Transition-based Adversarial Network for Cross-lingual Aspect Extraction
Authors: Wenya Wang, Sinno Jialin Pan
IJCAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The proposed method is end-to-end and achieves state-of-the-art performance on English, French and Spanish restaurant review datasets. 5 Experiments For experiments, we use the restaurant reviews from English, French and Spanish taken from Sem Eval Challenge 2016 task 5. The statistics of the datasets are listed in Table 1. We use labeled training data from the source language and unlabled training data from the target language to train the model. For testing, we conduct both transductive and inductive experiments to test our model on the unlabeled training data and the test data of the target language. The results are shown in F1 scores. |
| Researcher Affiliation | Collaboration | Wenya Wang and Sinno Jialin Pan Nanyang Technological University, Singapore SAP Innovation Center, Singapore {wa0001ya, sinnopan}@ntu.edu.sg |
| Pseudocode | No | The paper describes the transition actions in text and provides an example trace (Figure 2), but no formal pseudocode or algorithm blocks are present. |
| Open Source Code | No | The paper does not provide concrete access to its source code, nor does it explicitly state that the code will be released. |
| Open Datasets | Yes | For experiments, we use the restaurant reviews from English, French and Spanish taken from Sem Eval Challenge 2016 task 5. ... The parallel corpus are from Europarl3 that contains 2M sentences for each language. 3http://www.statmt.org/europarl/ |
| Dataset Splits | No | The paper provides dataset statistics with 'Training' and 'Test' splits in Table 1 but does not explicitly mention a separate validation split or how it was used for model tuning. |
| Hardware Specification | Yes | For the overall complexity, our model takes 10mins for training 1 epoch with 4000 sentences using Intel(R) Xeon(R) CPU E5-1650 v2 @ 3.50GHz. |
| Software Dependencies | No | The paper mentions using 'multivec' for word embeddings and 'Stanford universal dependencies' for dependency trees, but it does not provide specific version numbers for these software components. |
| Experiment Setup | Yes | The whole network is trained with SGD using learning rate 0.02. The trade-off parameters are α = 0.1 and β = 1. The size of word embeddings is 100 and the hidden layer size is 50. Each experiment is trained for 20 epochs and the best performance is reported. |