في هذه الورقة، نقدم تجارب حل النواة مع كورفوس كورفوس متعددة اللغات التي تم إنشاؤها حديثا (Nedoluzhko et al.، 2021).نحن نركز على اللغات التالية: التشيكية والروسية والبولندية والألمانية والإسبانية والكاتالونية.بالإضافة إلى التجارب أحادية الأحادية، نجمع بين بيانات التدريب في تجارب متعددة اللغات وتدريب نماذج متضررة - لغلق سلافية وللجميع اللغات معا.نحن نعتمد على نموذج التعلم العميق في نهاية إلى نهاية تتكيف قليلا مع Corefud Corpus.تظهر نتائجنا أنه يمكننا الاستفادة من التعليقات التوضيحية المنسقة، واستخدام النماذج الانضمام تساعد بشكل كبير على اللغات مع بيانات التدريب الأصغر.
In this paper, we present coreference resolution experiments with a newly created multilingual corpus CorefUD (Nedoluzhko et al.,2021). We focus on the following languages: Czech, Russian, Polish, German, Spanish, and Catalan. In addition to monolingual experiments, we combine the training data in multilingual experiments and train two joined models - for Slavic languages and for all the languages together. We rely on an end-to-end deep learning model that we slightly adapted for the CorefUD corpus. Our results show that we can profit from harmonized annotations, and using joined models helps significantly for the languages with smaller training data.
References used
https://aclanthology.org/
One can find dozens of data resources for various languages in which coreference - a relation between two or more expressions that refer to the same real-world entity - is manually annotated. One could also assume that such expressions usually consti
Contrastive Learning has emerged as a powerful representation learning method and facilitates various downstream tasks especially when supervised data is limited. How to construct efficient contrastive samples through data augmentation is key to its
Relating entities and events in text is a key component of natural language understanding. Cross-document coreference resolution, in particular, is important for the growing interest in multi-document analysis tasks. In this work we propose a new mod
Media coverage has a substantial effect on the public perception of events. Nevertheless, media outlets are often biased. One way to bias news articles is by altering the word choice. The automatic identification of bias by word choice is challenging
We study a new problem of cross-lingual transfer learning for event coreference resolution (ECR) where models trained on data from a source language are adapted for evaluations in different target languages. We introduce the first baseline model for