ENT-DESC: Entity Description Generation by Exploring Knowledge Graph

Cheng, Liying; Wu, Dekun; Zhang, Yan; Jie, Zhanming; Lu, Wei; Si, Luo

doi:10.48550/arxiv.2004.14813

Cited by 4 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(Zhu et al, 2020) proposes a fact-aware summarization model to ensure that the content generated by the model conforms to factual logic. The MGCN models (Cheng et al, 2020) adopt multiple graph transformations to obtain the context feature in different scales, which achieve great performance on KG-to-text tasks. (Chen et al, 2020) and (Ji et al, 2020) use PLM models with knowledge injection to generate the content with commonsense.…”

Section: Kg-to-textmentioning

confidence: 99%

“…ENT-DESC The ENT-DESC dataset (Cheng et al, 2020) is extracted from Wikipedia with more than 9.9 million pages. The dataset contains domains like humans, events, locations, etc.…”

Section: Datasetmentioning

confidence: 99%

“…It consists of 110k instances and is significantly larger than related data-to-text datasets such as WebNLG (Gardent et al, 2017), AGENDA (Koncel-Kedziorski et al, 2019), and E2E (Novikova et al, 2017). We follow the same experiment setup of (Cheng et al, 2020), the dataset is randomly split into three subsets for the training set (80%), development set (10%), and test set (10%). Table 1 presents the statistics of the datasets.…”

Section: Datasetmentioning

confidence: 99%

“…In this work, we adopt the GPT-2 as System 1, and System 2 is an extractor implemented based on a graph convolutional neural network (GCN). To effect our implantation, our model evaluates two large-scale KG-to-text datasets called ENT-DESC (Cheng et al, 2020) and Person and Animal (Vrandeči c & Krötzsch, 2014).…”

mentioning

confidence: 99%

See 3 more Smart Citations

CogNLG: Cognitive graph for KG‐to‐text generation

Lai,

Ye,

et al. 2023

Expert Systems

View full text Add to dashboard Cite

Knowledge graph (KG) has been fully considered in natural language generation (NLG) tasks. A KG can help models generate controllable text and achieve better performance. However, most existing related approaches still lack explainability and scalability in large‐scale knowledge reasoning. In this work, we propose a novel CogNLG framework for KG‐to‐text generation tasks. Our CogNLG is implemented based on the dual‐process theory in cognitive science. It consists of two systems: one system acts as the analytic system for knowledge extraction, and another is the perceptual system for text generation by using existing knowledge. During text generation, CogNLG provides a visible and explainable reasoning path. Our framework shows excellent performance on all datasets and achieves a BLEU score of 36.7, which increases by 6.7 compared to the best competitor.

show abstract

Section: Kg-to-textmentioning

confidence: 99%

“…ENT-DESC The ENT-DESC dataset (Cheng et al, 2020) is extracted from Wikipedia with more than 9.9 million pages. The dataset contains domains like humans, events, locations, etc.…”

Section: Datasetmentioning

confidence: 99%

Section: Datasetmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

CogNLG: Cognitive graph for KG‐to‐text generation

Lai,

Ye,

et al. 2023

Expert Systems

View full text Add to dashboard Cite

show abstract

“…Recent works for solving this task have two main categories. One category is using graph neural networks (Marcheggiani and Perez-Beltrachini, 2018;Ribeiro et al, 2020b;Cheng et al, 2020) et al, 2020a;Yang et al, 2020;Gardent et al, 2017;Hoyle et al, 2020) and then formulating a sequence-to-sequence generation task with lineared KG nodes as input to generate sentences. E.g., Distiawan et al (Distiawan et al, 2018) utilize a fixed tree traversal order to directly flatten the KG into a linearized representation.…”

Section: Kg-to-text Generationmentioning

confidence: 99%

Syntax Controlled Knowledge Graph-to-Text Generation with Order and Semantic Consistency

Liu¹,

Fan²,

Zhou³

et al. 2022

Findings of the Association for Computational Linguistics: NAACL 2022

View full text Add to dashboard Cite

The knowledge graph (KG) stores a large amount of structural knowledge, while it is not easy for direct human understanding. Knowledge graph-to-text (KG-to-text) generation aims to generate easy-to-understand sentences from the KG, and at the same time, maintains semantic consistency between generated sentences and the KG. Existing KG-to-text generation methods phrase this task as a sequence-tosequence generation task with linearized KG as input and consider the consistency issue of the generated texts and KG through a simple selection between decoded sentence word and KG node word at each time step. However, the linearized KG order is commonly obtained through a heuristic search without data-driven optimization. In this paper, we optimize the knowledge description order prediction under the order supervision extracted from the caption and further enhance the consistency of the generated sentences and KG through syntactic and semantic regularization. We incorporate the Part-of-Speech (POS) syntactic tags to constrain the positions to copy words from the KG and employ a semantic context scoring function to evaluate the semantic fitness for each word in its local context when decoding each word in the generated sentence. Extensive experiments are conducted on two datasets, WebNLG and DART, and achieve state-of-the-art performances. Our code is now public available 1 .

show abstract

Graphine: A Dataset for Graph-aware Terminology Definition Generation

Liu

Wang

et al. 2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Precisely defining the terminology is the first step in scientific communication. Developing neural text generation models for definition generation can circumvent the laborintensity 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 graphaware 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. 1

show abstract

ENT-DESC: Entity Description Generation by Exploring Knowledge Graph

Cited by 4 publications

References 18 publications

CogNLG: Cognitive graph for KG‐to‐text generation

CogNLG: Cognitive graph for KG‐to‐text generation

Syntax Controlled Knowledge Graph-to-Text Generation with Order and Semantic Consistency

Graphine: A Dataset for Graph-aware Terminology Definition Generation

Contact Info

Product

Resources

About