{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T08:25:05Z","timestamp":1765700705069,"version":"3.41.2"},"reference-count":55,"publisher":"ASME International","issue":"1","license":[{"start":{"date-parts":[[2023,6,23]],"date-time":"2023-06-23T00:00:00Z","timestamp":1687478400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.asme.org\/publications-submissions\/publishing-information\/legal-policies"}],"funder":[{"DOI":"10.13039\/100004675","name":"Autodesk","doi-asserted-by":"publisher","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}],"id":[{"id":"10.13039\/100004675","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["asmedigitalcollection.asme.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,1,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Semantic knowledge of part-part and part-whole relationships in assemblies is useful for a variety of tasks from searching design repositories to the construction of engineering knowledge bases. In this work, we propose that the natural language names designers use in computer aided design (CAD) software are a valuable source of such knowledge, and that large language models (LLMs) contain useful domain-specific information for working with this data as well as other CAD and engineering-related tasks. In particular, we extract and clean a large corpus of natural language part, feature, and document names and use this to quantitatively demonstrate that a pre-trained language model can outperform numerous benchmarks on three self-supervised tasks, without ever having seen this data before. Moreover, we show that fine-tuning on the text data corpus further boosts the performance on all tasks, thus demonstrating the value of the text data which until now has been largely ignored. We also identify key limitations to using LLMs with text data alone, and our findings provide a strong motivation for further work into multi-modal text-geometry models. To aid and encourage further work in this area we make all our data and code publicly available.<\/jats:p>","DOI":"10.1115\/1.4062454","type":"journal-article","created":{"date-parts":[[2023,5,3]],"date-time":"2023-05-03T02:42:55Z","timestamp":1683081775000},"update-policy":"https:\/\/doi.org\/10.1115\/crossmarkpolicy-asme","source":"Crossref","is-referenced-by-count":9,"title":["What\u2019s in a Name? Evaluating Assembly-Part Semantic Knowledge in Language Models Through User-Provided Names in Computer Aided Design Files"],"prefix":"10.1115","volume":"24","author":[{"given":"Peter","family":"Meltzer","sequence":"first","affiliation":[{"name":"Autodesk Research , London WC2R 0QE , UK"}]},{"given":"Joseph G.","family":"Lambourne","sequence":"additional","affiliation":[{"name":"Autodesk Research , London WC2R 0QE , UK"}]},{"given":"Daniele","family":"Grandi","sequence":"additional","affiliation":[{"name":"Autodesk Research , San Fransciso, CA 94105"}]}],"member":"33","published-online":{"date-parts":[[2023,6,23]]},"reference":[{"key":"2023062314361086400_CIT0001","first-page":"275","article-title":"Benchmarking CAD Search Techniques","author":"Bespalov","year":"2005"},{"issue":"1","key":"2023062314361086400_CIT0002","doi-asserted-by":"publisher","first-page":"e22","DOI":"10.1017\/S0890060422000130","article-title":"Enabling Multi-Modal Search for Inspirational Design Stimuli Using Deep Learning","volume":"36","author":"Kwon","year":"2022","journal-title":"Artif. Intell. Eng. Des. Anal. Manuf."},{"issue":"3","key":"2023062314361086400_CIT0003","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1177\/09544054211025775","article-title":"A CAD Model for the Tolerancing of Mechanical Assemblies Considering Non-Rigid Joints Between Parts With Defects","volume":"236","author":"Korbi","year":"2022","journal-title":"Proc. Inst. Mech. Eng. B"},{"issue":"6","key":"2023062314361086400_CIT0004","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3478513.3480562","article-title":"Automate: A Dataset and Learning Approach for Automatic Mating of CAD Assemblies","volume":"40","author":"Jones","year":"2021","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"2023062314361086400_CIT0005","first-page":"15849","article-title":"Joinable: Learning Bottom-Up Assembly of Parametric CAD Joints","author":"Willis","year":"2022"},{"issue":"11","key":"2023062314361086400_CIT0006","doi-asserted-by":"publisher","first-page":"111402","DOI":"10.1115\/1.4037649","article-title":"A Data-Driven Text Mining and Self-Learning Semantic Network Analysis for Design Knowledge Retrieval","volume":"139","author":"Shi","year":"2017","journal-title":"ASME J. Mech. Des."},{"issue":"1","key":"2023062314361086400_CIT0007","doi-asserted-by":"publisher","first-page":"112995","DOI":"10.1016\/j.eswa.2019.112995","article-title":"TechNet: Technology Semantic Network Based on Patent Data","volume":"142","author":"Sarica","year":"2020","journal-title":"Expert Syst. Appl."},{"issue":"2","key":"2023062314361086400_CIT0008","first-page":"1729881420911257","article-title":"Data-Driven Product Design Toward Intelligent Manufacturing: A Review","volume":"17","author":"Feng","year":"2020","journal-title":"Int. J. Adv. Rob. Syst."