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 5000
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
The Impact of Religious Themes in Hausa Films on Youths: A Study of Gusau Local Government Area, Zamfara State
Chapter One: Introduction
1.1 Background of the Study
Hausa films, popularly known as Kannywood, have emerged as one of the mos...
The Role of Community Radio in Fostering Women’s Empowerment: A Study of Kaura Namoda Local Government Area, Zamfara State
Chapter One: Introduction
1.1 Background of the Study
Community radio has become a critical platform for fostering social chang...
IMPACT OF E-PAYMENT ON ONLINE SHOPPING BEHAVIOUR
EXCERPT FROM THE STUDY
E-Payment systems refer to the automated processes of exchanging monetary value among parties in...
AN EVALUATION OF JOB SATISFACTION AMONG TEACHERS IN SECONDARY SCHOOLS
BACKGROUND OF THE STUDY
Job satisfaction is an attitude that arises from the balance and summation of n...
EFFECTIVENESS OF THE LAW ENFORCEMENT AGENCY
ABSTRACT
There has been a rising concern on the security of the country. This project is focused on studying the effect of Law enforcemen...
The Effect of Governmental Accounting Practices on Agricultural Subsidy Utilization in Bida LGA, Niger State
Background of the Study
Agriculture is a critical sector in Nigeria’s economy, employing a large portion of the population and cont...
The Impact of Performance-Based Accounting on Service Delivery in Nigerian Ministries: A Case Study of the Ministry of Water Resources
Background of the Study
Performance-based accounting is a financial management approach that aligns res...
ASSESSMENT OF THE ROLE PERFORMANCE OF PRINCIPALS IN MANAGEMENT OF SECONDARY SCHOOLS IN ZAMFARA STATE, NIGERIA
ABSTRACT
This study focused on the Assessment oftherole performance of Principals in the Management of Secondary Schools in Zamfara State...
THE EFFECT OF INTEREST RATE ON SAVINGS IN NIGERIA
ABSTRACT
This study examined the effect of interest rates on savings in Nigeria Using multiple regression analysis. The...
IMPACT OF ENVIRONMENTAL PLANNING ON RURAL DEVELOPMENT
ABSTRACT
The study examine impact of environmental planning on rural development, This study was undertaken majorly to e...
