Findings from various domains suggest that predictability is an important component of language processing. We report psycholinguistic research suggesting that predictability also influences referential processing, in the form of reduced acoustic durations for predictable referents. However, we do not find evidence that predictability directly influences likelihood of pronominalization, contrar...

We present a novel model for the task of joint mention extraction and classification. Unlike existing approaches, our model is able to effectively capture overlapping mentions with unbounded lengths. The model is highly scalable, with a time complexity that is linear in the number of words in the input sentence and linear in the number of possible mention classes. Our model can be extended to a...

Previous approaches to pronominalization have largely been theoretical rather than applied in nature. Frequently, such methods are based on Centering Theory, which deals with the resolution of anaphoric pronouns. But it is not clear that complex theoretical mechanisms, while having satisfying explanatory power, are necessary for the actual generation of pronouns. We first illustrate examples of...

This paper presents a quantitative and qualitative error analysis of Russian anaphora resolvers which participated in the RU-EVAL event. Its aim is to identify and characterize a set of challenging errors common to stateof-the-art systems dealing with Russian. We examined three types of pronouns: 3rd person pronouns, reflexive and relative pronouns. The investigation has shown that a high level...

Pronouns are commonly used instead of explicitly repeating a name, and, in many cases, we comprehend language faster when pronouns are used instead of repetitive references. This is surprising because pronouns are often ambiguous, whereas repeated names provide precise reference. We used functional MRI to investigate the neural correlates of this paradoxical preference. Reading repeated names e...

In a Hindi to Bengali transfer based machine translation system the baseline lexical transfer module replaces a Hindi word by its most frequent Bengali translation. Some pronouns in Hindi can have multiple translations in Bengali. The choices of actual translations have big impact on the accessibility of the translated sentence. The list of Hindi pronouns is small and their corresponding Bengal...

Findings from various domains suggest that predictability is an important component of language processing. We report two psycholinguistic experiments demonstrating that predictability also influences referential processing, in the form of reduced acoustic durations for predictable referents. However, we do not find evidence that predictability directly influences the likelihood of pronominaliz...

Entity detection and tracking (EDT) is the task of identifying textual mentions of real-world entities in documents, extending the named entity detection and coreference resolution task by considering mentions other than names (pronouns, definite descriptions, etc.). Like NE tagging and coreference resolution, most solutions to the EDT task separate out the mention detection aspect from the cor...

1. Introduction Resolving zero pronouns is a major problem in developing a natural language understanding (NLU) system for Thai. Since subject and object pronouns in Thai can be omitted from a sentence, an NLU system must be capable of identifying the missing subjects or objects in the sentence. This process of identifying referents for zero pronouns, which is a part of referent resolution 1 pr...