# A Joint Model for Definition Extraction with Syntactic Connection and Semantic Consistency

arXiv: https://arxiv.org/abs/1911.01678 · HTML: https://mlsanity.com/paper/1911.01678/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2019.

## Built on by (most cited first, 14 of 14)

- [Understanding Jargon: Combining Extraction and Generation for Definition Modeling](https://mlsanity.com/paper/2111.07267/) (2021)
- [Graphine: A Dataset for Graph-aware Terminology Definition Generation](https://mlsanity.com/paper/2109.04018/) (2021)
- [ACCoRD: A Multi-Document Approach to Generating Diverse Descriptions of Scientific Concepts](https://mlsanity.com/paper/2205.06982/) (2022)
- [MadDog: A Web-based System for Acronym Identification and Disambiguation](https://mlsanity.com/paper/2101.09893/) (2021)
- [SemEval 2022 Task 12: Symlink- Linking Mathematical Symbols to their Descriptions](https://mlsanity.com/paper/2202.09695/) (2022)
- [Generating Topic Pages for Scientific Concepts Using Scientific Publications](https://mlsanity.com/paper/2304.11922/) (2023)
- [Parmesan: mathematical concept extraction for education](https://mlsanity.com/paper/2307.06699/) (2023)
- [Discovering Patterns of Definitions and Methods from Scientific Documents](https://mlsanity.com/paper/2307.01216/) (2023)
- [Envisioning the Next-Gen Document Reader](https://mlsanity.com/paper/2302.07492/) (2023)
- [WIKITIDE: A Wikipedia-Based Timestamped Definition Pairs Dataset](https://mlsanity.com/paper/2308.03582/) (2023)
- [Mathematical Entities: Corpora and Benchmarks](https://mlsanity.com/paper/2406.11577/) (2024)
- [Transformer-Based Extraction of Statutory Definitions from the U.S. Code](https://mlsanity.com/paper/2504.16353/) (2025)
- [Breaking the Curse of Knowledge: Designing Personalized Jargon Support for Real-Time Online Meetings](https://mlsanity.com/paper/2508.10239/) (2025)
- [SciDef: Datasets and Tools for Automated Definition Extraction from Scientific Literature with LLMs](https://mlsanity.com/paper/2602.05413/) (2026)

## Abstract (arXiv)

Definition Extraction (DE) is one of the well-known topics in Information Extraction that aims to identify terms and their corresponding definitions in unstructured texts. This task can be formalized either as a sentence classification task (i.e., containing term-definition pairs or not) or a sequential labeling task (i.e., identifying the boundaries of the terms and definitions). The previous works for DE have only focused on one of the two approaches, failing to model the inter-dependencies between the two tasks. In this work, we propose a novel model for DE that simultaneously performs the two tasks in a single framework to benefit from their inter-dependencies. Our model features deep learning architectures to exploit the global structures of the input sentences as well as the semantic consistencies between the terms and the definitions, thereby improving the quality of the representation vectors for DE. Besides the joint inference between sentence classification and sequential labeling, the proposed model is fundamentally different from the prior work for DE in that the prior work has only employed the local structures of the input sentences (i.e., word-to-word relations), and not yet considered the semantic consistencies between terms and definitions. In order to implement these novel ideas, our model presents a multi-task learning framework that employs graph convolutional neural networks and predicts the dependency paths between the terms and the definitions. We also seek to enforce the consistency between the representations of the terms and definitions both globally (i.e., increasing semantic consistency between the representations of the entire sentences and the terms/definitions) and locally (i.e., promoting the similarity between the representations of the terms and the definitions).