},{"key":"2023062314361086400_CIT0009","first-page":"306","article-title":"Search & Retrieval in CAD Databases \u2013 A User-Centric State-of-the-Art Overview","author":"Schinko","year":"2017"},{"issue":"1","key":"2023062314361086400_CIT0010","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1016\/j.aiopen.2020.11.001","article-title":"Neural Machine Translation: A Review of Methods, Resources, and Tools","volume":"1","author":"Tan","year":"2020","journal-title":"AI Open"},{"issue":"140","key":"2023062314361086400_CIT0011","first-page":"1","article-title":"Exploring the Limits of Transfer Learning With a Unified Text-to-Text Transformer.","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"article-title":"Language Models are Few-Shot Learners","year":"2020","author":"Brown","key":"2023062314361086400_CIT0012"},{"key":"2023062314361086400_CIT0013","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2015.11","article-title":"Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books","author":"Zhu","year":"2015"},{"key":"2023062314361086400_CIT0014","first-page":"164","article-title":"Understanding Regional Context of World Wide Web Using Common Crawl Corpus","author":"Mehmood","year":"2017"},{"key":"2023062314361086400_CIT0015","first-page":"9593","article-title":"Abc: A Big CAD Model Dataset for Geometric Deep Learning","author":"Koch","year":"2019"},{"key":"2023062314361086400_CIT0016","article-title":"Attention is All You Need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1","key":"2023062314361086400_CIT0017","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1016\/j.aiopen.2021.12.001","article-title":"A Review of Deep Learning in Question Answering Over Knowledge Bases","volume":"2","author":"Zhang","year":"2021","journal-title":"AI Open"},{"article-title":"Language Models Are Unsupervised Multitask Learners","year":"2018","author":"Radford","key":"2023062314361086400_CIT0018"},{"key":"2023062314361086400_CIT0019","first-page":"4171","article-title":"BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Volume 1 (Long and Short Papers)","author":"Devlin","year":"2019"},{"volume-title":"DistilBERT, A Distilled Version of BERT: Smaller, Faster, Cheaper and Lighter, February","year":"2020","author":"Sanh","key":"2023062314361086400_CIT0020"},{"issue":"1","key":"2023062314361086400_CIT0021","doi-asserted-by":"publisher","first-page":"842","DOI":"10.1162\/tacl_a_00349","article-title":"A Primer in BERTology: What We Know About How BERT Works","volume":"8","author":"Rogers","year":"2020","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"2023062314361086400_CIT0022","first-page":"3744","article-title":"Set Transformer: A Framework for Attention-Based Permutation-Invariant Neural Networks","author":"Lee","year":"2019"},{"volume-title":"Learning Transferable Visual Models From Natural Language Supervision","year":"2021","author":"Radford","key":"2023062314361086400_CIT0023"},{"key":"2023062314361086400_CIT0024","first-page":"10684","article-title":"High-Resolution Image Synthesis With Latent Diffusion Models","author":"Rombach","year":"2022"},{"key":"2023062314361086400_CIT0025","first-page":"145","article-title":"A Survey of Content Based 3D Shape Retrieval Methods","author":"Tangelder","year":"2004"},{"issue":"6","key":"2023062314361086400_CIT0026","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1882261.1866204","article-title":"Context-Based Search for 3D Models","volume":"29","author":"Fisher","year":"2010","journal-title":"ACM Trans. Graph."},{"issue":"1","key":"2023062314361086400_CIT0027","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1145\/588272.588279","article-title":"A Search Engine for 3D Models","volume":"22","author":"Funkhouser","year":"2003","journal-title":"ACM Trans. Graph."},{"key":"2023062314361086400_CIT0028","first-page":"356","article-title":"The Smart Document Retrieval Project","author":"Salton","year":"1991"},{"key":"2023062314361086400_CIT0029","first-page":"313","article-title":"Relevance Feedback in Information Retrieval","volume-title":"The Smart Retrieval System \u2013 Experiments in Automatic Document Processing","author":"Rocchio","year":"1971"},{"key":"2023062314361086400_CIT0030","doi-asserted-by":"crossref","DOI":"10.1145\/3072959.3073652","article-title":"Learning Hierarchical Shape Segmentation and Labeling From Online Repositories","author":"Yi","year":"2017"},{"article-title":"Shapenet: An Information-Rich 3D Model Repository","year":"2015","author":"Chang","key":"2023062314361086400_CIT0031"},{"key":"2023062314361086400_CIT0032","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1007\/978-3-030-20893-6_7","article-title":"Text2shape: Generating Shapes From Natural Language by Learning Joint Embeddings","volume-title":"Computer Vision \u2013 ACCV 2018 \u2013 14th Asian Conference on Computer VisionRevised Selected Papers","author":"Chen","year":"2019"},{"issue":"01","key":"2023062314361086400_CIT0033","first-page":"126","article-title":"Y2seq2seq: Cross-Modal Representation Learning for 3D Shape and Text by Joint Reconstruction and Prediction of View and Word Sequences","volume":"33","author":"Han","year":"2019","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"2023062314361086400_CIT0034","first-page":"8821","article-title":"Zero-Shot