skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Automating Design Requirement Extraction From Text With Deep Learning
Abstract Nearly every artifact of the modern engineering design process is digitally recorded and stored, resulting in an overwhelming amount of raw data detailing past designs. Analyzing this design knowledge and extracting functional information from sets of digital documents is a difficult and time-consuming task for human designers. For the case of textual documentation, poorly written superfluous descriptions filled with jargon are especially challenging for junior designers with less domain expertise to read. If the task of reading documents to extract functional requirements could be automated, designers could actually benefit from the distillation of massive digital repositories of design documentation into valuable information that can inform engineering design. This paper presents a system for automating the extraction of structured functional requirements from textual design documents by applying state of the art Natural Language Processing (NLP) models. A recursive method utilizing Machine Learning-based question-answering is developed to process design texts by initially identifying the highest-level functional requirement, and subsequently extracting additional requirements contained in the text passage. The efficacy of this system is evaluated by comparing the Machine Learning-based results with a study of 75 human designers performing the same design document analysis task on technical texts from the field of Microelectromechanical Systems (MEMS). The prospect of deploying such a system on the sum of all digital engineering documents suggests a future where design failures are less likely to be repeated and past successes may be consistently used to forward innovation.  more » « less
Award ID(s):
1854833
PAR ID:
10340893
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
ASME 2021 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, 47th Design Automation Conference (DAC)
Volume:
Volume 3B
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; (, 32nd CIRP Design Conference (CIRP Design 2022) - Design in a changing world)
    Anwer, Nabil (Ed.)
    Design documentation is presumed to contain massive amounts of valuable information and expert knowledge that is useful for learning from the past successes and failures. However, the current practice of documenting design in most industries does not result in big data that can support a true digital transformation of enterprise. Very little information on concepts and decisions in early product design has been digitally captured, and the access and retrieval of them via taxonomy-based knowledge management systems are very challenging because most rule-based classification and search systems cannot concurrently process heterogeneous data (text, figures, tables, references). When experts retire or leave a design unit, industry often cannot benefit from past knowledge for future product design, and is left to reinvent the wheel repeatedly. In this work, we present AI-based Natural Language Processing (NLP) models which are trained for contextually representing technical documents containing texts, figures and tables, to do a semantic search for the retrieval of relevant data across large corpora of documents. By connecting textual and non-textual data through the use of an associative database, the semantic search question-answering system we developed can provide more comprehensive answers in the context of users’ questions. For the demonstration and assessment of this model, the semantic search question-answering system is applied to the Intergovernmental Panel on Climate Change (IPCC) Special Report 2019, which is more than 600 pages long and difficult to read and understand, even by most experts. Users can input custom queries relating to climate change concerns and receive evidence from the report that is contextually meaningful. We expect this method can transform current repositories of design documentation of heterogeneous data forms into structured knowledge-bases which can return relevant information efficiently as well as can evolve to embody manageable big data for the true digital transformation of design. 
    more » « less
  2. ; ; (, Proceedings of the BioCreative VI Workshop)
    Kinases are enzymes that mediate phosphate transfer. Extracting information on kinases from biomedical literature is an important task which has direct implications for applications such as drug design. In this work, we develop KinDER, Kinase Document Extractor and Ranker, a biomedical natural language processing tool for extracting functional and disease related information on kinases. This tool combines information retrieval and machine learning techniques to automatically extract information about protein kinases. First, it uses several bio-ontologies to retrieve documents related to kinases and then uses a supervised classification model to rank them according to their relevance. This was developed to participate in the Text-mining services for Human Kinome Curation Track of the BioCreative VI challenge. According to the official BioCreative evaluation results, KinDER provides stateof- the-art performance for extracting functional information on kinases from abstracts. 
