2026-09-19T11:16:53Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/127164 2025-03-29 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

application/pdf en text Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-03-28 without embargo terms The student, Pengfei Yu, accepted the attached license on 2024-10-22 at 22:35. The student, Pengfei Yu, submitted this Dissertation for approval on 2024-10-22 at 22:41. This Dissertation was approved for publication on 2024-10-28 at 10:53. DSpace SAF Submission Ingestion Package generated from Vireo submission #21267 on 2025-03-28 at 14:25:12 Association knowledge in natural language learning Yu, Pengfei 2024-10-28 Ji, Heng Ji, Heng Han, Jiawei Hoiem, Derek Neubig, Graham Yih, Scott Natural Language Processing Association Modeling Information Extraction Knowledge Editing eng Association is an important feature of natural language originates from the human's cognitive ability to associate concepts. It is the key to unveiling the computational mechanism of natural language, which is closely related to the research of natural language processing (NLP). However, the current dominant learning paradigm, which is based on neural models that combine distributed representations with probabilistic modeling, demonstrates insufficient capabilities in modeling associations in natural language. To compensate for the deficiency, we mathematically formulate the concept of Association Knowledge as the joint distribution over the probabilities of instances and establish a general methodology to incorporate association knowledge into the training architecture of neural models. We delve into Association Knowledge through a series of case studies across various dimensions, including associations among types of knowledge, languages, instances and unstructured information. These case studies span both smaller neural models and large language models. Through our investigations, we demonstrate that explicitly integrating Association Knowledge into neural architectures markedly improves model performance and efficiency. This enhanced capability is evident in diverse scenarios, from improving event detection in lifelong learning settings and facilitating robust cross-lingual translations, to enhancing the detection of long-tail mentions and refining the updates in large language models. Collectively, our findings underscore the pivotal role of Association Knowledge in advancing the state of NLP by fostering more robust and knowledge-aware neural models. 2024-12 Thesis https://hdl.handle.net/2142/127164 Copyright 2024 Pengfei Yu Siebel School Comp & Data Sci Computer Science University of Illinois at Urbana-Champaign Ph.D. Dissertation