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 ...

In this paper, we describe the treatment of extraction in HaG, an emerging computational grammar of Hausa, concentrating on the intricate patterns of interaction between resumptive and gap strategies. We shall argue with Tuller (1986) that Hausa resumption (both overt and covert) opens up the possibility for relativisation only to escape well-attested extraction islands in the language. As sugg...

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 ...

We present an experimental investigation of the role of resumptive pronouns. We investigate object extraction in wh-questions for a range of syntactic configurations (non-islands, weak islands, strong islands) and for multiple levels of embedding (single, double, and triple). In order to establish the crosslinguistic properties of resumption, parallel experiments are conducted in three language...

Introduction It is well known that so-called ergative languages are classified roughly into two groups: those which show an ergative pattern only at the morphological level and those which exhibit an ergative pattern also at the syntactic level. Syntactic ergativity is a curious phenomenon in the following respects. First, while there is apparently some correlation between morphological and syn...

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...

We present a cognitive computational model of pronoun resolution that reproduces the human interpretation preferences of the Subject Assignment Strategy and the Parallel Function Strategy. Our model relies on a probabilistic pronoun resolution system trained on corpus data. Factors influencing pronoun resolution are represented as features weighted by their relative importance. The importance t...

We present an automatic approach to determining whether a pronoun in text refers to a preceding noun phrase or is instead nonreferential. We extract the surrounding textual context of the pronoun and gather, from a large corpus, the distribution of words that occur within that context. We learn to reliably classify these distributions as representing either referential or non-referential pronou...