Papers by Jihong Li
Extracting Topics with Simultaneous Word Co-occurrence and Semantic Correlation Graphs: Neural Topic Modeling for Short Texts (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Empirical results validate that DWGTM can generate more semantically coherent topics than baseline topic models. |
| Approach: | They develop a neural topic model which extracts topics from word co-occurrence graphs . Empirical results validate that DWGTM can generate more semantically coherent topics than baseline topic models. |
| Outcome: | Empirical results show that the proposed model can generate more coherent topics than baseline topic models. |
Semi-Supervised Text Classification with Balanced Deep Representation Distributions (2021.acl-long)
Copied to clipboard
| Challenge: | Semi-Supervised Text Classification (SSTC) is a type of self-training that uses labeled and unlabeled data to perform certain applications. |
| Approach: | They propose a method to initialize a deep classifier by training over labeled texts . they then alternatively predict unlabeled texts as their pseudo-labels and train them over the mixture . |
| Outcome: | Empirical results show that the proposed method is more accurate when labeled texts are scarce. |
We Need to Talk About Reproducibility in NLP Model Comparison (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies show that standard splits produce low reproducible and unreliable conclusions . reproducibility of empirical experimental conclusions is a problem in NLP domain . |
| Approach: | They propose to transform the reproducibility of a model comparison into a probabilistic function . they propose to use a regularized corpus splitting strategy to estimate the model's performance . |
| Outcome: | The proposed estimator achieves a high SNR and significantly increases reproducibility. |
Bayes Test of Precision, Recall, and F1 Measure for Comparison of Two Natural Language Processing Models (P19-1)
Copied to clipboard
| Challenge: | Existing t-tests for cross-validation (CV) are inappropriate for model comparison . existing t tests for cross validation (CV), such as 52 CV t test and F ttest, are inadequate . |
| Approach: | They propose to use a block-regularized 32 CV to compare two NLP models . they calibrate the posterior distributions of P, R, and F1 and derive an accurate interval estimation of P and R . |
| Outcome: | The proposed model could regularize the difference in certain frequency distributions over linguistic units and yield stable estimators of P, R, and F1. |