مع سرعة البحوث المتزايدة بشكل مفيد والحجم المرتفع للاتصال العلمي، يواجه العلماء مهمة شاقة. ليس فقط يجب عليهم مواكبة الأدبيات المتزايدة في مجالاتهم ذات الصلة، كما يحتاج العلماء بشكل متزايد إلى إعادة صياغة العلوم الزائفة والإضاءة. تحفز هذه الاحتياجات تركيزا متزايدا على الأساليب الحسابية لتعزيز البحث والتلخيص وتحليل الوثائق العلمية. ومع ذلك، فإن خيوط البحث المختلفة بشأن معالجة الوثائق العلمية تظل مجزأة. للوصول إلى مجتمع NLP و AI / ML الأوسع، بجميع الجهود الموزعة في هذا المجال، وتمكين الوصول المشترك إلى البحث المنشور، عقدنا ورشة العمل الثانية بشأن معالجة الوثائق العلمية (SDP) في Naacl 2021 كحدث افتراضي (HTTPS: //sdproc.org/2021/). تتألف ورشة عمل SDP من مسار أبحاث وثلاثة محادثات مدعوة وثلاث مهام مشتركة (LongsUMM 2021، SEXIVER، و 3C). تم توجيه البرنامج نحو تطبيق NLP واسترجاع المعلومات والتعدين البيانات للمستندات العلمية، مع التركيز على تحديد وحلول الحلول لفتح التحديات.
With the ever-increasing pace of research and high volume of scholarly communication, scholars face a daunting task. Not only must they keep up with the growing literature in their own and related fields, scholars increasingly also need to rebut pseudo-science and disinformation. These needs have motivated an increasing focus on computational methods for enhancing search, summarization, and analysis of scholarly documents. However, the various strands of research on scholarly document processing remain fragmented. To reach out to the broader NLP and AI/ML community, pool distributed efforts in this area, and enable shared access to published research, we held the 2nd Workshop on Scholarly Document Processing (SDP) at NAACL 2021 as a virtual event (https://sdproc.org/2021/). The SDP workshop consisted of a research track, three invited talks, and three Shared Tasks (LongSumm 2021, SCIVER, and 3C). The program was geared towards the application of NLP, information retrieval, and data mining for scholarly documents, with an emphasis on identifying and providing solutions to open challenges.
References used
https://aclanthology.org/
This paper presents the results of the shared tasks from the 8th workshop on Asian translation (WAT2021). For the WAT2021, 28 teams participated in the shared tasks and 24 teams submitted their translation results for the human evaluation. We also ac
Argument mining targets structures in natural language related to interpretation and persuasion which are central to scientific communication. Most scholarly discourse involves interpreting experimental evidence and attempting to persuade other scien
We present the GermEval 2021 shared task on the identification of toxic, engaging, and fact-claiming comments. This shared task comprises three binary classification subtasks with the goal to identify: toxic comments, engaging comments, and comments
In this paper, we introduce the Eval4NLP-2021 shared task on explainable quality estimation. Given a source-translation pair, this shared task requires not only to provide a sentence-level score indicating the overall quality of the translation, but
Recent advances in NLP systems, notably the pretraining-and-finetuning paradigm, have achieved great success in predictive accuracy. However, these systems are usually not well calibrated for uncertainty out-of-the-box. Many recalibration methods hav