{"project":[{"name":"SFB 901","_id":"1"},{"_id":"3","name":"SFB 901 - Project Area B"},{"_id":"9","name":"SFB 901 - Subproject B1"}],"department":[{"_id":"579"}],"user_id":"58701","publisher":"Springer","citation":{"chicago":"Kersting, Joschka, and Michaela Geierhos. “Human Language Comprehension in Aspect Phrase Extraction with Importance Weighting.” In <i>Natural Language Processing and Information Systems</i>, edited by Epaminondas Kapetanios, Helmut Horacek, Elisabeth Métais, and Farid Meziane, 12801:231--242. Lecture Notes in Computer Science. Saarbrücken, Germany: Springer, 2021.","bibtex":"@inbook{Kersting_Geierhos_2021, place={Saarbrücken, Germany}, series={Lecture Notes in Computer Science}, title={Human Language Comprehension in Aspect Phrase Extraction with Importance Weighting}, volume={12801}, booktitle={Natural Language Processing and Information Systems}, publisher={Springer}, author={Kersting, Joschka and Geierhos, Michaela}, editor={Kapetanios, Epaminondas and Horacek, Helmut and Métais, Elisabeth and Meziane, Farid}, year={2021}, pages={231--242}, collection={Lecture Notes in Computer Science} }","ama":"Kersting J, Geierhos M. Human Language Comprehension in Aspect Phrase Extraction with Importance Weighting. In: Kapetanios E, Horacek H, Métais E, Meziane F, eds. <i>Natural Language Processing and Information Systems</i>. Vol 12801. Lecture Notes in Computer Science. Springer; 2021:231--242.","short":"J. Kersting, M. Geierhos, in: E. Kapetanios, H. Horacek, E. Métais, F. Meziane (Eds.), Natural Language Processing and Information Systems, Springer, Saarbrücken, Germany, 2021, pp. 231--242.","ieee":"J. Kersting and M. Geierhos, “Human Language Comprehension in Aspect Phrase Extraction with Importance Weighting,” in <i>Natural Language Processing and Information Systems</i>, vol. 12801, E. Kapetanios, H. Horacek, E. Métais, and F. Meziane, Eds. Saarbrücken, Germany: Springer, 2021, pp. 231--242.","apa":"Kersting, J., &#38; Geierhos, M. (2021). Human Language Comprehension in Aspect Phrase Extraction with Importance Weighting. In E. Kapetanios, H. Horacek, E. Métais, &#38; F. Meziane (Eds.), <i>Natural Language Processing and Information Systems</i> (Vol. 12801, pp. 231--242). Springer.","mla":"Kersting, Joschka, and Michaela Geierhos. “Human Language Comprehension in Aspect Phrase Extraction with Importance Weighting.” <i>Natural Language Processing and Information Systems</i>, edited by Epaminondas Kapetanios et al., vol. 12801, Springer, 2021, pp. 231--242."},"series_title":"Lecture Notes in Computer Science","editor":[{"last_name":"Kapetanios","full_name":"Kapetanios, Epaminondas","first_name":"Epaminondas"},{"full_name":"Horacek, Helmut","last_name":"Horacek","first_name":"Helmut"},{"last_name":"Métais","full_name":"Métais, Elisabeth","first_name":"Elisabeth"},{"full_name":"Meziane, Farid","last_name":"Meziane","first_name":"Farid"}],"date_updated":"2022-07-14T08:00:56Z","has_accepted_license":"1","publication_status":"published","language":[{"iso":"eng"}],"title":"Human Language Comprehension in Aspect Phrase Extraction with Importance Weighting","file":[{"date_created":"2022-07-14T08:00:35Z","success":1,"file_id":"32362","access_level":"closed","relation":"main_file","content_type":"application/pdf","file_name":"Kersting & Geierhos (2021b), Kersting2021b.pdf","creator":"jkers","date_updated":"2022-07-14T08:00:35Z","file_size":506329}],"place":"Saarbrücken, Germany","ddc":["004"],"abstract":[{"lang":"eng","text":"In this study, we describe a text processing pipeline that transforms user-generated text into structured data. To do this, we train neural and transformer-based models for aspect-based sentiment analysis. As most research deals with explicit aspects from product or service data, we extract and classify implicit and explicit aspect phrases from German-language physician review texts. Patients often rate on the basis of perceived friendliness or competence. The vocabulary is difficult, the topic sensitive, and the data user-generated. The aspect phrases come with various wordings using insertions and are not noun-based, which makes the presented case equally relevant and reality-based. To find complex, indirect aspect phrases, up-to-date deep learning approaches must be combined with supervised training data. We describe three aspect phrase datasets, one of them new, as well as a newly annotated aspect polarity dataset. Alongside this, we build an algorithm to rate the aspect phrase importance. All in all, we train eight transformers on the new raw data domain, compare 54 neural aspect extraction models and, based on this, create eight aspect polarity models for our pipeline. These models are evaluated by using Precision, Recall, and F-Score measures. Finally, we evaluate our aspect phrase importance measure algorithm."}],"volume":12801,"status":"public","author":[{"first_name":"Joschka","id":"58701","last_name":"Kersting","full_name":"Kersting, Joschka"},{"full_name":"Geierhos, Michaela","last_name":"Geierhos","id":"42496","first_name":"Michaela","orcid":"0000-0002-8180-5606"}],"year":"2021","conference":{"location":"Saarbrücken, Germany","start_date":"2021-06-23","name":"26th International Conference on Natural Language & Information Systems (NLDB 2021)","end_date":"2021-06-25"},"_id":"22052","intvolume":"     12801","file_date_updated":"2022-07-14T08:00:35Z","page":"231--242","type":"book_chapter","date_created":"2021-05-07T16:31:05Z","publication":"Natural Language Processing and Information Systems"}