Pub Date : 2020-12-21DOI: 10.1109/CSICC52343.2021.9420563
Mehrdad Farahani, Mohammad Gharachorloo, M. Manthouri
Text summarization is one of the most critical Natural Language Processing (NLP) tasks. More and more researches are conducted in this field every day. Pre-trained transformer-based encoder-decoder models have begun to gain popularity for these tasks. This paper proposes two methods to address this task and introduces a novel dataset named pn-summary for Persian abstractive text summarization. The models employed in this paper are mT5 and an encoder-decoder version of the ParsBERT model (i.e., a monolingual BERT model for Persian). These models are fine-tuned on the pn-summary dataset. The current work is the first of its kind and, by achieving promising results, can serve as a baseline for any future work.
{"title":"Leveraging ParsBERT and Pretrained mT5 for Persian Abstractive Text Summarization","authors":"Mehrdad Farahani, Mohammad Gharachorloo, M. Manthouri","doi":"10.1109/CSICC52343.2021.9420563","DOIUrl":"https://doi.org/10.1109/CSICC52343.2021.9420563","url":null,"abstract":"Text summarization is one of the most critical Natural Language Processing (NLP) tasks. More and more researches are conducted in this field every day. Pre-trained transformer-based encoder-decoder models have begun to gain popularity for these tasks. This paper proposes two methods to address this task and introduces a novel dataset named pn-summary for Persian abstractive text summarization. The models employed in this paper are mT5 and an encoder-decoder version of the ParsBERT model (i.e., a monolingual BERT model for Persian). These models are fine-tuned on the pn-summary dataset. The current work is the first of its kind and, by achieving promising results, can serve as a baseline for any future work.","PeriodicalId":374593,"journal":{"name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129907312","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-03DOI: 10.1109/CSICC52343.2021.9420578
Peyman Tahghighi, R. Zoroofi, Sareh Saffi, Alireza Ramezani
For screening of eye retina, the information about elevations in different parts can assist ophthalmologists to diagnose diseases better. However, fundus images which are one of the most common screening modalities for retina diagnosis lack this information due to their 2D nature. Hence, in this work, we try to automatically reconstruct this height information from a single color fundus image. Recent approaches have used shading information for reconstructing the heights but their output is not accurate since the utilized information is not sufficient. Additionally, other methods were dependent on the availability of more than one image of the eye which is not available in practice. In this paper, motivated by the success of Conditional Generative Adversarial Networks(cGANs) and deeply supervised networks, we propose a novel architecture for the generator which enhances the details in a sequence of steps. Comparisons on our dataset illustrate that the proposed method outperforms all of the state-of-the-art methods in image translation and medical image translation on this particular task. Additionally, clinical studies also indicate that the proposed method can provide additional information for ophthalmologists for diagnosis.
{"title":"Heightmap Reconstruction of Macula on Color Fundus Images Using Conditional Generative Adversarial Networks","authors":"Peyman Tahghighi, R. Zoroofi, Sareh Saffi, Alireza Ramezani","doi":"10.1109/CSICC52343.2021.9420578","DOIUrl":"https://doi.org/10.1109/CSICC52343.2021.9420578","url":null,"abstract":"For screening of eye retina, the information about elevations in different parts can assist ophthalmologists to diagnose diseases better. However, fundus images which are one of the most common screening modalities for retina diagnosis lack this information due to their 2D nature. Hence, in this work, we try to automatically reconstruct this height information from a single color fundus image. Recent approaches have used shading information for reconstructing the heights but their output is not accurate since the utilized information is not sufficient. Additionally, other methods were dependent on the availability of more than one image of the eye which is not available in practice. In this paper, motivated by the success of Conditional Generative Adversarial Networks(cGANs) and deeply supervised networks, we propose a novel architecture for the generator which enhances the details in a sequence of steps. Comparisons on our dataset illustrate that the proposed method outperforms all of the state-of-the-art methods in image translation and medical image translation on this particular task. Additionally, clinical studies also indicate that the proposed method can provide additional information for ophthalmologists for diagnosis.","PeriodicalId":374593,"journal":{"name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","volume":"153 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122772681","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.1109/csicc52343.2021.9420584
{"title":"26th International Computer Conference, Computer Society of Iran [ISBN]","authors":"","doi":"10.1109/csicc52343.2021.9420584","DOIUrl":"https://doi.org/10.1109/csicc52343.2021.9420584","url":null,"abstract":"","PeriodicalId":374593,"journal":{"name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117344942","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：