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
TAX AS A STIMULUS FOR GROWTH AND DEVELOPMENT IN NIGERIA
ABSTRACT
Taxation and its product, Tax have been very important vehicles for eco...
IMPACT OF WORK ENVIRONMENT, SUPERVISION AND JOB SATISFACTION ON EMPLOYEES PRODUTIVITY
ABSTRACT
Job satisfaction is an attitude variable that reflects how people feel about their jobs overall as well as vari...
An Analysis of Property Valuation Practices and Financial Reporting: A Study of Real Estate Agencies in Lagos
Background of the Study
Property valuation is a critical component in the real estate sector, influencing investment decisions, financial...
An appraisal of mobile application usability improvements on driving digital banking adoption in Nigeria: a case study of Heritage Bank
Background of the Study
Mobile banking applications are the primary interface for digital financial services in Nigeria. Heritage Bank ha...
The role of budgetary planning in enhancing operational efficiency: A case study of Nestlé Nigeria Plc
Background of the Study
Budgetary planning is a crucial component of corporate governance that involves the preparation...
The impact of political instability on economic growth: A study of Jalingo Local Government Area, Taraba State
Background of the Study
Political instability refers to the absence of stable and predictable governance, often marked by f...
An investigation of neuromarketing techniques and their impact on advertising effectiveness: A study of a consumer brand in Port Harcourt, Nigeria.
Background of the study
Neuromarketing integrates neuroscience and marketing to better understand consumer decision-making...
An assessment of digital marketing innovation on boosting customer acquisition in banking: a case study of Access Bank Nigeria
Background of the Study
Digital marketing innovation has revolutionized customer acquisition strategies in the banking sec...
An investigation into the challenges of adult education in nomadic settlements in Damaturu Local Government Area, Yobe State
Background of the Study
Nomadic settlements in Damaturu Local Government Area, Yobe State, face unique challenges in acces...
CENTRAL BANK OF NIGERIA AS A CATALYST TO NATIONAL ECONOMIC POLICY AND DEVELOPMENT IN NIGERIA
Background of the Study
Economic policies are deliberate actions by the authority geared towards influe...
