these signals, two experiments tested conceptual, lexical, and ...

This paper investigates the problem of Chinese zero pronoun resolution. Most existing approaches are based on machine learning algorithms, using hand-crafted features, which is labor-intensive. Moreover, semantic information that is essential in the resolution of noun phrases has not been addressed enough by previous approaches on zero pronoun resolution. This is because that zero pronouns have...

Children's poor performance on object relative clauses has been explained in terms of intervention locality. This approach predicts that object relatives with a full DP head and an embedded pronominal subject are easier than object relatives in which both the head noun and the embedded subject are full DPs. This prediction is shared by other accounts formulated to explain processing mechanisms....