{"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/semantic-hilbert-space-for-text","title":"Semantic Hilbert Space for Text Representation Learning","arxiv_id":"1902.09802","date":"2019-02-26","proceeding":null,"authors":["Benyou Wang","Qiuchi Li","Massimo Melucci","Dawei Song"],"abstract":"Capturing the meaning of sentences has long been a challenging task. Current\nmodels tend to apply linear combinations of word features to conduct semantic\ncomposition for bigger-granularity units e.g. phrases, sentences, and\ndocuments. However, the semantic linearity does not always hold in human\nlanguage. For instance, the meaning of the phrase `ivory tower' can not be\ndeduced by linearly combining the meanings of `ivory' and `tower'. To address\nthis issue, we propose a new framework that models different levels of semantic\nunits (e.g. sememe, word, sentence, and semantic abstraction) on a single\n\\textit{Semantic Hilbert Space}, which naturally admits a non-linear semantic\ncomposition by means of a complex-valued vector word representation. An\nend-to-end neural network~\\footnote{https://github.com/wabyking/qnn} is\nproposed to implement the framework in the text classification task, and\nevaluation results on six benchmarking text classification datasets demonstrate\nthe effectiveness, robustness and self-explanation power of the proposed model.\nFurthermore, intuitive case studies are conducted to help end users to\nunderstand how the framework works.","url_abs":"http://arxiv.org/abs/1902.09802v1","url_pdf":"http://arxiv.org/pdf/1902.09802v1.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":"semantic-hilbert-space-for-text","repo_url":"https://github.com/wabyking/qnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"semantic-composition","task_name":"Semantic Composition"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.09802","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}