Syntactic parsers perform poorly in prediction of Argument-Cluster Coordination (ACC). We change the PTB representation of ACC to be more suitable for learning by a statistical PCFG parser, affecting 125 trees in the training set. Training on the modified trees yields a slight improvement in EVALB scores on sections 22 and 23. The main evaluation is on a corpus of 4th grade science exams, in wh...

This paper describes our work which is based on discovering context for text document categorization. The document categorization approach is derived from a combination of a learning paradigm known as relation extraction and an technique known as context discovery. We demonstrate the effectiveness of our categorization approach using reuters 21578 dataset and synthetic real world data from spor...

the kalila & dimna is considered as one of the beautiful collections of stories written in the field of philosophy and politics. in other words, animals used in this book as symbols have incurred much impact and at the same time could keep the actual intentions of the author hidden. one of the fables in this book is about a lion and jackals that show how their hostilities turn into friendship. ...

Language processing tools suffer from significant performance drops in social media domain due to its continuously evolving language. Transforming non-standard words into their standard forms has been studied as a step towards proper processing of ill-formed texts. This work describes a normalization system that considers contextual and lexical similarities between standard and non-standard wor...

In this research, we present the concept of Hyperaudio as non-linear presentation of auditory information in the context of underlying theoretical assumptions of how Hyperaudio differs from existing non-linear information media. We present a study comparing text and auditory represented information either in a linear or non-linear manner and the interaction of these presentation formats with di...

We consider a challenging clustering task: the clustering of multi-word terms without document co-occurrence information in order to form coherent groups of topics. For this task, we developed a methodology taking as input multi-word terms and lexico-syntactic relations between them. Our clustering algorithm, named CPCL is implemented in the TermWatch system. We compared CPCL to other existing ...

Discovering the interactions between the persons mentioned in a set of topic documents can help readers construct the background of the topic and facilitate document comprehension. To discover person interactions, we need a detection method that can identify text segments containing information about the interactions. Information extraction algorithms then analyze the segments to extract intera...

Traditional plan recognition systems try to recognize a user's domain plan from the user's queries. In contrast, the Interactive Discourse Planner (IDP) tries to recognize an expansion of its own text plan from the user's queries. During interaction, IDP builds a text plan in reaction to user feedback that it uses as the discourse context. IDP uses this text plan to analyze user questions for i...