{"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/a-generalized-language-model-in-tensor-space","title":"A Generalized Language Model in Tensor Space","arxiv_id":"1901.11167","date":"2019-01-31","proceeding":null,"authors":["Lipeng Zhang","Peng Zhang","Xindian Ma","Shuqin Gu","Zhan Su","Dawei Song"],"abstract":"In the literature, tensors have been effectively used for capturing the\ncontext information in language models. However, the existing methods usually\nadopt relatively-low order tensors, which have limited expressive power in\nmodeling language. Developing a higher-order tensor representation is\nchallenging, in terms of deriving an effective solution and showing its\ngenerality. In this paper, we propose a language model named Tensor Space\nLanguage Model (TSLM), by utilizing tensor networks and tensor decomposition.\nIn TSLM, we build a high-dimensional semantic space constructed by the tensor\nproduct of word vectors. Theoretically, we prove that such tensor\nrepresentation is a generalization of the n-gram language model. We further\nshow that this high-order tensor representation can be decomposed to a\nrecursive calculation of conditional probability for language modeling. The\nexperimental results on Penn Tree Bank (PTB) dataset and WikiText benchmark\ndemonstrate the effectiveness of TSLM.","url_abs":"http://arxiv.org/abs/1901.11167v1","url_pdf":"http://arxiv.org/pdf/1901.11167v1.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":"a-generalized-language-model-in-tensor-space","repo_url":"https://github.com/TJUIRLAB/AAAI19-TSLM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"tensor-decomposition","task_name":"Tensor Decomposition"},{"task_slug":"tensor-networks","task_name":"Tensor Networks"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1901.11167","atlas_url":"https://app.syntology.ai/?focus=1901.11167","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}