Researcher:
Sert, Ulaş

Profile Picture
ORCID

Job Title

Master Student

First Name

Ulaş

Last Name

Sert

Name

Name Variants

Sert, Ulaş

Email Address

Birth Date

Filters

20193

Advanced Search

Filter by

Settings

Researcher Of Publications: search.filters.isAuthorOfPublication.349645d9-ba17-4132-b8e1-b9b1f45d69ba

Search Results

Now showing 1 - 3 of 3
  • Placeholder
    PublicationMetadata only
    KU ai at MEDIQA 2019: domain-specific pre-training and transfer learning for medical NLI
    (Association for Computational Linguistics (ACL), 2019) Department of Computer Engineering; N/A; N/A; Yüret, Deniz; Sert, Ulaş; Cengiz, Cemil; Faculty Member; Master Student; Master Student; Department of Computer Engineering; College of Engineering; Graduate School of Sciences and Engineering; Graduate School of Sciences and Engineering
    In this paper, we describe our system and results submitted for the Natural Language Inference (NLI) track of the MEDIQA 2019 Shared Task (Ben Abacha et al., 2019). As KU ai team, we used BERT (Devlin et al., 2018) as our baseline model and pre-processed the MedNLI dataset to mitigate the negative impact of de-identification artifacts. Moreover, we investigated different pre-training and transfer learning approaches to improve the performance. We show that pre-training the language model on rich biomedical corpora has a significant effect in teaching the model domain-specific language. In addition, training the model on large NLI datasets such as MultiNLI and SNLI helps in learning task-specific reasoning. Finally, we ensembled our highest-performing models, and achieved 84.7% accuracy on the unseen test dataset and ranked 10th out of 17 teams in the official results.
  • Placeholder
    PublicationMetadata only
    KU_ai at MEDIQA 2019: domain-specific pre-training and transfer learning for medical NLI
    (assoc Computational Linguistics-acl, 2019) N/A; N/A; Department of Computer Engineering; Cengiz, Cemil; Sert, Ulaş; Yüret, Deniz; Master Student; Master Student; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; N/A; 179996
    in this paper, we describe our system and results submitted for the Natural Language inference (NLI) track of the MEDIQa 2019 Shared Task (Ben abacha et al., 2019). as KU ai team, we used BERT (Devlin et al., 2018) as our baseline model and pre-processed the MedNLI dataset to mitigate the negative impact of de-identification artifacts. Moreover, we investigated different pre-training and transfer learning approaches to improve the performance. We show that pre-training the language model on rich biomedical corpora has a significant effect in teaching the model domain-specific language. in addition, training the model on large NLI datasets such as MultiNLI and SNLI helps in learning task-specific reasoning. Finally, we ensembled our highest-performing models, and achieved 84.7% accuracy on the unseen test dataset and ranked 10th out of 17 teams in the official results.
  • Thumbnail Image
    PublicationOpen Access
    KU_ai at MEDIQA 2019: domain-specific pre-training and transfer learning for medical NLI
    (Association for Computational Linguistics (ACL), 2019) N/A; Department of Computer Engineering; Cengiz, Cemil; Sert, Ulaş; Yüret, Deniz; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; N/A; N/A; 179996
    In this paper, we describe our system and results submitted for the Natural Language Inference (NLI) track of the MEDIQA 2019 Shared Task (Ben Abacha et al., 2019). As KU ai team, we used BERT (Devlin et al., 2018) as our baseline model and pre-processed the MedNLI dataset to mitigate the negative impact of de-identification artifacts. Moreover, we investigated different pre-training and transfer learning approaches to improve the performance. We show that pre-training the language model on rich biomedical corpora has a significant effect in teaching the model domain-specific language. In addition, training the model on large NLI datasets such as MultiNLI and SNLI helps in learning task-specific reasoning. Finally, we ensembled our highest-performing models, and achieved 84.7% accuracy on the unseen test dataset and ranked 10th out of 17 teams in the official results.