mlsanityData to 7 Oct 2026

ACCoRD: A Multi-Document Approach to Generating Diverse Descriptions of Scientific Concepts

arXiv 2205.06982 ↗First posted 14 May 2022cs.CL cs.AI cs.HCcited by 10

Not on the map. Why?

Abstract (arXiv)

Systems that can automatically define unfamiliar terms hold the promise of improving the accessibility of scientific texts, especially for readers who may lack prerequisite background knowledge. However, current systems assume a single "best" description per concept, which fails to account for the many potentially useful ways a concept can be described. We present ACCoRD, an end-to-end system tackling the novel task of generating sets of descriptions of scientific concepts. Our system takes advantage of the myriad ways a concept is mentioned across the scientific literature to produce distinct, diverse descriptions of target scientific concepts in terms of different reference concepts. To support research on the task, we release an expert-annotated resource, the ACCoRD corpus, which includes 1,275 labeled contexts and 1,787 hand-authored concept descriptions. We conduct a user study demonstrating that (1) users prefer descriptions produced by our end-to-end system, and (2) users prefer multiple descriptions to a single "best" description.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 22 of its 42 references that are in the map. First posted on arXiv 14 May 2022.

Builds on

22 of 42 references.

References · 22

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019SciBERT: A Pretrained Language Model for Scientific Textcited by 1,404
  3. 2018Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Constructioncited by 321
  4. 2019Entity, Relation, and Event Extraction with Contextualized Span Representationscited by 261
  5. 2019Invertible generative models for inverse problems: mitigating representation error and dataset biascited by 93
  6. 2019Enriching Pre-trained Language Model with Entity Information for Relation Classificationcited by 82
  7. 2019Chasing Ghosts: Instruction Following as Bayesian State Trackingcited by 41
  8. 2019A Joint Model for Definition Extraction with Syntactic Connection and Semantic Consistencycited by 14
  9. 2021Bursting Scientific Filter Bubbles: Boosting Innovation via Novel Author Discoverycited by 13
  10. 2020Document-Level Definition Detection in Scholarly Documents: Existing Models, Error Analyses, and Future Directionscited by 11
  11. 2018Neural Particle Smoothing for Sampling from Conditional Sequence Modelscited by 7
  12. 2019Retrofitting Contextualized Word Embeddings with Paraphrasescited by 6
10 more
  1. 2020Automated Discovery of Mathematical Definitions in Text with Deep Neural Networkscited by 6
  2. 2019Learning Compositional Representations of Interacting Systems with Restricted Boltzmann Machines: Comparative Study of Lattice Proteinscited by 5
  3. 2020High-Precision Extraction of Emerging Concepts from Scientific Literaturecited by 5
  4. 2019On Variational Learning of Controllable Representations for Text without Supervisioncited by 3
  5. 2017Order-Preserving Abstractive Summarization for Spoken Content Based on Connectionist Temporal Classificationcited by 2
  6. 2019Truncated Gaussian-Mixture Variational AutoEncodercited by 2
  7. 2017Opinion-Based Centrality in Multiplex Networks: A Convex Optimization Approachcited by 1
  8. 2018Phase Collaborative Network for Two-Phase Medical Image Segmentationcited by 1
  9. 2019Variational Autoencoders for Sparse and Overdispersed Discrete Datacited by 1
  10. 2019JUMT at WMT2019 News Translation Task: A Hybrid approach to Machine Translation for Lithuanian to Englishcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 3; 2024: 4; 2025: 0; 2026: 1.

10 papers.

  1. 2023Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrieverscited by 91
  2. 2024CiteME: Can Language Models Accurately Cite Scientific Claims?cited by 45
  3. 2024Leveraging Large Language Models for Learning Complex Legal Concepts through Storytellingcited by 23
  4. 2022Words as Gatekeepers: Measuring Discipline-specific Terms and Meanings in Scholarly Publicationscited by 14
  5. 2023The Semantic Reader Project: Augmenting Scholarly Documents through AI-Powered Interactive Reading Interfacescited by 9
  6. 2022KnowledgeShovel: An AI-in-the-Loop Document Annotation System for Scientific Knowledge Base Constructioncited by 2
  7. 2023Generating Topic Pages for Scientific Concepts Using Scientific Publicationscited by 2
  8. 2024Inferring Scientific Cross-Document Coreference and Hierarchy with Definition-Augmented Relational Reasoningcited by 2
  9. 2024TOPICAL: TOPIC Pages AutomagicaLlycited by 0
  10. 2026Explain Like I'm 5 or Whatever I Choose: Evaluating the Interactive Potential of Language Model Responsescited by 0