Attention-Based Personalized Encoder-Decoder Model for Local Citation Recommendation

Abstract

With a tremendous growth in the number of scientific papers, researchers have to spend too much time and struggle to find the appropriate papers they are looking for. Local citation recommendation that provides a list of references based on a text segment could alleviate the problem. Most existing local citation recommendation approaches concentrate on how to narrow the semantic difference between the scientific papers’ and citation context’s text content, completely neglecting other information. Inspired by the successful use of the encoder-decoder framework in machine translation, we develop an attention-based encoder-decoder (AED) model for local citation recommendation. The proposed AED model integrates venue information and author information in attention mechanism and learns relations between variable-length texts of the two text objects, i.e., citation contexts and scientific papers. Specifically, we first construct an encoder to represent a citation context as a vector in a low-dimensional space; after that, we construct an attention mechanism integrating venue information and author information and use RNN to construct a decoder, then we map the decoder’s output into a softmax layer, and score the scientific papers. Finally, we select papers which have high scores and generate a recommended reference paper list. We conduct experiments on the DBLP and ACL Anthology Network (AAN) datasets, and the results illustrate that the performance of the proposed approach is better than the other three state-of-the-art approaches.

A Bibliometric Analysis of Mesenchymal Stem Cell-Derived Exosomes in Acute Lung Injury/Acute Respiratory Distress Syndrome from 2013 to 2022

“… 24 , 25 As an indicator to evaluate the innovation degree of a publication in a certain field, local citation score (LCS) can also represents its Nc value. 26 The LCS is the number of times a collected article has been cited by other literature in the collected literature. H-index plays an increasingly important role in evaluating the academic achievements of a scientific researcher in recent years.…”

Author-Profile-Based Journal Recommendation for a Candidate Article: Using Hybrid Semantic Similarity and Trend Analysis

“…Finally; by looking at the references/citations, the similarity relations between the references of the articles and candidate journals could be calculated [17], [18]. Thus, the references similarity can be used as an another feature to calculate distance between documents [19], [20] like context similarity.…”

A New Citation Recommendation Strategy Based on Term Functions in Related Studies Section

“…Journal of Data and Information Science recommendation (LCR) (Tang, Wan, & Zhang, 2014;Yang et al, 2019) and global citation recommendation (GCR) (Tang, Wan, & Zhang, 2014;Ayala-Gomez et al, 2018).…”

“…A New Citation Recommendation Strategy Based on Term Functions in Related Studies Section http://www.jdis.org https://www.degruyter.com/view/j/jdis retrieval and recommendation, our term function weighting-based strategies recommend a more accurate and structured literature list, demonstrating that term function is an effective feature in citation recommendation, especially when recommending papers for structured literature review. Compared with deep learningbased-recommendation approaches (Zhang et al, 2019), our strategy can generate intuitive explanations of the results for users or system designers, improving system transparency and persuasiveness, trustworthiness, and effectiveness. For example, users can quickly figure out both the content and term function relevance of a recommended item.…”