This work introduces a machine learning approach to the identification of mention heads needed for multilingual coreference resolution (MCR). We evaluate the method and compare it to a heuristic baseline and a rule-based approach, which are widely used in coreference resolution systems. We use the CoNLL-2012 shared task data sets, which include data for Arabic, Chinese, and English. We show tha...

The relationship between pronoun production and interpretation has been proposed to follow Bayesian principles, combining a comprehender’s expectation about which referent will be mentioned next their estimate of how likely it is that potential re-mentioned using pronoun. Model received support from studies in several languages (English, Mandarin Chinese, Catalan, German), but tested contexts h...

The traditional mention-pair model for coreference resolution cannot capture information beyond mention pairs for both learning and testing. To deal with this problem, we present an expressive entity-mention model that performs coreference resolution at an entity level. The model adopts the Inductive Logic Programming (ILP) algorithm, which provides a relational way to organize different knowle...

We develop a uniform analysis of single-wh and multiple-wh questions couched in dynamic inquisitive semantics. The captures the effects number marking on which-phrases, derives both mention-some mention-all readings as well an often neglected partial reading questions.

This work proposes a case-based classifier to tackle the gene/protein mention problem in biomedical literature. The so called gene mention problem consists of the recognition of gene and protein entities in scientific texts. A classification process aiming at deciding if a term is a gene mention or not is carried out for each word in the text. It is based on the selection of the best or most si...

We tackle the task of extracting tweets that mention a specific event from all tweets that contain relevant keywords, for which the main challenges include unbalanced positive and negative cases, and the unavailability of manually labeled training data. Existing methods leverage a few manually given seed events and large unlabeled tweets to train a classifier, by using expectation regularizatio...

The research question treated in this paper is centered on the idea of exploiting rich resources of one language to enhance the performance of a mention detection system of another one. We successfully achieve this goal by projecting information from one language to another via a parallel corpus. We examine the potential improvement using various degrees of linguistic information in a statistic...