    more » « less
  3. ; ; ; ; ; ; (, ASME International Design Engineering Technical Conferences and Computers in Engineering)
    During the design process, designers must satisfy customer needs while adequately developing engineering objectives. Among these engineering objectives, human considerations such as user interactions, safety, and comfort are indispensable during the design process. Nevertheless, traditional design engineering methodologies have significant limitations incorporating and understanding physical user interactions during early design phases. For example, Human Factors methods use checklists and guidelines applied to virtual or physical prototypes at later design stages to evaluate the concept. As a result, designers struggle to identify design deficiencies and potential failure modes caused by user-system interactions without relying on the use of detailed and costly prototypes. The Function-Human Error Design Method (FHEDM) is a novel approach to assess physical interactions during the early design stage using a functional basis approach. By applying FHEDM, designers can identify user interactions required to complete the functions of the system and to distinguish failure modes associated with such interactions, by establishing user-system associations using the information of the functional model. In this paper, we explore the use of data mining techniques to develop relationships between component, functions, flows and user interactions. We extract design information about components, functions, flows, and user interactions from a set of distinct coffee makers found in the Design Repository to build associations rules. Later, using a functional model of an electric kettle, we compared the functions, flows, and user interactions associations generated from data mining against the associations created by the authors, using the FHEDM. The results show notable similarities between the associations built from data mining and the FHEDM. We are suggesting that design information from a rich dataset can be used to extract association rules between functions, flows, components, and user interactions. This work will contribute to the design community by automating the identification of user interactions from a functional model. 
    more » « less
  4. ; (, Construction Research Congress 2020)
    Tang, P.; Grau, D.; El Asmar, M. (Ed.)
    Existing automated code checking (ACC) systems require the extraction of requirements from regulatory textual documents into computer-processable rule representations. The information extraction processes in those ACC systems are based on either human interpretation, manual annotation, or predefined automated information extraction rules. Despite the high performance they showed, rule-based information extraction approaches, by nature, lack sufficient scalability—the rules typically need some level of adaptation if the characteristics of the text change. Machine learning-based methods, instead of relying on hand-crafted rules, automatically capture the underlying patterns of the existing training text and have a great capability of generalizing to a variety of texts. A more scalable, machine learning-based approach is thus needed to achieve a more robust performance across different types of codes/documents for automatically generating semantically-enriched building-code sentences for the purpose of ACC. To address this need, this paper proposes a machine learning-based approach for generating semantically-enriched building-code sentences, which are annotated syntactically and semantically, for supporting IE. For improved robustness and scalability, the proposed approach uses transfer learning strategies to train deep neural network models on both general-domain and domain-specific data. The proposed approach consists of four steps: (1) data preparation and preprocessing; (2) development of a base deep neural network model for generating semantically-enriched building-code sentences; (3) model training using transfer learning strategies; and (4) model evaluation. The proposed approach was evaluated on a corpus of sentences from the 2009 International Building Code (IBC) and the Champaign 2015 IBC Amendments. The preliminary results show that the proposed approach achieved an optimal precision of 88%, recall of 86%, and F1-measure of 87%, indicating good performance. 
    more » « less
  5. ; (, Proceedings of the VLDB Endowment)
    null (Ed.)
    Along with textual content, visual features play an essential role in the semantics of visually rich documents. Information extraction (IE) tasks perform poorly on these documents if these visual cues are not taken into account. In this paper, we present Artemis - a visually aware, machine-learning-based IE method for heterogeneous visually rich documents. Artemis represents a visual span in a document by jointly encoding its visual and textual context for IE tasks. Our main contribution is two-fold. First, we develop a deep-learning model that identifies the local context boundary of a visual span with minimal human-labeling. Second, we describe a deep neural network that encodes the multimodal context of a visual span into a fixed-length vector by taking its textual and layout-specific features into account. It identifies the visual span(s) containing a named entity by leveraging this learned representation followed by an inference task. We evaluate Artemis on four heterogeneous datasets from different domains over a suite of information extraction tasks. Results show that it outperforms state-of-the-art text-based methods by up to 17 points in F1-score. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email