{"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/paraphrase-thought-sentence-embedding-module","title":"Paraphrase Thought: Sentence Embedding Module Imitating Human Language Recognition","arxiv_id":"1808.05505","date":"2018-08-16","proceeding":null,"authors":["Myeongjun Jang","Pilsung Kang"],"abstract":"Sentence embedding is an important research topic in natural language\nprocessing. It is essential to generate a good embedding vector that fully\nreflects the semantic meaning of a sentence in order to achieve an enhanced\nperformance for various natural language processing tasks, such as machine\ntranslation and document classification. Thus far, various sentence embedding\nmodels have been proposed, and their feasibility has been demonstrated through\ngood performances on tasks following embedding, such as sentiment analysis and\nsentence classification. However, because the performances of sentence\nclassification and sentiment analysis can be enhanced by using a simple\nsentence representation method, it is not sufficient to claim that these models\nfully reflect the meanings of sentences based on good performances for such\ntasks. In this paper, inspired by human language recognition, we propose the\nfollowing concept of semantic coherence, which should be satisfied for a good\nsentence embedding method: similar sentences should be located close to each\nother in the embedding space. Then, we propose the Paraphrase-Thought\n(P-thought) model to pursue semantic coherence as much as possible.\nExperimental results on two paraphrase identification datasets (MS COCO and STS\nbenchmark) show that the P-thought models outperform the benchmarked sentence\nembedding methods.","url_abs":"http://arxiv.org/abs/1808.05505v3","url_pdf":"http://arxiv.org/pdf/1808.05505v3.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":"paraphrase-thought-sentence-embedding-module","repo_url":"https://github.com/MJ-Jang/Paraphrase-Thought","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"document-classification","task_name":"Document Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"paraphrase-identification","task_name":"Paraphrase Identification"},{"task_slug":"sts","task_name":"STS"},{"task_slug":"sts-benchmark","task_name":"STS Benchmark"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-classification","task_name":"Sentence Classification"},{"task_slug":"sentence-embedding","task_name":"Sentence Embedding"},{"task_slug":"sentence-embedding-1","task_name":"Sentence-Embedding"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}