Graphine: A Dataset for Graph-aware Terminology Definition Generation
- URL: http://arxiv.org/abs/2109.04018v1
- Date: Thu, 9 Sep 2021 03:29:23 GMT
- Title: Graphine: A Dataset for Graph-aware Terminology Definition Generation
- Authors: Zequn Liu, Shukai Wang, Yiyang Gu, Ruiyi Zhang, Ming Zhang, Sheng Wang
- Abstract summary: We present a large-scale terminology definition dataset Graphine covering 2,010,648 terminology definition pairs.
We propose a novel graph-aware definition generation model Graphex that integrates transformer with graph neural network.
- Score: 17.978450464176863
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Precisely defining the terminology is the first step in scientific
communication. Developing neural text generation models for definition
generation can circumvent the labor-intensity curation, further accelerating
scientific discovery. Unfortunately, the lack of large-scale terminology
definition dataset hinders the process toward definition generation. In this
paper, we present a large-scale terminology definition dataset Graphine
covering 2,010,648 terminology definition pairs, spanning 227 biomedical
subdisciplines. Terminologies in each subdiscipline further form a directed
acyclic graph, opening up new avenues for developing graph-aware text
generation models. We then proposed a novel graph-aware definition generation
model Graphex that integrates transformer with graph neural network. Our model
outperforms existing text generation models by exploiting the graph structure
of terminologies. We further demonstrated how Graphine can be used to evaluate
pretrained language models, compare graph representation learning methods and
predict sentence granularity. We envision Graphine to be a unique resource for
definition generation and many other NLP tasks in biomedicine.
Related papers
- Graph Lineages and Skeletal Graph Products [0.0]
Graphs, and sequences of growing graphs, can be used to specify the architecture of mathematical models in many fields including machine learning and computational science.<n>We define structured graph "lineages" that grow in a hierarchical fashion, so that the number of graph vertices and edges increases exponentially in level number.<n>We demonstrate such application to deep neural networks (including visual and feature scale spaces) and to multigrid numerical methods.
arXiv Detail & Related papers (2025-07-31T22:31:34Z) - Graph Prompting for Graph Learning Models: Recent Advances and Future Directions [75.7773954442738]
"Pre-training, adaptation" scheme first pre-trains graph learning models on unlabeled graph data in a self-supervised manner.<n> graph prompting emerges as a promising approach that learns trainable prompts while keeping the pre-trained graph learning models unchanged.
arXiv Detail & Related papers (2025-06-10T01:27:19Z) - GraphLSS: Integrating Lexical, Structural, and Semantic Features for Long Document Extractive Summarization [19.505955857963855]
We present GraphLSS, a heterogeneous graph construction for long document extractive summarization.
It defines two levels of information (words and sentences) and four types of edges (sentence semantic similarity, sentence occurrence order, word in sentence, and word semantic similarity) without any need for auxiliary learning models.
arXiv Detail & Related papers (2024-10-25T23:48:59Z) - Graph Generation with Diffusion Mixture [57.78958552860948]
Generation of graphs is a major challenge for real-world tasks that require understanding the complex nature of their non-Euclidean structures.
We propose a generative framework that models the topology of graphs by explicitly learning the final graph structures of the diffusion process.
arXiv Detail & Related papers (2023-02-07T17:07:46Z) - State of the Art and Potentialities of Graph-level Learning [54.68482109186052]
Graph-level learning has been applied to many tasks including comparison, regression, classification, and more.
Traditional approaches to learning a set of graphs rely on hand-crafted features, such as substructures.
Deep learning has helped graph-level learning adapt to the growing scale of graphs by extracting features automatically and encoding graphs into low-dimensional representations.
arXiv Detail & Related papers (2023-01-14T09:15:49Z) - Explanation Graph Generation via Pre-trained Language Models: An
Empirical Study with Contrastive Learning [84.35102534158621]
We study pre-trained language models that generate explanation graphs in an end-to-end manner.
We propose simple yet effective ways of graph perturbations via node and edge edit operations.
Our methods lead to significant improvements in both structural and semantic accuracy of explanation graphs.
arXiv Detail & Related papers (2022-04-11T00:58:27Z) - GraphFormers: GNN-nested Transformers for Representation Learning on
Textual Graph [53.70520466556453]
We propose GraphFormers, where layerwise GNN components are nested alongside the transformer blocks of language models.
With the proposed architecture, the text encoding and the graph aggregation are fused into an iterative workflow.
In addition, a progressive learning strategy is introduced, where the model is successively trained on manipulated data and original data to reinforce its capability of integrating information on graph.
arXiv Detail & Related papers (2021-05-06T12:20:41Z) - ExplaGraphs: An Explanation Graph Generation Task for Structured
Commonsense Reasoning [65.15423587105472]
We present a new generative and structured commonsense-reasoning task (and an associated dataset) of explanation graph generation for stance prediction.
Specifically, given a belief and an argument, a model has to predict whether the argument supports or counters the belief and also generate a commonsense-augmented graph that serves as non-trivial, complete, and unambiguous explanation for the predicted stance.
A significant 83% of our graphs contain external commonsense nodes with diverse structures and reasoning depths.
arXiv Detail & Related papers (2021-04-15T17:51:36Z) - Promoting Graph Awareness in Linearized Graph-to-Text Generation [72.83863719868364]
We study the ability of linearized models to encode local graph structures.
Our findings motivate solutions to enrich the quality of models' implicit graph encodings.
We find that these denoising scaffolds lead to substantial improvements in downstream generation in low-resource settings.
arXiv Detail & Related papers (2020-12-31T18:17:57Z) - A Systematic Survey on Deep Generative Models for Graph Generation [16.546379779385575]
Graph generation considers learning the distributions of given graphs and generating more novel graphs.
Recent advances in deep generative models for graph generation is an important step towards improving the fidelity of generated graphs.
This article provides an extensive overview of literature in the field of deep generative models for graph generation.
arXiv Detail & Related papers (2020-07-13T20:56:27Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.