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

arXiv: https://arxiv.org/abs/2205.06982 · HTML: https://mlsanity.com/paper/2205.06982/

## Key facts

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

## Builds on (most cited first, 22 of 22)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction](https://mlsanity.com/paper/1808.09602/) (2018)
- [Entity, Relation, and Event Extraction with Contextualized Span Representations](https://mlsanity.com/paper/1909.03546/) (2019)
- [Invertible generative models for inverse problems: mitigating representation error and dataset bias](https://mlsanity.com/paper/1905.11672/) (2019)
- [Enriching Pre-trained Language Model with Entity Information for Relation Classification](https://mlsanity.com/paper/1905.08284/) (2019)
- [Chasing Ghosts: Instruction Following as Bayesian State Tracking](https://mlsanity.com/paper/1907.02022/) (2019)
- [A Joint Model for Definition Extraction with Syntactic Connection and Semantic Consistency](https://mlsanity.com/paper/1911.01678/) (2019)
- [Bursting Scientific Filter Bubbles: Boosting Innovation via Novel Author Discovery](https://mlsanity.com/paper/2108.05669/) (2021)
- [Document-Level Definition Detection in Scholarly Documents: Existing Models, Error Analyses, and Future Directions](https://mlsanity.com/paper/2010.05129/) (2020)
- [Neural Particle Smoothing for Sampling from Conditional Sequence Models](https://mlsanity.com/paper/1804.10747/) (2018)
- [Retrofitting Contextualized Word Embeddings with Paraphrases](https://mlsanity.com/paper/1909.09700/) (2019)
- [Automated Discovery of Mathematical Definitions in Text with Deep Neural Networks](https://mlsanity.com/paper/2011.04521/) (2020)
- [Learning Compositional Representations of Interacting Systems with Restricted Boltzmann Machines: Comparative Study of Lattice Proteins](https://mlsanity.com/paper/1902.06495/) (2019)
- [High-Precision Extraction of Emerging Concepts from Scientific Literature](https://mlsanity.com/paper/2006.06877/) (2020)
- [On Variational Learning of Controllable Representations for Text without Supervision](https://mlsanity.com/paper/1905.11975/) (2019)
- [Order-Preserving Abstractive Summarization for Spoken Content Based on Connectionist Temporal Classification](https://mlsanity.com/paper/1709.05475/) (2017)
- [Truncated Gaussian-Mixture Variational AutoEncoder](https://mlsanity.com/paper/1902.03717/) (2019)
- [Opinion-Based Centrality in Multiplex Networks: A Convex Optimization Approach](https://mlsanity.com/paper/1703.03741/) (2017)
- [Phase Collaborative Network for Two-Phase Medical Image Segmentation](https://mlsanity.com/paper/1811.11814/) (2018)
- [Variational Autoencoders for Sparse and Overdispersed Discrete Data](https://mlsanity.com/paper/1905.00616/) (2019)
- [JUMT at WMT2019 News Translation Task: A Hybrid approach to Machine Translation for Lithuanian to English](https://mlsanity.com/paper/1908.01349/) (2019)

## Built on by (most cited first, 10 of 10)

- [Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrievers](https://mlsanity.com/paper/2311.09180/) (2023)
- [CiteME: Can Language Models Accurately Cite Scientific Claims?](https://mlsanity.com/paper/2407.12861/) (2024)
- [Leveraging Large Language Models for Learning Complex Legal Concepts through Storytelling](https://mlsanity.com/paper/2402.17019/) (2024)
- [Words as Gatekeepers: Measuring Discipline-specific Terms and Meanings in Scholarly Publications](https://mlsanity.com/paper/2212.09676/) (2022)
- [The Semantic Reader Project: Augmenting Scholarly Documents through AI-Powered Interactive Reading Interfaces](https://mlsanity.com/paper/2303.14334/) (2023)
- [KnowledgeShovel: An AI-in-the-Loop Document Annotation System for Scientific Knowledge Base Construction](https://mlsanity.com/paper/2210.02830/) (2022)
- [Generating Topic Pages for Scientific Concepts Using Scientific Publications](https://mlsanity.com/paper/2304.11922/) (2023)
- [Inferring Scientific Cross-Document Coreference and Hierarchy with Definition-Augmented Relational Reasoning](https://mlsanity.com/paper/2409.15113/) (2024)
- [TOPICAL: TOPIC Pages AutomagicaLly](https://mlsanity.com/paper/2405.01796/) (2024)
- [Explain Like I'm 5 or Whatever I Choose: Evaluating the Potential for Interactive Complexity in Language Model Responses](https://mlsanity.com/paper/2606.06788/) (2026)

## 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.