ABSTRACT
The evolution of the Web over the last three decades has led to a deluge of scientific and news articles on the Internet. Harnessing these publications in different fields of study is critical to effective end user information consumption. Similarly, in the domain of healthcare, one of the key challenges with the adoption of Electronic Health Records (EHRs) for clinical practice has been the tremendous amount of clinical notes generated that can be summarized without which clinical decision making and communication will be inefficient and costly. In spite of the rapid advances in information retrieval and deep learning techniques towards abstractive document summarization, the results of these efforts continue to resemble extractive summaries, achieving promising results predominantly on lexical metrics but performing poorly on semantic metrics. Thus, abstractive summarization that is driven by intrinsic and extrinsic semantics of documents is not adequately explored. Resources that can be used for generating semantics-driven abstractive summaries include: • Abstracts of multiple scientific articles published in a given technical field of study to generate an abstractive summary for topically-related abstracts within the field, thus reducing the load of having to read semantically duplicate abstracts on a given topic. • Citation contexts from different authoritative papers citing a reference paper can be used to generate utility-oriented abstractive summary for a scientific article. • Biomedical articles and the named entities characterizing the biomedical articles along with background knowledge bases to generate entity and fact-aware abstractive summaries. • Clinical notes of patients and clinical knowledge bases for abstractive clinical text summarization using knowledge-driven multi-objective optimization. iii In this dissertation, we develop semantics-driven abstractive models based on intradocument and inter-document semantic analyses along with facts of named entities retrieved from domain-specific knowledge bases to produce summaries. Concretely, we propose a sequence of frameworks leveraging semantics at various granularity (e.g., word, sentence, document, topic, citations, and named entities) levels, by utilizing external resources. The proposed frameworks have been applied to a range of tasks including: 1. Abstractive summarization of topic-centric multi-document scientific articles and news articles. 2. Abstractive summarization of scientific articles using crowd-sourced citation contexts. 3. Abstractive summarization of biomedical articles clustered based on entity-relatedness. 4. Abstractive summarization of clinical notes of patients with heart failure and Chest X-Rays recordings. The proposed approaches achieve impressive performance in terms of preserving semantics in abstractive summarization while paraphrasing. For summarization of topiccentric multiple scientific/news articles, we propose a three-stage approach where abstracts of scientific articles or news articles are clustered based on their topical similarity determined from topics generated using Latent Dirichlet Allocation (LDA), followed by extractive phase and abstractive phase. Then, in the next stage, we focus on abstractive summarization of biomedical literature where we leverage named entities in biomedical articles to 1) cluster related articles; and 2) leverage the named entities towards guiding abstractive summarization. Finally, in the last stage, we turn to external resources such as citation contexts pointing to a scientific article to generate a comprehensive and utility-centric abstractive summary of a scientific article, domain-specific knowledge bases to fill gaps in information about entities in a biomedical article to summarize and clinical notes to guide iv abstractive summarization of clinical text. Thus, the bottom-up progression of exploring semantics towards abstractive summarization in this dissertation starts with (i) Semantic Analysis of Latent Topics; builds on (ii) Internal and External Knowledge-I (gleaned from abstracts and Citation Contexts); and extends it to make it comprehensive using (iii) Internal and External Knowledge-II (Named Entities and Knowledge Bases).
ABSTRACT
The study examined the influence of youth culture on the social orientation of adolesc...
Statement of the problem
The objective of assessing the effect of internet culture on administrative ef...
Background of the study
It is widely agreed that one of the fundamental requirements for human existenc...
THE IMPACT OF LEADERSHIP ON TEAM PERFORMANCE
This study examines the impact of leaders...
BACKGROUND OF THE STUDY
Over the course of its history, the petroleum sector in Nigeria, which has the...
ABSTRACT
The study conducted in Plateau State set out to find out the perception of the residents in the selected study areas of Jos Nort...
Abstract
Financial management and Acquisition of information resources is an essential activity which...
Abstract
The study focused on the effect of the laboratory method of teaching on the achievement of J.SS II students in...
Abstract
This study is on the effect of examination anxiety on the academic performance of students in tertiary institut...
ABSTRACT
In educational situation, success is measured by academic performance or how well a student me...