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 Effect of Digital Visual Narratives on Nigerian Syntax: A Comparative Study of Instagram Story Captions
Background of the study
Instagram Story captions in Nigeria represent a fusion of visual and textual story...
Examining the Impact of Social Media on Emergency Response Coordination in Karu Local Government Area, Nasarawa State
Chapter One: Introduction
1.1 Background of the Study...
An evaluation of the socio-political implications of archaeological discoveries in Owo Local Government Area, Ondo State
Background of the Study
Archaeological discoveries in Owo have significantly influenced the socio-political landscape by u...
THE IMPACT OF MANAGEMENT CHALLENGES ON THE PRODUCTIVITY OF INTERGRATED BUILDING TECHNOLOGY AND SERVICES
ABSTRACT
The research is an descriptive attempt to study and analyze “the impact of management challenges on produ...
An investigation of global strategic narratives and their impact on national policies: A case study of US strategic communications in Abuja
Background of the Study
Global strategic narratives are powerful tools used by nations to shape international perceptions a...
The impact of rural development initiatives on local economies in Nigeria: An evaluation of policies in Benue State (2000–2020).
Background of the Study:
Rural development initiatives are crucial for bridging the gap between urban and rural areas, enhancing local ec...
A Case Study on Regulating Hate Speech in Online Media: A Study of Ilorin East Local Government Area, Kwara State
Background of the Study
The proliferation of online media has transformed communication, enabling rapid dissemination of...
An evaluation of informal education in promoting financial literacy among secondary school students in Azare Local Government Area, Bauchi State
Background of the Study
Financial literacy is an essential life skill that empowers individuals to make informed decisions...
Investigation into the Role of Big Data in Enhancing Secondary School Examination Performance in Birnin Kebbi Local Government, Kebbi State
Background of the Study
Examination performance in secondary schools is a key indicator of educational quality and student...
An investigation of debit fee restructuring on enhancing transaction transparency in banking: a case study of United Bank for Africa
Background of the Study
Transaction transparency is a critical factor in building customer trust in the banking sector. Un...
