Workshop Schedule

The workshop will take place both in-person and online on Oct 17th, 2022 at COLING 2022.

KST (on 10/17) PT (on 10/16) ET (on 10/16) CET (on 10/17)
Virtual Poster Sesssion 1 (GatherTown)
Hosts: Anita de Waard & Dayne Freitag
  • A Japanese Masked Language Model for Academic Domain
  • Exploiting Unary Relations with Stacked Learning for Relation Extraction
  • Finding Scientific Topics in Continuously Growing Text Corpora
  • Incorporating the Rhetoric of Scientific Language into Sentence Embeddings using Phrase-guided Distant Supervision and Metric Learning
  • Lightweight Contextual Logical Structure Recovery
  • Named Entity Inclusion in Abstractive Text Summarization
  • Named Entity Recognition Based Automatic Generation of Research Highlights
  • Unsupervised Partial Sentence Matching for Cited Text Identification
  • Visualisation Methods for Diachronic Semantic Shift
  • Benchmark for Research Theme Classification of Scholarly Documents
  • Overview of MSLR2022: A Shared Task on Multi-document Summarization for Literature Reviews
  • SynSciPass: detecting appropriate uses of scientific text generation
 0:00-1:00 8:00-9:00 11:00-12:00 17:00-1-18:00-1
Opening 9:00-9:10 17:00-17:10 20:00-20:10 2:00-2:10
Keynote 1: Scholarly Document Processing Research in the Age of AI
Speaker: Min Yen Kan (National University of Singapore) 		9:10-9:55 17:10-17:55 20:10-20:55 2:10-2:55
Shared Task 1: SKGG: Scholarly Knowledge Graph Generation
Speakers: Oscar Espitiamendoza & Petr Knoth 		10:00-10:20 18:00-18:20 21:00-21:20 3:00-3:20
Shared Task 2: MSLR22: Multi-Document Summarization for Literature Reviews
Speakers: Yulia Otmakhova, Kartik Shinde & Lucy Lu Wang 		10:25-10:45 18:25-18:45 21:25-21:45 3:25-3:45
Coffee Break 10:45-11:00 18:45-19:00 21:45-22:00 3:45-4:00
Keynote 2: Designing the Interactive Paper: Exploring How Intelligent Interfaces Can Support the Reading of Scholarly Articles
Speaker: Andrew Head (University of Pennsylvania) 		11:00-11:45 19:00-19:45 22:00-22:45 4:00-4:45
Paper presentations (hybrid)
  • Identifying Medical Paraphrases in Scientific versus Popularization Texts in French for Laypeople Understanding presented by Ioana Buhnila
  • Incorporating the Rhetoric of Scientific Language into Sentence Embeddings using Phrase-guided Distant Supervision and Metric Learning presented by Kaito Sugimoto
  • Large-scale Evaluation of Transformer-based Article Encoders on the Task of Citation Recommendation presented by Zoran Medić
 11:45-12:10 19:45-20:10 22:45-23:10 4:45-5:10
Shared Task 3: MuP 2022: Multi Perspective Scientific Document Summarization
Speakers: Michal Shmueli-Scheuer, Tirthankar Ghosal & Guy Feigenblat 		12:15-12:35 20:15-20:35 23:15-23:35 5:15-5:35
Lunch 12:35-14:00 20:35-22:00 23:35-1:00+1 5:35-7:00
Shared Task 4: DAGPap22: Detecting automatically generated scientific papers
Speakers: Yury Kashnitsky, Cyril Labbé & Domenic Anthony Rosati 		14:00-14:20 22:00-22:20 1:00+1-1:20+1 7:00-7:20
Shared Task 5: SV-Ident 2022: Survey Variable Identification in Social Science Publications
Speakers: Tornike Tsereteli & Alica Hövelmeyer 		14:25-14:45 22:25-23:45 1:25+1-1:45+1 7:25-7:45
Keynote 3: Biomedical Text Summarisation: Methods and Challenges
Speaker: Sophia Ananiadou (University of Manchester) 		14:55-15:30 22:55-23:30 1:55+1-2:30+1 7:55-8:30
Coffee Break 15:30-16:00 23:30-0:00+1 2:30+1-3:00+1 8:30-9:00
In-person Poster Session
  • Identifying Medical Paraphrases in Scientific versus Popularization Texts in French for Laypeople Understanding
  • Incorporating the Rhetoric of Scientific Language into Sentence Embeddings using Phrase-guided Distant Supervision and Metric Learning
  • Large-scale Evaluation of Transformer-based Article Encoders on the Task of Citation Recommendation
  • Transferable Keyword Extraction and Generation from Scholarly Documents with Text-to-text Language Models
  • Benchmark for Research Theme Classification of Scholarly Documents
  • Evaluating Pre-Trained Language Models on Multi-Document Summarization for Literature Reviews
  • LED down the rabbit hole: exploring the potential of global attention for biomedical multi-document summarisation
 16:00-17:30 0:00+1-1:30+1 3:00+1-4:30+1 9:00-10:30
Virtual Poster Sesssion 2 (GatherTown)
Hosts: Philipp Mayr & Guy Feigenblat
  • Citation Context Classification: Critical vs Non-critical
  • Citation Sentence Generation Leveraging the Content of Cited Papers
  • Finding Scientific Topics in Continuously Growing Text Corpora
  • Identifying Medical Paraphrases in Scientific versus Popularization Texts in French for Laypeople Understanding
  • Investigating Metric Diversity for Evaluating Long Document Summarisation
  • Investigating the detection of Tortured Phrases in Scientific Literature
  • Large-scale Evaluation of Transformer-based Article Encoders on the Task of Citation Recommendation
  • Lightweight Contextual Logical Structure Recovery
  • Mitigating Data Shift of Biomedical Research Articles for Information Retrieval and Semantic Indexing
  • Named Entity Inclusion in Abstractive Text Summarization
  • Named Entity Recognition Based Automatic Generation of Research Highlights
  • Visualisation Methods for Diachronic Semantic Shift
  • Benchmark for Research Theme Classification of Scholarly Documents
  • Detecting Generated Scientific Papers using an Ensemble of Transformer Models
  • Exploring the limits of a base BART for multi-document summarization in the medical domain
  • LED down the rabbit hole: exploring the potential of global attention for biomedical multi-document summarisation
  • Team AINLPML @ MuP in SDP 2021: Scientific Document Summarization by End-to-End Extractive and Abstractive Approach
  • Varanalysis@SV-Ident 2022: Variable Detection and Disambiguation Based on Semantic Similarity
 18:00-19:00 2:00+1-3:00+1 5:00+1-6:00+1 11:00-12:00