This paper explores the effect of using multitask learning for abstractive summarization in the context of small training corpora. In particular, we incorporate four different tasks (extractive summarization, language modeling, concept detection, and paraphrase detection) both individually and in combination, with the goal of enhancing the target…

The increasing amount of available subjective text data in internet such as product reviews, movie critiques and social media comments provides golden opportunities for information retrieval researchers to extract useful information out of such datasets. Topic modeling and sentiment analysis are two widely researched fields that separately try to…

The present study is intended to critically examine metadiscourse markers in 24 master thesis abstracts. Twelve of them are written by non-native Iraqi female students and the rest by native American female students. To do so, the researchers have set two aims: examining the types and subtypes of metadiscourse markers in terms of nativity and…

This work covers topics in event coreference and event classification from spoken conversation. Event coreference is the process of identifying descriptions of the same event across sentences, documents, or structured databases. Existing event coreference work focuses on sentence similarity models or feature based similarity models requiring slot…

Online discussion forums have become popular in recent times. They provide a platform for people from different parts of the world sharing a common interest to come together and topics of mutual interest and seek solutions to their problems. There are hundreds of thousands of internet forums containing tens of millions of discussion threads and…

A framework is presented to document the process of category development. This two-dimensional model designed to facilitate the documentation of procedures used to generate categories specifies components associated with the development of categories and addresses the temporal aspects of category development. A study of preservice teachers…

Proposes a model for digital library and hypermedia organizations that is adaptive, providing different conceptual orderings to support browsing for different individuals' or groups' needs. Highlights include types of links, document ordering and the Gray code (a binary programming code), adaptive classification, and an economic model for document…

Describes the development of a software system, SIMPR (Structured Information Management: Processing and Retrieval), that will process documents by indexing them and classifying their subjects. Topics discussed include information storage and retrieval, file inversion techniques, modelling the user, natural language searching, automatic indexing,…

Describes the development and outcome of a cooperative computerization effort involving nine public and university museums. The discussion covers the project goals, data development and analysis, and contributions resulting form the project. Appendices provide the system data fields used and a comparison between automation of library and museum…

RESULTS ARE REPORTED OF A STUDY OF THE FEASIBILITY OF A NATIONAL ADULT EDUCATION INFORMATION CENTER, IN WHICH IT WAS PROPOSED TO (1) STUDY INFORMATION PROBLEMS AND RESOURCES IN ADULT EDUCATION AND RECOMMEND NEW SERVICES WHICH WOULD BE MOST USEFUL TO THE FIELD , (2) DEVELOP THE TOOLS OF SUBJECT ANALYSIS WHICH WOULD BE NEEDED IN THESE SERVICES, AND…

E-learning leads to evolutions in the way of designing a course. Diffused through the web, the course content cannot be the direct transcription of a face to face course content. A course can be seen as an organization in which different actors are involved. These actors produce documents, information and knowledge that they often share. We…