Attentive Stacked Denoising Autoencoder With Bi-LSTM for Personalized Context-Aware Citation Recommendation

Dai, Tao; Zhu, Li; Wang, Yaxiong; Carley, Kathleen M.

doi:10.1109/taslp.2019.2949925

Cited by 40 publications

(27 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We evaluate our model on two datasets: RefSeer (Huang et al, 2015) and ACL-ARC (Bird et al, 2008), both of which were used in work on local CR (Ebesu and Fang, 2017;Dai et al, 2019). Dataset statistics are given in Table 1.…”

Section: Discussionmentioning

confidence: 99%

“…Dataset statistics are given in Table 1. RefSeer dataset splits are subsets of those used in (Ebesu and Fang, 2017), while ACL-ARC splits are ours, as we were unable to obtain the version used in (Dai et al, 2019). Details on hyperparameters, prefiltering, and training are given in the appendix.…”

Section: Discussionmentioning

confidence: 99%

“…The model of Ebesu and Fang (2017) encodes citation context and decodes it into the title of cited article, using also the information about the authors of citing and cited articles. Dai et al (2019) use stacked denoising autoencoders for representing cited articles and bidirectional LSTMs for citation context's embedding. Our approach extends on these models by enhancing the representation of citation context with global information.…”

Section: Related Workmentioning

confidence: 99%

“…Intuitively, in the former case, the model should put more weight on the bibliographic score, while in the latter case a higher weight on semantic score would be expected. Dai et al (2019), we use bidirectional long short-term memory (Bi-LSTM) cells (Hochreiter and Schmidhuber, 1997) to represent citation context, but also to represent both cited article and global information from the citing article. Text fed to the module is segmented and tokenized using spaCy.…”

Section: Modelmentioning

confidence: 99%

“…Approaches to CR come in two types: global (Bethard and Jurafsky, 2010;Ren et al, 2014;Guo et al, 2017;Bhagavatula et al, 2018) and local (He et al, 2010;Huang et al, 2012;Ebesu and Fang, 2017;Dai et al, 2019). Global CR models typically take the article's abstract or the entire text as input (the citing article) and output a list of relevant articles (the candidates for cited articles).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Improved Local Citation Recommendation Based on Context Enhanced with Global Information

Medić¹,

Šnajder²

2020

Proceedings of the First Workshop on Scholarly Document Processing

View full text Add to dashboard Cite

Local citation recommendation aims at finding articles relevant for given citation context. While most previous approaches represent context using solely text surrounding the citation, we propose enhancing context representation with global information. Specifically, we include citing article's title and abstract into context representation. We evaluate our model on datasets with different citation context sizes and demonstrate improvements with globallyenhanced context representations when citation contexts are smaller.1 Most work on local CR uses contexts from published articles with citations masked out. While this is a somewhat artificial setup as those articles are biased toward existing citations, local CR can nonetheless be used in this setup to recommend additional citations.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Improved Local Citation Recommendation Based on Context Enhanced with Global Information

Medić¹,

Šnajder²

2020

Proceedings of the First Workshop on Scholarly Document Processing

View full text Add to dashboard Cite

show abstract

Local Citation Recommendation with Hierarchical-Attention Text Encoder and SciBERT-Based Reranking

Gao

Hahnloser

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The goal of local citation recommendation is to recommend a missing reference from the local citation context and optionally also from the global context. To balance the tradeoff between speed and accuracy of citation recommendation in the context of a large-scale paper database, a viable approach is to first prefetch a limited number of relevant documents using efficient ranking methods and then to perform a fine-grained reranking using more sophisticated models. In that vein, BM25 has been found to be a tough-to-beat approach to prefetching, which is why recent work has focused mainly on the reranking step. Even so, we explore prefetching with nearest neighbor search among text embeddings constructed by a hierarchical attention network. When coupled with a SciBERT reranker fine-tuned on local citation recommendation tasks, our hierarchical Attention encoder (HAtten) achieves high prefetch recall for a given number of candidates to be reranked. Consequently, our reranker requires fewer prefetch candidates to rerank, yet still achieves state-of-the-art performance on various local citation recommendation datasets such as FullTextPeerRead, RefSeer, and arXiv.

show abstract

Citation Recommendation Based on Knowledge Graph and Multi-task Learning

Wan

Yuan

Wang

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Attentive Stacked Denoising Autoencoder With Bi-LSTM for Personalized Context-Aware Citation Recommendation

Cited by 40 publications

References 39 publications

Improved Local Citation Recommendation Based on Context Enhanced with Global Information

Improved Local Citation Recommendation Based on Context Enhanced with Global Information

Local Citation Recommendation with Hierarchical-Attention Text Encoder and SciBERT-Based Reranking

Citation Recommendation Based on Knowledge Graph and Multi-task Learning

Contact Info

Product

Resources

About