Text Simplification Using Neural Machine Translation
Authors: Tong Wang, Ping Chen, John Rochford, Jipeng Qiang
AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | This work is at an early stage. Due to the lack of available aligned sentence pairs, the first step is to collect training data. We plan to do so in two ways: crowdsourcing, or automatic discovery of aligned sentences from Simple English Wikipedia and English Wikipedia. We will then train the RNN encoder-decoder to score candidate words on a lexical simplification system. Our final goal is to build the RNN encoder-decoder model to simplify any English sentence. |
| Researcher Affiliation | Academia | Tong Wang and Ping Chen and John Rochford and Jipeng Qiang Department of Computer Science, University of Massachusetts Boston, tongwang0001@gmail.com Department of Computer Engineering, University of Massachusetts Boston Eunice Kennedy Shriver Center, University of Massachusetts Medical School Department of Computer Science, Hefei University of Technology |
| Pseudocode | No | The paper does not contain any pseudocode or clearly labeled algorithm blocks. |
| Open Source Code | No | The paper does not provide any explicit statements or links about open-source code for the described methodology. |
| Open Datasets | No | Due to the lack of available aligned sentence pairs, the first step is to collect training data. We plan to do so in two ways: crowdsourcing, or automatic discovery of aligned sentences from Simple English Wikipedia and English Wikipedia. The paper states that training data needs to be collected but does not provide access information for a public dataset used in this paper. |
| Dataset Splits | No | The paper does not present any experimental results or dataset splits (train/validation/test). |
| Hardware Specification | No | The paper proposes a model and discusses challenges and strategies, but does not report on any implemented experiments, therefore no hardware specifications are mentioned. |
| Software Dependencies | No | The paper discusses a neural network model but does not mention specific software dependencies with version numbers for implementation. |
| Experiment Setup | No | The paper proposes an approach and discusses conceptual challenges, but does not describe any specific experimental setup details such as hyperparameters or training configurations. |