Controllable Abstractive Sentence Summarization with Guiding Entities

Zheng, Changmeng; Cai, Yi; Zhang, Guanjie; Li, Qing

doi:10.18653/v1/2020.coling-main.497

Cited by 11 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, the standard system used in the field of oil and gas exploration and development in China includes platforms such as the dynamic management system of standards, the system for standard formulation and revision, the oil field standard query system, and the technical supervision management platform [2]. The historical standard data of each platform is stored independently, and the standard specifications and formats are not unified, which brings inconvenience to the uniform use and centralized management of standards.…”

Section: The Current Number Of Existing Standards and Regulations In ...mentioning

confidence: 99%

Design and Implementation of Digital Platform Based on Standard Knowledge Map in Oil and Gas Exploration and Development Field

Huang,

Su,

Yue

et al. 2024

HSET

View full text Add to dashboard Cite

This paper introduces the current situation and problems of standardization development in the field of oil and gas exploration and development in China. To solve the problems of large amount of standard knowledge, large professional span and complex level, the concept connotation of ontology and knowledge graph is clarified. A triplet core data model of “standardized object (product) -style (paragraph structure) -index (attribute)” is proposed for oil and gas exploration and development. Based on this, the construction idea, main function, and future direction of digital platform of standard knowledge map in oil and gas exploration and development are studied.

show abstract

Section: The Current Number Of Existing Standards and Regulations In ...mentioning

confidence: 99%

Design and Implementation of Digital Platform Based on Standard Knowledge Map in Oil and Gas Exploration and Development Field

Huang,

Su,

Yue

et al. 2024

HSET

View full text Add to dashboard Cite

show abstract

“…E Rec measures the percentage of entities in a generated summary that are present in both its reference summary and its source article. Entities can be used as a proxy to measure the information relevance of a summary (Zheng et al, 2020). As shown in Fig.…”

Section: Datasets and Evaluation Setupmentioning

confidence: 99%

Lexical Repetitions Lead to Rote Learning: Unveiling the Impact of Lexical Overlap in Train and Test Reference Summaries

Choubey,

Fabbri,

Xiong

et al. 2023

Findings of the Association for Computational Linguistics: EMNLP 2023

View full text Add to dashboard Cite

Ideal summarization models should generalize to novel summary-worthy content without remembering reference training summaries by rote. However, a single average performance score on the entire test set is inadequate in determining such model competencies. We propose a fine-grained evaluation protocol by partitioning a test set based on the lexical similarity of reference test summaries with training summaries. We observe up to a 5x (1.2x) difference in ROUGE-2 (entity recall) scores between the subsets with the lowest and highest similarity. Next, we show that such training repetitions also make a model vulnerable to rote learning, reproducing data artifacts such as factual errors, especially when reference test summaries are lexically close to training summaries. Consequently, we propose to limit lexical repetitions in training summaries during both supervised fine-tuning and likelihood calibration stages to improve the performance on novel test cases while retaining average performance. Our automatic and human evaluations on novel test subsets and recent news articles show that limiting lexical repetitions in training summaries can prevent rote learning and improve generalization.

show abstract

“…Fan et al (2018) has leveraged PLMs with special tokens prepended to the input, to control the length, entities, and style of the generated summary. Zheng et al (2020) and He et al (2020) further extended prompts, keywords and entities as guiding markers. Chan et al (2021) proposed the constrained markov decision process (CMDP) based method to control attributes of summarization.…”

Section: Controllable Text Summarizationmentioning

confidence: 99%

Readability Controllable Biomedical Document Summarization

Luo¹,

Ananiadou²

2022

Preprint

View full text Add to dashboard Cite

Different from general documents, it is recognised that the ease with which people can understand a biomedical text is eminently varied, owing to the highly technical nature of biomedical documents and the variance of readers' domain knowledge. However, existing biomedical document summarization systems have paid little attention to readability control, leaving users with summaries that are incompatible with their levels of expertise. In recognition of this urgent demand, we introduce a new task of readability controllable summarization for biomedical documents, which aims to recognise users' readability demands and generate summaries that better suit their needs: technical summaries for experts and plain language summaries (PLS) for laymen. To establish this task, we construct a corpus consisting of biomedical papers with technical summaries and PLSs written by the authors, and benchmark multiple advanced controllable abstractive and extractive summarization models based on pre-trained language models (PLMs) with prevalent controlling and generation techniques. Moreover, we propose a novel masked language model (MLM) based metric and its variant to effectively evaluate the readability discrepancy between lay and technical summaries. Experimental results from automated and human evaluations show that though current control techniques allow for a certain degree of readability adjustment during generation, the performance of existing controllable summarization methods is far from desirable in this task.

show abstract

Controllable Abstractive Sentence Summarization with Guiding Entities

Cited by 11 publications

References 22 publications

Design and Implementation of Digital Platform Based on Standard Knowledge Map in Oil and Gas Exploration and Development Field

Design and Implementation of Digital Platform Based on Standard Knowledge Map in Oil and Gas Exploration and Development Field

Lexical Repetitions Lead to Rote Learning: Unveiling the Impact of Lexical Overlap in Train and Test Reference Summaries

Readability Controllable Biomedical Document Summarization

Contact Info

Product

Resources

About