Enhancing Scientific Papers Summarization with Citation Graph
Authors: Chenxin An, Ming Zhong, Yiran Chen, Danqing Wang, Xipeng Qiu, Xuanjing Huang12498-12506
AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments show that our model can achieve competitive performance when compared with the pretrained models even with a simple architecture. The results also indicates the citation graph is crucial to better understand the content of papers and generate high-quality summaries. |
| Researcher Affiliation | Academia | Chenxin An, Ming Zhong, Yiran Chen, Danqing Wang, Xipeng Qiu*, Xuanjing Huang Shanghai Key Laboratory of Intelligent Information Processing, Fudan University School of Computer Science, Fudan University {cxan20, mzhong18, yrchen19, dqwang18, xpqiu, xjhuang}@fudan.edu.cn |
| Pseudocode | Yes | Algorithm 1 Citation Graph Construction |
| Open Source Code | No | No explicit statement or link providing concrete access to the source code for the methodology described in this paper was found. |
| Open Datasets | Yes | we construct a large-scale summarization dataset, Semantic Scholar Network (SSN), consists of 141k research papers extracted from Semantic Scholar Open Research Corpus (S2ORC) (Lo et al. 2020). |
| Dataset Splits | Yes | for SNN (transductive) we randomly choose 6,250/6250 papers from the whole dataset as test/validation sets and the remaining 128,299 papers are classified as training set which is the most commonly way to split the dataset. The training/validation/test graphs in inductive setting contain 128,400/6,123/6,276 nodes and 603,737/17,221/14,515 edges. In both inductive and transducitve setting, the summary of papers in the test set and validation set are kept invisible during the training phase. |
| Hardware Specification | No | No specific hardware details (e.g., GPU/CPU models, processor types, memory amounts, or detailed computer specifications) used for running experiments were mentioned in the paper. |
| Software Dependencies | No | The paper mentions 'spaCy (Honnibal and Johnson 2015)' and 'Deep Graph Library (Wang et al. 2019)' but does not provide specific version numbers for these or any other software dependencies. |
| Experiment Setup | Yes | We use mini-batches of size 16 and we limit the input document length to 500 tokens. The input citation graph includes the source paper and its K-hop neighbors (K = 1, 2), and we initialize the node representation with body text of source papers and the abstract of neighbors. We constrain the maximum number of papers in an input graph to 64. We implement graph attention network with Deep Graph Library (Wang et al. 2019) and the number of attention heads is set to 4. We use Adagrad optimizer with learning rate 0.15 and an initial accumulator value of 0.1. We set the beam size b to 5 and ls to 75 in the ROUGE credit, and the ROUGE (Lin 2004) score used is the value of ROUGE-1 F1. We do not train the model with coverage loss in the first epoch to help the model converge faster, and we train our model for 10 epochs and do validation every 2000 steps. |