Toward Knowledge-Centric Natural Language Processing: Acquisition, Representation, Transfer, and Reasoning
- Project Research
- 1-5 Chapters
- Abstract : Available
- Table of Content: Available
- Reference Style: APA
- Recommended for : Student Researchers
- NGN 3000
Abstract
Past decades have witnessed the great success of modern Artificial Intelligence (AI) via learning incredible statistical correlations from large-scale data. However, a knowledge gap still exists between the statistical learning of AI and the human-like learning process. Unlike machines, humans can first accumulate enormous background knowledge about how the world works and then quickly adapt it to new environments by understanding the underlying concepts. For example, given the limited life experience with mammals, a child can quickly learn the new concept of a dog to infer knowledge, like a dog is a mammal, a mammal has a heart, and thus, a dog has a heart. Then the child can generalize the concept to new cases, such as a golden retriever, a beagle, or a chihuahua. However, an AI system trained on a large-scale mammal but not dog-focused dataset cannot do such learning and generalization. AI techniques will fundamentally influence our everyday lives, and bridging this knowledge gap to empower existing AI systems with more explicit human knowledge is both timely and necessary to make them more generalizable, robust, trustworthy, interpretable, and efficient. To close this gap, we seek inspiration from how humans learn, such as the ability to abstract knowledge from data, generalize knowledge to new tasks, and reason to solve complex problems. Inspired by the human learning process, in this dissertation, we present our research efforts to address the knowledge gap between AI and human learning with a ii systematic study of the full life cycle of how to incorporate more explicit human knowledge in intelligent systems. Specifically, we need first to extract high-quality knowledge from the real world (knowledge acquisition), such as raw data or model parameters. We then transform various types of knowledge into neural representations (knowledge representation). We can also transfer existing knowledge between neural systems (knowledge transfer) or perform human-like complex reasoning to enable more transparent and generalizable inference (knowledge reasoning). All stages pose unique research challenges but are also intertwined, potentially leading to a unified framework of knowledge-centric natural language processing (NLP). This dissertation demonstrates our established achievements along the previous four directions. The introduction first elaborates on our motivation and research vision to construct a holistic and systematic view of knowledge-centric natural language processing. We describe our contributions distributed in these four directions in each chapter separately. For knowledge acquisition, we study extracting structured knowledge (e.g., synonyms, relations) from the text corpus that can be leveraged to build a better knowledge space. We leverage the corpus-level co-occurrence statistics to preserve privacy and personal information better. Our proposed framework can fully utilize the surface form and global context information for advanced performance. For knowledge representation, we focus on graph representation learning and propose to learn better representations of node pairs for pairwise prediction tasks on graphs, such as link prediction or relation classification. Our proposed method encourages the interaction between local contexts and would generate more interpretable results. For knowledge transfer, we present two works. The first one transfers knowledge between structured (Knowledge Base) and unstructured (text corpus) knowledge sources, and the second one transfers knowledge from pre-trained large iii language models (LLMs) to downstream tasks via multitask prompt tuning. For knowledge reasoning, we present two works. The first one shows a self-interpretable framework for medical relation prediction that can generate human-intuitive rationales to explain neural prediction. It relied on a recall and recognition process inspired by the human memory theory from cognitive science. We verify the trustworthiness of generated rationales by conducting a human evaluation of the medical expert. The second one focuses on commonsense reasoning for better word representation learning, in which an explicit reasoning module runs over a commonsense knowledge graph to perform multi-hop reasoning. The learned vector representations can benefit downstream tasks and show the reasoning steps as interpretations. In the last chapter, we summarize our key contributions and outline future research directions toward knowledge-centric natural language processing. Ultimately, we envision that human knowledge and reasoning should be indispensable components for the next generation of AI techniques
Related Project Materials
INTERNAL CONTROL SYSTEM AS A TOOL FOR EFFICIENCY IN THE MANAGEMENT OF SMALL AND MEDIUM SCALE ENTERPRISES IN ILORIN
ABSTRACT
The main objective of this study is to ascertain the efficiency of internal control system as...
BREAST FEEDING PROMOTION IN PRIMARY HEALTH CENTER
Abstract
Breast feeding promotion plays a significant role in the well being of nursing mother and their children. There...
EFFECT OF POOR MAINTENANCE STUDIO EQUIPMENT AND THE PRACTICE
Abstract
This study is on effect of poor maintenance studio equipment and the practical. The total population for...
THE ROLE OF COST REDUCTION STRATEGIES IN BUSINESS OPERATIONS
ABSTRACT
THE ROLE OF COST REDUCTION STRATEGIES IN BUSINESS OPERATIONS
This research explores the role of cost reduction strateg...
THE PROBLEMS OF CLASSROOM MANAGEMENT AND CONTROL IN SECONDARY SCHOOL
Background to the Study
The idea behind discipline in school is not across a single point of view About the proper defin...
AN ANALYSIS OF SOCIAL MEDIA COMMENTS IN THE PORTRAYAL OF PUBLIC SENTIMENT TOWARDS GOVERNMENT POLICIES (A CASE STUDY OF ENDBADGOVERNANCE PROTEST)
Chapter One: Introduction
1.1 Background of the Study
Social media has revolutionized the way people communicate, mobilize, and...
THE EFFECT OF CLASS SIZE ON EFFECTIVE TEACHING AND LEARNING OF JUNIOR SECONDARY SCHOOLS” A CASE STUDY OF IKPOBA OKHA LOCAL GOVERNMENT AREA OF EDO STATE
ABSTRACT
The purpose of this research work is to investigate the effect of class size in effective teaching and lear...
BIOCALCIFICATION OF CONCRETE USING CARBONIC ANYHDRASE PRODUCED BY SOIL BACTERIAL ISOLATES
ABSTRACT
Two (2) bacterial isolates obtained from Garima construction sites were named GARIMA (A) and (B), and code-named GA (A) and GA (...
PARENTAL SOCIO-ECONOMIC STATUS AND ITS INFLUENCE ON THE ACADEMIC ACHIEVEMENT STUDENTS
EXCERPT FROM THE STUDY
Parents with high occupational status are able to provide a measure of a household ability t...
THE INFLUENCE OF ONBOARDING PROGRAMS ON RECRUITMENT EFFECTIVENESS
Abstract : THE INFLUENCE OF ONBOARDING PROGRAMS ON RECRUITMENT EFFECTIVENESS
The objective of this study is to investigate the influence...
