Artificial Intelligence (AI) technologies are increasingly pervading aspects of our lives. Because people use natural language to communicate with each other, computers should also use natural language to communicate with us. One of the principal obstacles to achieving this is the ambiguity of natural language, evidenced in problems such as prepositional phrase attachment and pronoun coreference. Current methods rely on the statistical frequency of word patterns, but this is often brittle and opaque to people.
In this thesis, I explore the idea of using commonsense knowledge to resolve linguistic ambiguities. I introduce PatchComm, which invokes explicit commonsense assertions to solve context-independent ambiguities. When commonsense assertions are missing, I invoke RetroGAN-DRD, which leverages state-of-the-art inference techniques such as retrofitting and generative adversarial networks (GAN) to infer commonsense assertions. I build upon that with ProGeneXP, which brings state-of-the-art language models to the task of describing its inputs and implicit knowledge in natural language while providing meaningful descriptions for PatchComm to align to further resolve linguistic ambiguities. Finally, I introduce DialComm to lay the groundwork for moving from single-sentence disambiguation to discourse. Specifically, DialComm builds upon PatchComm to obtain information from single sentences and integrates such information with additional commonsense assertions to build integral frame representations for discourses. I illustrate DialComm’s ability with an application to end-user programming in natural language.
The contributions of this dissertation lie in showing how commonsense inference can be integrated with parsing to resolve ambiguities in natural language, in a transparent manner. I have implemented three candidate systems, with increasingly sophisticated approaches. I verified that they perform well on some standard tests, and they operate in such a way that is understandable to people. This obviates the mythical inevitability of an interpretability-performance tradeoff. I have shown how my techniques can be used in a candidate application, programming in natural language.
My work leaves us in a good position to exploit further advances in natural language understanding and commonsense inference. I am optimistic that natural, transparent communication with computers will help make the world a better place.
| Identifer | oai:union.ndltd.org:bu.edu/oai:open.bu.edu:2144/48024 |
| Date | 07 February 2024 |
| Creators | Xin, Yida |
| Contributors | Homer, Steve |
| Source Sets | Boston University |
| Language | en_US |
| Detected Language | English |
| Type | Thesis/Dissertation |
Page generated in 0.002 seconds