Domain-Adaptive Text Classification with Structured Knowledge from Unlabeled Data
Authors: Tian Li, Xiang Chen, Zhen Dong, Kurt Keutzer, Shanghang Zhang
IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We validate DASK on a wide range of cross-domain sentiment classification tasks and observe up to 2.9% absolute performance improvement over baselines for 20 different domain pairs. To evaluate the efficacy of our proposed method, we extensively experiment on two cross-domain sentiment classification datasets. |
| Researcher Affiliation | Academia | 1Peking University, 2University of California, Berkeley, {davidli, caspar}@pku.edu.cn, {zhendong, keutzer}@berkeley.edu, shanghang@pku.edu.cn |
| Pseudocode | No | The paper describes its method in detail with narrative text and figures (e.g., Figure 3 illustrating DASK steps), but it does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Code is available at https://github.com/hikaru-nara/DASK. |
| Open Datasets | Yes | We use the standard Amazon-product-review2 dataset [Blitzer et al., 2007]. It contains four types of product reviews: books(B), dvd(D), electronics(E), kitchen(K), which form the four domains in the dataset. Besides, following PBLM [Ziser and Reichart, 2018], we also introduce the Airlines dataset3. ... 2Dataset can be found at http://www.cs.jhu.edu/ mdredze/ datasets/sentiment/index2.html 3Dataset and process procedures can be found at https://github. com/quankiquanki/skytrax-reviews-dataset |
| Dataset Splits | Yes | Each time before training, we randomly sample 400 labeled source domain data for dev set, and the rest 1600 along with all unlabeled data from source and target domain are used for training. |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments. It only mentions using BERT as the feature extractor. |
| Software Dependencies | No | The paper mentions software like BERT, K-BERT, and NLTK library, but it does not provide specific version numbers for these or any other software dependencies needed to replicate the experiment. |
| Experiment Setup | Yes | For all the methods in our experiments, we set the learning rate to 2e-5, warmup 0.1, batch size 32, and select weight decay in {1e-4, 2e-4, 3e-4}. For adversarial training, we select γ in the gradient reversal layer from {0.15, 0.25, 0.5, 0.75, 1.0}. For KG fact filtering, we set the confidence threshold in the interval [0.1, 0.45]... For SCL, we apply a balance factor λ to the pivot-prediction loss, and choose its value from [0.1, 0.5]... we update the sentiment classifier once in 5-11 training steps. For the dynamic memory bank, we update the pivots every 10 training steps, and the top 500 words are selected as pivots.The learning rate of word sentiment score is set to 1e-4 or 2e-4, and the pseudo-labeling confidence threshold to 0.9. |