mlsanityData to 7 Oct 2026

SciCo: Hierarchical Cross-Document Coreference for Scientific Concepts

arXiv 2104.08809 ↗First posted 18 Apr 2021cs.CL cs.IR cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

Determining coreference of concept mentions across multiple documents is a fundamental task in natural language understanding. Previous work on cross-document coreference resolution (CDCR) typically considers mentions of events in the news, which seldom involve abstract technical concepts that are prevalent in science and technology. These complex concepts take diverse or ambiguous forms and have many hierarchical levels of granularity (e.g., tasks and subtasks), posing challenges for CDCR. We present a new task of Hierarchical CDCR (H-CDCR) with the goal of jointly inferring coreference clusters and hierarchy between them. We create SciCo, an expert-annotated dataset for H-CDCR in scientific papers, 3X larger than the prominent ECB+ resource. We study strong baseline models that we customize for H-CDCR, and highlight challenges for future work.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 35 of its 67 references that are in the map. First posted on arXiv 18 Apr 2021.

Builds on

35 of 67 references.

References · 35

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2020Longformer: The Long-Document Transformercited by 3,362
  5. 2017Billion-scale similarity search with GPUscited by 2,477
  6. 2015A large annotated corpus for learning natural language inferencecited by 1,837
  7. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,548
  8. 2019SciBERT: A Pretrained Language Model for Scientific Textcited by 1,404
  9. 2017SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluationcited by 998
  10. 2018Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Constructioncited by 321
  11. 2019Entity, Relation, and Event Extraction with Contextualized Span Representationscited by 261
  12. 2017End-to-end Neural Coreference Resolutioncited by 240
23 more
  1. 2016Linear Algebraic Structure of Word Senses, with Applications to Polysemycited by 165
  2. 2018Breaking NLI Systems with Sentences that Require Simple Lexical Inferencescited by 134
  3. 2020SciREX: A Challenge Dataset for Document-Level Information Extractioncited by 111
  4. 2018TaxoGen: Unsupervised Topic Taxonomy Construction by Adaptive Term Embedding and Clusteringcited by 48
  5. 2019Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolutioncited by 43
  6. 2017Accelerating Innovation Through Analogy Miningcited by 32
  7. 2018Neural Models for Reasoning over Multiple Mentions using Coreferencecited by 27
  8. 2016Improving Hypernymy Detection with an Integrated Path-based and Distributional Methodcited by 26
  9. 2018Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corporacited by 26
  10. 2021WEC: Deriving a Large-scale Cross-document Event Coreference dataset from Wikipediacited by 23
  11. 2018Resolving Event Coreference with Supervised Representation Learning and Clustering-Oriented Regularizationcited by 22
  12. 2017Event Coreference Resolution by Iteratively Unfolding Inter-dependencies among Eventscited by 19
  13. 2021CSFCube -- A Test Collection of Computer Science Research Articles for Faceted Query by Examplecited by 19
  14. 2021CDLM: Cross-Document Language Modelingcited by 17
  15. 2020SciSight: Combining faceted navigation and research group detection for COVID-19 exploratory scientific searchcited by 16
  16. 2020Streamlining Cross-Document Coreference Resolution: Evaluation and Modelingcited by 16
  17. 2019Do Multi-hop Readers Dream of Reasoning Chains?cited by 14
  18. 2020Extracting a Knowledge Base of Mechanisms from COVID-19 Paperscited by 13
  19. 2017Multimodal Word Distributionscited by 12
  20. 2020CoRefi: A Crowd Sourcing Suite for Coreference Annotationcited by 12
  21. 2021CD2CR: Co-reference Resolution Across Documents and Domainscited by 9
  22. 2018Combining Distant and Direct Supervision for Neural Relation Extractioncited by 6
  23. 2021Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applicationscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 3; 2023: 4; 2024: 3; 2025: 1; 2026: 1.

14 papers.

Sort:

By area:

  1. 2023SciMON: Scientific Inspiration Machines Optimized for Noveltycited by 174
  2. 2021Entity Linking and Discovery via Arborescence-based Supervised Clusteringcited by 22
  3. 2022A Computational Inflection for Scientific Discoverycited by 22
  4. 2023Beyond Summarization: Designing AI Support for Real-World Expository Writing Taskscited by 20
  5. 2021Bursting Scientific Filter Bubbles: Boosting Innovation via Novel Author Discoverycited by 13
  6. 2022SsciBERT: A Pre-trained Language Model for Social Science Textscited by 12
  7. 2024MDCure: A Scalable Pipeline for Multi-Document Instruction-Followingcited by 10
  8. 2023From Key Points to Key Point Hierarchy: Structured and Expressive Opinion Summarizationcited by 8
  9. 2024SEAM: A Stochastic Benchmark for Multi-Document Taskscited by 8
  10. 2022EDIN: An End-to-end Benchmark and Pipeline for Unknown Entity Discovery and Indexingcited by 5
  11. 2024Inferring Scientific Cross-Document Coreference and Hierarchy with Definition-Augmented Relational Reasoningcited by 2
  12. 2025Enhancing Coreference Resolution with Pretrained Language Models: Bridging the Gap Between Syntax and Semanticscited by 1
2 more
  1. 2023CHAMP: Efficient Annotation and Consolidation of Cluster Hierarchiescited by 0
  2. 2026Do Lexical and Contextual Coreference Resolution Systems Degrade Differently under Mention Noise? An Empirical Study on Scientific Software Mentionscited by 0