Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer 2021
DOI: 10.18653/v1/2021.acl-long.354
|View full text |Cite
|
Sign up to set email alerts
|

One2Set: Generating Diverse Keyphrases as a Set

Abstract: Recently, the sequence-to-sequence models have made remarkable progress on the task of keyphrase generation (KG) by concatenating multiple keyphrases in a predefined order as a target sequence during training. However, the keyphrases are inherently an unordered set rather than an ordered sequence. Imposing a predefined order will introduce wrong bias during training, which can highly penalize shifts in the order between keyphrases. In this work, we propose a new training paradigm ONE2SET without predefining an… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
34
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
4
4
1

Relationship

1
8

Authors

Journals

citations
Cited by 45 publications
(34 citation statements)
references
References 19 publications
0
34
0
Order By: Relevance
“…We use four different models, three of which are acclaimed models in the Keyphrase Generation task, viz. catSeq (Yuan et al, 2020), One2Set (Ye et al, 2021), ExHiRD (Chen et al, 2020); and the fourth is based on one of the latest Transformer models, i.e., Longformer Encoder-Decoder (LED) , suitable for longer documents. The baseline in each model takes the title and abstract (T+A) as input and predicts a sequence of keyphrases.…”
Section: Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…We use four different models, three of which are acclaimed models in the Keyphrase Generation task, viz. catSeq (Yuan et al, 2020), One2Set (Ye et al, 2021), ExHiRD (Chen et al, 2020); and the fourth is based on one of the latest Transformer models, i.e., Longformer Encoder-Decoder (LED) , suitable for longer documents. The baseline in each model takes the title and abstract (T+A) as input and predicts a sequence of keyphrases.…”
Section: Methodsmentioning
confidence: 99%
“…This approach can not only predict the exact keyphrases that are present in the document (present keyphrases) but also the absent keyphrases. A lot of works (Yuan et al (2020); ; Meng et al (2017); Chan et al (2019); Chen et al (2020); Ye et al (2021)) adopt this approach but their focus is mainly on the architectural innovations to improve the generation of present and absent keyphrases. However, our focus is different from all the prior works in keyphrase generation.…”
Section: Introductionmentioning
confidence: 99%
“…KG, to generate absent words, is often modeled as neural encoder-decoder architecture (Sutskever et al, 2014), which generates the keyphrase sequence given the input document (Meng et al, 2017). KG approaches can be further categorized into two settings: one-to-one (O2O) and one-to-seq (O2S) (Yuan et al, 2020;Ye et al, 2021). In O2O, a model is trained to generate a single keyphrase for each document, and then, for evaluation, the model generates multiple keyphrases using beam search decoding with a large beam size (e.g., 200).…”
Section: Related Workmentioning
confidence: 99%
“…More recently, Chen et al (2018) leverages the coverage (Tu et al, 2016) mechanism to incorporate the correlation among keyphrases, enrich the generating stage by utilizing title information, and Chen et al (2020) proposed hierarchical decoding for better generating keyphrases. In addition, there are some works focus on keyphrase diversity (Ye et al, 2021), selections (Zhao et al, 2021), different module structure , or linguistic constraints (Zhao and Zhang, 2019).…”
Section: Keyphrase Generation Modelsmentioning
confidence: 99%