Slot Filling (SF) aims to extract the values of certain types of attributes (or slots, such as person:cities of residence) for a given entity from a large collection of source documents. In this paper we propose an effective DNN architecture for SF with the following new strategies: (1). Take a regularized dependency graph instead of a raw sentence as input to DNN, to compress the wide contexts...

The authors of Ferguson and Ponciano (2014) would like to correct the following errors found in the paper and online Supporting Information. These errors, however, do not affect the main analysis or the interpretation of our results in any manner. We would like to thank Michael Barfield for pointing these out. 1. On page 256, the second sentence in the second column should read “A negligible AR...

In an eye-tracking experiment we examined the risky reading hypothesis, in which long saccades and many regressions are considered to be indicative of a proactive reading style (Rayner et al. in Psychol Aging 21(3):448, 2006; Psychol Aging 24(3):755, 2009). We did so by presenting short texts-that confirmed or disconfirmed verb-based implicit causality expectations-to two types of readers: proa...

The present study examined whether abnormal cerebral control was evident in the lip movements of adult stutterers (AS) compared to non-stutterers (ANS), as demonstrated during speech and non-speech tasks. Electromyographic (EMG) activity during production of words with initial /f/ and /p/ phonemes, single-sentence production and lip pursing were measured. Differences between AS and ANS were evi...

This paper concerns itself with the relation between two important semantic notions: the traditional notion of proposition and a more recent notion of context as an information state. The notion of proposition has traditionally played an important role in the theory of meaning: propositions are entities that have independent truth conditions and act as the meaning of both independent and embedd...

Protein-protein interaction (PPI) identification is an integral component of many biomedical research and database curation tools. Automation of this task through classification is one of the key goals of text mining (TM). However, labelled PPI corpora required to train classifiers are generally small. In order to overcome this sparsity in the training data, we propose a novel method of integra...

In this paper, we propose a bigram based supervised method for extractive document summarization in the integer linear programming (ILP) framework. For each bigram, a regression model is used to estimate its frequency in the reference summary. The regression model uses a variety of indicative features and is trained discriminatively to minimize the distance between the estimated and the ground ...