{"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/representation-learning-for-very-short-texts","title":"Representation learning for very short texts using weighted word embedding aggregation","arxiv_id":"1607.00570","date":"2016-07-02","proceeding":null,"authors":["Cedric De Boom","Steven Van Canneyt","Thomas Demeester","Bart Dhoedt"],"abstract":"Short text messages such as tweets are very noisy and sparse in their use of\nvocabulary. Traditional textual representations, such as tf-idf, have\ndifficulty grasping the semantic meaning of such texts, which is important in\napplications such as event detection, opinion mining, news recommendation, etc.\nWe constructed a method based on semantic word embeddings and frequency\ninformation to arrive at low-dimensional representations for short texts\ndesigned to capture semantic similarity. For this purpose we designed a\nweight-based model and a learning procedure based on a novel median-based loss\nfunction. This paper discusses the details of our model and the optimization\nmethods, together with the experimental results on both Wikipedia and Twitter\ndata. We find that our method outperforms the baseline approaches in the\nexperiments, and that it generalizes well on different word embeddings without\nretraining. Our method is therefore capable of retaining most of the semantic\ninformation in the text, and is applicable out-of-the-box.","url_abs":"http://arxiv.org/abs/1607.00570v1","url_pdf":"http://arxiv.org/pdf/1607.00570v1.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":"representation-learning-for-very-short-texts","repo_url":"https://github.com/cedricdeboom/RepresentationLearning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"event-detection","task_name":"Event Detection"},{"task_slug":"news-recommendation","task_name":"News Recommendation"},{"task_slug":"opinion-mining","task_name":"Opinion Mining"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}