{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/structvae-tree-structured-latent-variable","title":"StructVAE: Tree-structured Latent Variable Models for Semi-supervised Semantic Parsing","arxiv_id":"1806.07832","date":"2018-06-20","proceeding":"ACL 2018 7","authors":["Pengcheng Yin","Chunting Zhou","Junxian He","Graham Neubig"],"abstract":"Semantic parsing is the task of transducing natural language (NL) utterances\ninto formal meaning representations (MRs), commonly represented as tree\nstructures. Annotating NL utterances with their corresponding MRs is expensive\nand time-consuming, and thus the limited availability of labeled data often\nbecomes the bottleneck of data-driven, supervised models. We introduce\nStructVAE, a variational auto-encoding model for semisupervised semantic\nparsing, which learns both from limited amounts of parallel data, and\nreadily-available unlabeled NL utterances. StructVAE models latent MRs not\nobserved in the unlabeled data as tree-structured latent variables. Experiments\non semantic parsing on the ATIS domain and Python code generation show that\nwith extra unlabeled data, StructVAE outperforms strong supervised models.","url_abs":"http://arxiv.org/abs/1806.07832v1","url_pdf":"http://arxiv.org/pdf/1806.07832v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"structvae-tree-structured-latent-variable","repo_url":"https://github.com/DeepLearnXMU/CG-RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"structvae-tree-structured-latent-variable","repo_url":"https://github.com/Pro-v-7/code-generation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"structvae-tree-structured-latent-variable","repo_url":"https://github.com/kzCassie/ucl_nlp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"structvae-tree-structured-latent-variable","repo_url":"https://github.com/neulab/external-knowledge-codegen","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"structvae-tree-structured-latent-variable","repo_url":"https://github.com/pcyin/tranX","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"structvae-tree-structured-latent-variable","repo_url":"https://gitlab.com/codegenfact/BertranX","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"structvae-tree-structured-latent-variable","repo_url":"https://gitlab.com/codegenfactors/BertranX","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.07832","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}