A Context-Aware Citation Recommendation Model with BERT and Graph Convolutional Networks

Jeong, Chanwoo; Jang, Sion; Shin, Hyuna; Park, Eunjeong; Choi, Sungchul

doi:10.48550/arxiv.1903.06464

Cited by 14 publications

(16 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yang et al [34] used the LSTM model to develop a contextaware citation recommendation system. Recently, Jeong et al [17] developed a contextaware neural citation recommendation model. While there are a lot of new methods coming in the domain of citation recommendation systems, the problem of identifying and recommending baselines of a paper has been untouched.…”

Section: Related Workmentioning

confidence: 99%

Why Did You Not Compare With That? Identifying Papers for Use as Baselines

Bedi¹,

Pandey²,

Bhatia³

et al. 2022

Preprint

View full text Add to dashboard Cite

We propose the task of automatically identifying papers used as baselines in a scientific article. We frame the problem as a binary classification task where all the references in a paper are to be classified as either baselines or nonbaselines. This is a challenging problem due to the numerous ways in which a baseline reference can appear in a paper. We develop a dataset of 2, 075 papers from ACL anthology corpus with all their references manually annotated as one of the two classes. We develop a multi-module attention-based neural classifier for the baseline classification task that outperforms four state-of-the-art citation role classification methods when applied to the baseline classification task. We also present an analysis of the errors made by the proposed classifier, eliciting the challenges that make baseline identification a challenging problem.

show abstract

Section: Related Workmentioning

confidence: 99%

Why Did You Not Compare With That? Identifying Papers for Use as Baselines

Bedi¹,

Pandey²,

Bhatia³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Combinations of BERT and GCN: Recent works have used concatenation of BERT and GCN representations of texts or entities to improve performance of tasks like commonsense knowledge-base completion (Malaviya et al, 2019), text classification Lu et al, 2020), multi-hop reasoning , citation recommendation (Jeong et al, 2019), medication recommendation (Shang et al, 2019), relation extraction (Zhao et al, 2019). Graph-BERT (Zhang et al, 2020) solely depends on attention layers of BERT without using any message aggregation techniques.…”

Section: Related Workmentioning

confidence: 99%

Constructing Flow Graphs from Procedural Cybersecurity Texts

Pal¹,

Kashihara²,

Banerjee³

et al. 2021

Preprint

View full text Add to dashboard Cite

Following procedural texts written in natural languages is challenging. We must read the whole text to identify the relevant information or identify the instruction-flow to complete a task, which is prone to failures. If such texts are structured, we can readily visualize instruction-flows, reason or infer a particular step, or even build automated systems to help novice agents achieve a goal. However, this structure recovery task is a challenge because of such texts' diverse nature. This paper proposes to identify relevant information from such texts and generate information flows between sentences. We built a large annotated procedural text dataset (CTFW) in the cybersecurity domain (3154 documents). This dataset contains valuable instructions regarding software vulnerability analysis experiences. We performed extensive experiments on CTFW with our LM-GNN model variants in multiple settings. To show the generalizability of both this task and our method, we also experimented with procedural texts from two other domains (Maintenance Manual and Cooking), which are substantially different from cybersecurity. Our experiments show that Graph Convolution Network with BERT sentence embeddings outperforms BERT in all three domains.

show abstract

“…5) SciBERT-ARGA-based models: adopt an approach inspired by Jeong et al [38], and place a higher weight on the paper's abstracts. The abstracts are embedded using SciBERT, as before, while the nodes of the citation or co-authorship networks are embedded using the adversarially regularised graph autoencoder (ARGA) framework proposed by Pan et al [39].…”

Section: Recommendation Techniquesmentioning

confidence: 99%

GraphConfRec: A Graph Neural Network-Based Conference Recommender System

Iana

Paulheim

2021

2021 ACM/IEEE Joint Conference on Digital Libraries (JCDL)

View full text Add to dashboard Cite

In today's academic publishing model, especially in Computer Science, conferences commonly constitute the main platforms for releasing the latest peer-reviewed advancements in their respective fields. However, choosing a suitable academic venue for publishing one's research can represent a challenging task considering the plethora of available conferences, particularly for those at the start of their academic careers, or for those seeking to publish outside of their usual domain. In this paper, we propose GraphConfRec, a conference recommender system which combines SciGraph and graph neural networks, to infer suggestions based not only on title and abstract, but also on coauthorship and citation relationships. GraphConfRec achieves a recall@10 of up to 0.580 and a MAP of up to 0.336 with a graph attention network-based recommendation model. A user study with 25 subjects supports the positive results.

show abstract

A Context-Aware Citation Recommendation Model with BERT and Graph Convolutional Networks

Cited by 14 publications

References 9 publications

Why Did You Not Compare With That? Identifying Papers for Use as Baselines

Why Did You Not Compare With That? Identifying Papers for Use as Baselines

Constructing Flow Graphs from Procedural Cybersecurity Texts

GraphConfRec: A Graph Neural Network-Based Conference Recommender System

Contact Info

Product

Resources

About