{"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-quantum-many-body-wave-function-inspired","title":"A Quantum Many-body Wave Function Inspired Language Modeling Approach","arxiv_id":"1808.09891","date":"2018-08-28","proceeding":null,"authors":["Peng Zhang","Zhan Su","Lipeng Zhang","Benyou Wang","Dawei Song"],"abstract":"The recently proposed quantum language model (QLM) aimed at a principled\napproach to modeling term dependency by applying the quantum probability\ntheory. The latest development for a more effective QLM has adopted word\nembeddings as a kind of global dependency information and integrated the\nquantum-inspired idea in a neural network architecture. While these\nquantum-inspired LMs are theoretically more general and also practically\neffective, they have two major limitations. First, they have not taken into\naccount the interaction among words with multiple meanings, which is common and\nimportant in understanding natural language text. Second, the integration of\nthe quantum-inspired LM with the neural network was mainly for effective\ntraining of parameters, yet lacking a theoretical foundation accounting for\nsuch integration. To address these two issues, in this paper, we propose a\nQuantum Many-body Wave Function (QMWF) inspired language modeling approach. The\nQMWF inspired LM can adopt the tensor product to model the aforesaid\ninteraction among words. It also enables us to reveal the inherent necessity of\nusing Convolutional Neural Network (CNN) in QMWF language modeling.\nFurthermore, our approach delivers a simple algorithm to represent and match\ntext/sentence pairs. Systematic evaluation shows the effectiveness of the\nproposed QMWF-LM algorithm, in comparison with the state of the art\nquantum-inspired LMs and a couple of CNN-based methods, on three typical\nQuestion Answering (QA) datasets.","url_abs":"http://arxiv.org/abs/1808.09891v3","url_pdf":"http://arxiv.org/pdf/1808.09891v3.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-quantum-many-body-wave-function-inspired","repo_url":"https://github.com/TJUIRLAB/CIKM2018_QMWFLM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.09891","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}