Using a Frustratingly Easy Domain and Tagset Adaptation for Creating Slavic Named Entity Recognition Systems
We present a collection of Named Entity Recognition (NER) systems for six Slavic languages: Bulgarian, Czech, Polish, Slovenian, Russian and Ukrainian. These NER systems have been trained using different BERT models and a Frustratingly Easy Domain Adaptation (FEDA). FEDA allow us creating NER systems using multiple datasets without having to worry about whether the tagset (e.g. Location, Event, Miscellaneous, Time) in the source and target domains match, while increasing the amount of data available for training. Moreover, we boosted the prediction on named entities by marking uppercase words and predicting masked words. Participating in the 3rd Shared Task on SlavNER, our NER systems reached a strict match micro F-score of up to 0.908. The results demonstrate good generalization, even in named entities with weak regularity, such as book titles, or entities that were never seen during the training.
Code (1)
Tasks
Domain AdaptationMiscellaneousnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NERSimilar Papers 제목 키워드 기반
Frustratingly Easy Uncertainty Estimation for Distribution Shift
Distribution shift is an important concern in deep image classification, produced either by corruption of the source images, or a complete change, with the solution involving domain adaptation. While the primary goal is …
Domain Adaptationimage-classificationImage ClassificationUnsupervised Domain AdaptationReturn of Frustratingly Easy Unsupervised Video Domain Adaptation
Unsupervised video domain adaptation (UVDA) is a practical but under-explored problem. In this paper, we propose a frustratingly easy UVDA method, called MetaTrans. Specifically, MetaTrans adopts a concise learning objec…
Action RecognitionDomain AdaptationReturn of Frustratingly Easy Domain Adaptation
Unlike human learning, machine learning often fails to handle changes between training (source) and test (target) input distributions. Such domain shifts, common in practical scenarios, severely damage the performance of…
BIG-bench Machine LearningDomain AdaptationUnsupervised Domain AdaptationFrustratingly Easy Domain Adaptation
We describe an approach to domain adaptation that is appropriate exactly in the case when one has enough ``target'' data to do slightly better than just using only ``source'' data. Our approach is incredibly simple, easy…
Domain AdaptationDeep CORAL: Correlation Alignment for Deep Domain Adaptation
Deep neural networks are able to learn powerful representations from large quantities of labeled input data, however they cannot always generalize well across changes in input distributions. Domain adaptation algorithms …
Domain AdaptationDomain GeneralizationImage ClassificationUnsupervised Domain Adaptation