Text-to-Image Generation","author":"Ramesh","year":"2021"},{"year":"2021","author":"Dayma","key":"2023062314361086400_CIT0035"},{"key":"2023062314361086400_CIT0036","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.01805","article-title":"Clip-Forge: Towards Zero-Shot Text-to-Shape Generation","author":"Sanghi","year":"2022"},{"article-title":"Clip-Mesh: Generating Textured Meshes From Text Using Pretrained Image-Text Models","year":"2022","author":"Khalid","key":"2023062314361086400_CIT0037"},{"year":"2022","author":"Sanghi","key":"2023062314361086400_CIT0038"},{"key":"2023062314361086400_CIT0039","doi-asserted-by":"crossref","DOI":"10.1145\/3550340.3564216","article-title":"Zero-Shot Multi-Modal Artist-Controlled Retrieval and Exploration of 3D Object Sets","author":"Schlachter","year":"2022"},{"issue":"3","key":"2023062314361086400_CIT0040","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1109\/5254.846285","article-title":"Design Repositories: Engineering Design\u2019s New Knowledge Base","volume":"15","author":"Szykman","year":"2000","journal-title":"IEEE Intell. Syst. Appl."},{"key":"2023062314361086400_CIT0041","first-page":"55","article-title":"Product Design Support: Exploring a Design Repository System","author":"Bohm","year":"2004"},{"issue":"7","key":"2023062314361086400_CIT0042","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1016\/j.cad.2007.09.003","article-title":"Introduction of a Data Schema to Support a Design Repository","volume":"40","author":"Bohm","year":"2008","journal-title":"CAD Comput. Aided Des."},{"key":"2023062314361086400_CIT0043","first-page":"1","article-title":"Development of a Design for Manufacturing Rules Database for Use in Instruction of Dfm Practices","author":"Phelan","year":"2014"},{"key":"2023062314361086400_CIT0044","first-page":"1","article-title":"Development of a Pilot Manufacturing Cyberinfrastructure With an Information Rich Mechanical CAD 3D Model Repository","author":"Bharadwaj","year":"2019"},{"article-title":"Deriving a Component Basis for Computational Functional Synthesis","year":"2005","author":"Kurtoglu","key":"2023062314361086400_CIT0045"},{"issue":"2","key":"2023062314361086400_CIT0046","first-page":"65","article-title":"A Functional Basis for Engineering Design: Reconciling and Evolving Previous Efforts","volume":"13","author":"Hirtz","year":"2002","journal-title":"Res. Eng. Des. Theor. Appl. Concurr. Eng."},{"issue":"2","key":"2023062314361086400_CIT0047","doi-asserted-by":"publisher","first-page":"021007","DOI":"10.1115\/1.4003249","article-title":"Biologically Meaningful Keywords for Functional Terms of the Functional Basis","volume":"133","author":"Cheong","year":"2011","journal-title":"ASME J. Mech. Des"},{"year":"2020","author":"Ferrero","key":"2023062314361086400_CIT0048"},{"issue":"11","key":"2023062314361086400_CIT0049","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","article-title":"WordNet","volume":"38","author":"Miller","year":"1995","journal-title":"Commun. ACM"},{"issue":"4","key":"2023062314361086400_CIT0050","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1023\/B:BTTJ.0000047600.45421.6d","article-title":"ConceptNet - A Practical Commonsense Reasoning Tool-Kit","volume":"22","author":"Liu","year":"2004","journal-title":"BT Technol. J."},{"key":"2023062314361086400_CIT0051","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v24i1.7519","article-title":"Toward an Architecture for Never-Ending Language Learning","author":"Carlson","year":"2010"},{"key":"2023062314361086400_CIT0052","first-page":"3111","article-title":"Distributed Representations of Words and Phrases and Their Compositionality","author":"Mikolov","year":"2013"},{"key":"2023062314361086400_CIT0053","doi-asserted-by":"crossref","DOI":"10.1115\/DETC2022-88049","article-title":"Material Prediction for Design Automation Using Graph Representation Learning","author":"Bian","year":"2022"},{"volume-title":"Natural Language Processing With Python","year":"2009","author":"Bird","key":"2023062314361086400_CIT0054"},{"issue":"1","key":"2023062314361086400_CIT0055","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","article-title":"Enriching Word Vectors With Subword Information","volume":"5","author":"Bojanowski","year":"2017","journal-title":"Trans. Assoc. Comput. Linguist."}],"container-title":["Journal of Computing and Information Science in Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/24\/1\/011002\/7020778\/jcise_24_1_011002.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/24\/1\/011002\/7020778\/jcise_24_1_011002.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,24]],"date-time":"2023-06-24T16:16:47Z","timestamp":1687623407000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article\/24\/1\/011002\/1163204\/What-s-in-a-Name-Evaluating-Assembly-Part-Semantic"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,23]]},"references-count":55,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1,1]]}},"URL":"https:\/\/doi.org\/10.1115\/1.4062454","relation":{},"ISSN":["1530-9827","1944-7078"],"issn-type":[{"type":"print","value":"1530-9827"},{"type":"electronic","value":"1944-7078"}],"subject":[],"published":{"date-parts":[[2023,6,23]]},"article-number":"011002"}}