Write-righter: An Academic Writing Assistant System
Authors: Yuanchao Liu, Xin Wang, Ming Liu, Xiaolong Wang
AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | This paper presents an academic writing assistant system called Write-righter, which can provide real-time hint and recommendation by analyzing the input context. Currently, 5.4GB index generated from 40, 243 scientific papers, which is mainly crawled from Sciencedirect2, is used in the system. There are 34, 040 phrases in the library and we set N=20 in this paper. |
| Researcher Affiliation | Academia | Yuanchao Liu, Xin Wang, Ming Liu, Xiaolong Wang School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China ycliu@hit.edu.cn, xwang@insun.hit.edu.cn, mliu@insun.hit.edu.cn, wangxl@insun.hit.edu.cn |
| Pseudocode | No | The paper describes procedural steps for calculations but does not present a formal pseudocode block or algorithm. |
| Open Source Code | No | The paper provides a link to a demo video but does not include an explicit statement or link to the open-source code for the described system. |
| Open Datasets | No | The paper states that '5.4GB index generated from 40, 243 scientific papers, which is mainly crawled from Sciencedirect2, is used in the system,' but it does not provide concrete access (link, DOI, or specific citation for the dataset itself) to this specific index or the curated collection of papers. |
| Dataset Splits | No | The paper does not provide any information about training, validation, or test dataset splits. |
| Hardware Specification | No | The paper describes the system's client-server architecture but does not specify any hardware details used for its implementation or experiments. |
| Software Dependencies | No | The paper mentions 'mallet LDA (Mc Callum, et al, 2002)' and 'Wordnet3' but does not specify version numbers for these or any other software dependencies. |
| Experiment Setup | Yes | If ) ( ) ( w P w P S S W ! , then w is more likely to be the structure word. Here ) (w PS W to 0.65 and use 10 topics by experience. There are 34, 040 phrases in the library and we set N=20 in this paper. We set 4.0 ,6.0 E D in this paper. if the number of words in input area is bigger than threshold (e.g., 30 words). |