Structure-Augmented Keyphrase Generation

Kim, Ji-Hyuk; Jeong, Myeongho; Choi, Seungtaek; Hwang, Seung-won

doi:10.18653/v1/2021.emnlp-main.209

Cited by 8 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(Meng et al, 2017;Yuan et al, 2020;Kim et al, 2021). However, these datasets all belong to the scientific domain, and mainly differ by source of documents and annotation methods (Kim et al, 2021). Therefore, after confirming the effectiveness of our approach for low-resource keyphrase generation, we are interested in measuring its performance on generalizing across domains that are far from each other with no annotated keyphrase data from the target domain.…”

Section: Kp20kmentioning

confidence: 88%

See 1 more Smart Citation

Representation Learning for Resource-Constrained Keyphrase Generation

Wu¹,

Ahmad²,

Dev³

et al. 2022

Preprint

View full text Add to dashboard Cite

State-of-the-art keyphrase generation methods generally depend on large annotated datasets, limiting their performance in domains with constrained resources. To overcome this challenge, we investigate strategies to learn an intermediate representation suitable for the keyphrase generation task. We introduce salient span recovery and salient span prediction as guided denoising language modeling objectives that condense the domainspecific knowledge essential for keyphrase generation. Through experiments on multiple scientific keyphrase generation benchmarks, we show the effectiveness of the proposed approach for facilitating low-resource and zeroshot keyphrase generation. Furthermore, we observe that our method especially benefits the generation of absent keyphrases, approaching the performance of SOTA methods trained with large training sets.

show abstract

Section: Kp20kmentioning

confidence: 88%

“…Best result is boldfaced. (Meng et al, 2017;Yuan et al, 2020;Kim et al, 2021). However, these datasets all belong to the scientific domain, and mainly differ by source of documents and annotation methods (Kim et al, 2021).…”

Section: Kp20kmentioning

confidence: 99%

Representation Learning for Resource-Constrained Keyphrase Generation

Wu¹,

Ahmad²,

Dev³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Wang et al [19] proposed TAKG, the first keyword generating model for social media text, utilizing corpus level latent topic representation to enrich the contextual representation of input obtained using the encoder. After that, Kim et al [20] proposed a method for expanding missing related phrases from existing keywords to increase context, and Yang et al [21] solved the problem of dispersed social media text information through graph convolutional networks.…”

Section: Related Workmentioning

confidence: 99%

Hierarchical Keyword Generation Method for Low-Resource Social Media Text

Guan,

Long

2023

Information

View full text Add to dashboard Cite

The exponential growth of social media text information presents a challenging issue in terms of retrieving valuable information efficiently. Utilizing deep learning models, we can automatically generate keywords that express core content and topics of social media text, thereby facilitating the retrieval of critical information. However, the performance of deep learning models is limited by the labeled text data in the social media domain. To address this problem, this paper presents a hierarchical keyword generation method for low-resource social media text. Specifically, the text segment is introduced as a hierarchical unit of social media text to construct a hierarchical model structure and design a text segment recovery task for self-supervised training of the model, which not only improves the ability of the model to extract features from social media text, but also reduces the dependence of the keyword generation model on the labeled data in the social media domain. Experimental results from publicly available social media datasets demonstrate that the proposed method can effectively improve the keyword generation performance even given limited social media labeled data. Further discussions demonstrate that the self-supervised training stage based on the text segment recovery task indeed benefits the model in adapting to the social media text domain.

show abstract

“…Similar approaches have been investigated in neural machine translation (Gu et al, 2018;Cai et al, 2021), dialogue (Weston et al, 2018), and knowledge-base QA (Das et al, 2021). In keyphrase generation, Chen et al (2019a); Ye et al (2021a); Kim et al (2021) retrieve similar documents from training data to produce more accurate keyphrases. However, their retrieval module is a non-parametric model and cannot be generalized in the multilingual setting due to the large vocabulary gap between languages.…”

Section: Related Workmentioning

confidence: 99%

Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative Training

Gao¹,

Yin²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

Keyphrase generation is the task of automatically predicting keyphrases given a piece of long text. Despite its recent flourishing, keyphrase generation on non-English languages haven't been vastly investigated. In this paper, we call attention to a new setting named multilingual keyphrase generation and we contribute two new datasets, Ecom-merceMKP and AcademicMKP, covering six languages. Technically, we propose a retrievalaugmented method for multilingual keyphrase generation to mitigate the data shortage problem in non-English languages. The retrievalaugmented model leverages keyphrase annotations in English datasets to facilitate generating keyphrases in low-resource languages. Given a non-English passage, a cross-lingual dense passage retrieval module finds relevant English passages. Then the associated English keyphrases serve as external knowledge for keyphrase generation in the current language. Moreover, we develop a retrievergenerator iterative training algorithm to mine pseudo parallel passage pairs to strengthen the cross-lingual passage retriever. Comprehensive experiments and ablations show that the proposed approach outperforms all baselines. 1 * Qingyu Yin and Zheng Li are corresponding authors. This work was mainly done while Rui Meng was a Ph.D. student at University of Pittsburgh.1 The datasets are released at https://github. com/Yifan-Gao/multilingual_keyphrase_ generation.

show abstract

Structure-Augmented Keyphrase Generation

Cited by 8 publications

References 15 publications

Representation Learning for Resource-Constrained Keyphrase Generation

Representation Learning for Resource-Constrained Keyphrase Generation

Hierarchical Keyword Generation Method for Low-Resource Social Media Text

Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative Training

Contact Info

Product

Resources

About