{"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/sector-a-neural-model-for-coherent-topic","title":"SECTOR: A Neural Model for Coherent Topic Segmentation and Classification","arxiv_id":"1902.04793","date":"2019-02-13","proceeding":"TACL 2019 3","authors":["Sebastian Arnold","Rudolf Schneider","Philippe Cudré-Mauroux","Felix A. Gers","Alexander Löser"],"abstract":"When searching for information, a human reader first glances over a document,\nspots relevant sections and then focuses on a few sentences for resolving her\nintention. However, the high variance of document structure complicates to\nidentify the salient topic of a given section at a glance. To tackle this\nchallenge, we present SECTOR, a model to support machine reading systems by\nsegmenting documents into coherent sections and assigning topic labels to each\nsection. Our deep neural network architecture learns a latent topic embedding\nover the course of a document. This can be leveraged to classify local topics\nfrom plain text and segment a document at topic shifts. In addition, we\ncontribute WikiSection, a publicly available dataset with 242k labeled sections\nin English and German from two distinct domains: diseases and cities. From our\nextensive evaluation of 20 architectures, we report a highest score of 71.6% F1\nfor the segmentation and classification of 30 topics from the English city\ndomain, scored by our SECTOR LSTM model with bloom filter embeddings and\nbidirectional segmentation. This is a significant improvement of 29.5 points F1\ncompared to state-of-the-art CNN classifiers with baseline segmentation.","url_abs":"http://arxiv.org/abs/1902.04793v1","url_pdf":"http://arxiv.org/pdf/1902.04793v1.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":"sector-a-neural-model-for-coherent-topic","repo_url":"https://github.com/sebastianarnold/SECTOR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"sector-a-neural-model-for-coherent-topic","repo_url":"https://github.com/sebastianarnold/WikiSection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"sector-a-neural-model-for-coherent-topic","repo_url":"https://github.com/sebastianarnold/TeXoo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[{"slug":"wikisection","name":"WikiSection","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.04793","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}