{"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/automatic-argumentative-zoning-using-word2vec","title":"Automatic Argumentative-Zoning Using Word2vec","arxiv_id":"1703.10152","date":"2017-03-29","proceeding":null,"authors":["Haixia Liu"],"abstract":"In comparison with document summarization on the articles from social media\nand newswire, argumentative zoning (AZ) is an important task in scientific\npaper analysis. Traditional methodology to carry on this task relies on feature\nengineering from different levels. In this paper, three models of generating\nsentence vectors for the task of sentence classification were explored and\ncompared. The proposed approach builds sentence representations using learned\nembeddings based on neural network. The learned word embeddings formed a\nfeature space, to which the examined sentence is mapped to. Those features are\ninput into the classifiers for supervised classification. Using\n10-cross-validation scheme, evaluation was conducted on the\nArgumentative-Zoning (AZ) annotated articles. The results showed that simply\naveraging the word vectors in a sentence works better than the paragraph to\nvector algorithm and by integrating specific cuewords into the loss function of\nthe neural network can improve the classification performance. In comparison\nwith the hand-crafted features, the word2vec method won for most of the\ncategories. However, the hand-crafted features showed their strength on\nclassifying some of the categories.","url_abs":"http://arxiv.org/abs/1703.10152v1","url_pdf":"http://arxiv.org/pdf/1703.10152v1.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":"automatic-argumentative-zoning-using-word2vec","repo_url":"https://github.com/abstatic/ire_project18","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"document-summarization","task_name":"Document Summarization"},{"task_slug":"feature-engineering","task_name":"Feature Engineering"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-classification","task_name":"Sentence Classification"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}