Schedule

The workshop will be held online via Zoom on February 9, 2021. To access the Zoom link, please login into the AAAI 2021 virtual conference website at https://virtual.2021.aaai.org Note that registration at the AAAI 2021 conference is required to access the session.

The Scientific Document Understanding workshop also provides a poster session scheduled from 4:30 to 5:30 PM (PST) on Feb 9, 2021. The poster session will be held via Virtual Chair in Room E, accessible from the conference virtual website https://virtual.2021.aaai.org/posters.html


All times are Pacific Time (Vancouver) UTC-8


Workshop Schedule


  • 09:00 Opening Remarks

  • 09:05 Keynote I by Byron Wallace (Title: What does the evidence say? Language technologies to help make sense of biomedical texts)

  • 09:35 Keynote II by Hoifung Poon (Title: Machine Reading for Precision Medicine)

  • 10:05 Break

  • 10:20 On Generating Extended Summaries of Long Documents (by Sajad Sotudeh) (Paper)

  • 10:30 Unsupervised Key-phrase Extraction and Clustering for Classification Scheme in Scientific Publications (by Xiajing Li) (Paper)

  • 10:40 Diffusion-based Temporal Embeddings for Biomedical Entities (by Ahnaf Farhan) (Paper)

  • 10:50 Towards a Virtual Librarian for Biologically Inspired Design – Knowledge-Based Methods for Document Understanding (by Ruth Petit-Bois) (Paper)

  • 11:00 BERTKG-DDI: Towards incorporating Entity-specific Knowledge Graph information in predicting Drug-Drug Interactions (by Ishani Mondal) (Paper)

  • 11:10 Extraction of Formulaic Expressions from Scientific Papers (by Kenichi Iwatsuki) (Paper)

  • 11:20 Multi-span Style Extraction for Generative Reading Comprehension (by Junjie Yang) (Paper)

  • 11:30 A Paragraph-level Multi-task Learning Model for Scientific Fact-Verification (by Xiangci Li) (Paper)

  • 11:40 Automatic recognition of figurative language in biomedical articles (by Dina Demner-Fushman) (Paper)

  • 11:50 Probing the SpanBERT Architecture to interpret Scientific Domain Adaptation Challenges for Coreference Resolution (by Hari Timmapathini) (Paper)

  • 12:00 Graph Knowledge Extraction of Causal, Comparative, Predictive, and Proportional Associations in Scientific Claims with a Transformer-Based Model (by Ian H. Magnusson)

  • 12:10 Lunch Break

  • 12:40 Interaction Matching for Long-Tail Multi-Label Classification (by Sean Macavaney) (Paper)

  • 12:50 Dual Reinforcement-Based Specification Generation for Image De-Rendering (by Ramakanth Pasunuru) (Paper)

  • 13:00 Understood in translation: transformers for domain understanding (by Dimitrios Christofidellis) (Paper)

  • 13:10 Biomedical Corpus Filtering: A Weak Supervision Paradigm With Infused Domain Expertise (by Sejal Dua) (Paper)

  • 13:20 Name Entity Recognition from Synthesis Procedural Text in Materials Science Domain with Attention-Based Approach (by Huichen Yang) (Paper)

  • 13:30 Understanding and Predicting Retractions of Published Work (by Sai Ajay Modukuri) (Paper)

  • 13:40 Importance Assessment in Scholarly Networks (by Saurav Manchanda) (Paper)

  • 13:50 Toward A Robust Method for Understanding the Replicability of Research (by Ben Gelman) (Paper)

  • 14:00 Identifying Used Methods and Datasets in Scientific Publications (by Michael Färber) (Paper)

  • 14:10 Data Augmentations for Document Images (by Yunsung Lee) (Paper)

  • 14:20 Recognizing Figure Labels in Patents (by Ming Gong) (Paper)

  • 14:30 Improving Clinical Document Understanding on COVID-19 Research with Spark NLP (by Veysel Kocaman) (Paper)

  • 14:40 Break

  • 14:50 Acronym Identification and Disambiguation shared tasks at SDU@AAA-21 (by Amir Veyseh) (Paper)

  • 15:00 AT-BERT: Adversarial Training BERT for Acronym Identification Winning Solution for SDU@AAAI-21 (by Danqing Zhu) (Paper)

  • 15:10 BERT-based Acronym Disambiguation with Multiple Training Strategies (by Chunguang Pan) (Paper)

  • 15:20 Closing Remark


Poster Session


  • Participation of UC3M in SDU@AAAI-21: A Hybrid Approach to Disambiguate Scientific Acronyms (Areej Jaber) (Paper)

  • Effective Ensembling of Transformer based Language Models for Acronyms Identification (Divesh Kubal) (Paper)

  • Systems at SDU-2021 Task1: Transformers for sentence level sequence label (Wuhe Zou) (Paper)

  • Leveraging Domain Agnostic and Specific Knowledge for Acronym Disambiguation (Qiwei Zhong) (Paper)

  • AI-NLM exploration of the Acronym Identification and Disambiguation Shared Tasks at SDU@AAAI-21 (Willie Rogers) (Paper)

  • Primer AI's Systems for Acronym Identification and Disambiguation (Nicholas Egan) (Paper)

  • SciDr at SDU-2020 : IDEAS - Identifying and Disambiguating Everyday Acronyms for Scientific Domain (Aadarsh Singh) (Paper)

  • Acronym Expander at SDU@AAAI-21: an Acronym Disambiguation Module (João L. M. Pereira) (Paper)