AGRA: An Analysis-Generation-Ranking Framework for Automatic Abbreviation from Paper Titles
Authors: Jianbing Zhang, Yixin Sun, Shujian Huang, Cam-Tu Nguyen, Xiaoliang Wang, Xinyu Dai, Jiajun Chen, Yang Yu
IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conduct experiments to compare different settings of our framework with several analysis approaches from different perspectives. Compared to online or baseline systems, our framework could achieve the best results. |
| Researcher Affiliation | Academia | Jianbing Zhang, Yixin Sun, Shujian Huang , Cam-Tu Nguyen, Xiaoliang Wang, Xinyu Dai, Jiajun Chen, Yang Yu National Key Laboratory for Novel Software Technology, Nanjing University, China |
| Pseudocode | No | The paper describes various processes and steps with equations but does not contain a structured pseudocode or algorithm block. |
| Open Source Code | No | The paper states: "The demonstration system is available at http://nlp.nju.edu.cn/demo/abbreviation.html". This refers to a demonstration system, not the source code for the methodology itself. |
| Open Datasets | Yes | We collect 1000 paper titles with abbreviations from Citer Seer X1. Most of these papers are about computer and information science. These titles are split into two parts: the abbreviation part and the title word part (Table 2). 1http://citeseerx.ist.psu.edu. We use the skip-gram model of the word2vec tool [Mikolov et al., 2013] to train our word embedding on a large paper title data set we collect from arxiv.org, containing about 60,000 paper titles. |
| Dataset Splits | No | The paper states: "Among these items, we randomly select 140 of them for test and use the rest of them as the training set for optimizing the parameters." While train and test splits are provided, an explicit validation split is not mentioned. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments. |
| Software Dependencies | No | The paper mentions tools like "Stanford Parser [Chen and Manning, 2014]", "word2vec tool [Mikolov et al., 2013]", and "SRILM toolkit [Stolcke, 2004]", citing the papers. However, it does not provide explicit version numbers for these software components in the text. |
| Experiment Setup | No | The paper mentions optimizing parameters using "Bayes Opt [Martinez-Cantin, 2014] and RACOS [Yu et al., 2016; Hu et al., 2017]" and running optimization algorithms for "1000 iterations", but it does not provide specific hyperparameters (e.g., learning rate, batch size) or other detailed training configurations. |