Martínez Alonso, Wilfrido (2024) An NLP approach to understand construction long text. PhD thesis, Stanford University, USA.
Abstract
Construction contracts can make or break a project. Given their complexity, length, and the limited time and resources to review them, decision-makers often rely on summaries rather than the original documents. However, producing these summaries is a repetitive, expensive, and inefficient task. Additionally, human-produced summaries are prone to inconsistencies and stakeholders may not always be fully aware of the scope of their obligations. This lack of clarity can lead to acrimonious and expensive litigation when disputes arise. Natural Language Processing (NLP) offers an opportunity to make the summarization process faster, less expensive, and scalable. This work has two main parts. First, we propose an NLP model tailored to the specific needs of the construction industry to produce thorough, yet concise, summaries. Then, we present a case study applying our model in collaboration with an industry partner. Overall, this dissertation contributes an NLP-based model that efficiently (i.e, faster and better than the baseline) summarizes construction contracts. This research also demonstrates the feasibility of using a customized model to improve the contract review process while reducing the effort expended and enhancing user-perceived performance.
| Item Type: | Thesis (Doctoral) |
|---|---|
| Thesis advisor: | Fischer, Martin |
| Index terms: | case study, dispute, litigation, construction contract, construction industry, dissertation, collaboration, documents, complexity |
| Subjects: | dispute resolution, data collection methods, industry analysis, systems engineering, professional development, management, research dissemination and communication, contract type |
| Topics: | Engineering Principles, Procurement, Legal Issues, Research Practice, Information Management, Organizational Design |
| Descriptive scope: | 4 PCTE |
N.B. Descriptive scope is a count of how many of the five facets of empirical research are indicated by the words used in title, abstract and keywords. It is not intended as a judgement on the research; merely a count of the kind of word we would expect to indicate Phenomenon, Concepts, Theoretical framing, Empirical techniques, Analytical techniques. If all five are present, then a code of “5 PCTEA” will indicate this. If you feel the coding for this record is questionable, we welcome discussion around the terms we matched or the way we categorized them. The facet you would expect may not be coded, or a facet may be coded inappropriately. This can also bear on a larger question, of which facets should be treated as defining in construction management research. Please get in touch, and we will look at it. More details here