Ximing Li


pdf bib
A Contrastive Cross-Channel Data Augmentation Framework for Aspect-Based Sentiment Analysis
Bing Wang | Liang Ding | Qihuang Zhong | Ximing Li | Dacheng Tao
Proceedings of the 29th International Conference on Computational Linguistics

Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task, which focuses on detecting the sentiment polarity towards the aspect in a sentence. However, it is always sensitive to the multi-aspect challenge, where features of multiple aspects in a sentence will affect each other. To mitigate this issue, we design a novel training framework, called Contrastive Cross-Channel Data Augmentation (C3 DA), which leverages an in-domain generator to construct more multi-aspect samples and then boosts the robustness of ABSA models via contrastive learning on these generated data. In practice, given a generative pretrained language model and some limited ABSA labeled data, we first employ some parameter-efficient approaches to perform the in-domain fine-tuning. Then, the obtained in-domain generator is used to generate the synthetic sentences from two channels, i.e., Aspect Augmentation Channel and Polarity Augmentation Channel, which generate the sentence condition on a given aspect and polarity respectively. Specifically, our C3 DA performs the sentence generation in a cross-channel manner to obtain more sentences, and proposes an Entropy-Minimization Filter to filter low-quality generated samples. Extensive experiments show that our C3 DA can outperform those baselines without any augmentations by about 1% on accuracy and Macro- F1. Code and data are released in https://github.com/wangbing1416/C3DA.


pdf bib
Semi-Supervised Text Classification with Balanced Deep Representation Distributions
Changchun Li | Ximing Li | Jihong Ouyang
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Semi-Supervised Text Classification (SSTC) mainly works under the spirit of self-training. They initialize the deep classifier by training over labeled texts; and then alternatively predict unlabeled texts as their pseudo-labels and train the deep classifier over the mixture of labeled and pseudo-labeled texts. Naturally, their performance is largely affected by the accuracy of pseudo-labels for unlabeled texts. Unfortunately, they often suffer from low accuracy because of the margin bias problem caused by the large difference between representation distributions of labels in SSTC. To alleviate this problem, we apply the angular margin loss, and perform Gaussian linear transformation to achieve balanced label angle variances, i.e., the variance of label angles of texts within the same label. More accuracy of predicted pseudo-labels can be achieved by constraining all label angle variances balanced, where they are estimated over both labeled and pseudo-labeled texts during self-training loops. With this insight, we propose a novel SSTC method, namely Semi-Supervised Text Classification with Balanced Deep representation Distributions (S2TC-BDD). To evaluate S2TC-BDD, we compare it against the state-of-the-art SSTC methods. Empirical results demonstrate the effectiveness of S2TC-BDD, especially when the labeled texts are scarce.

pdf bib
Extracting Topics with Simultaneous Word Co-occurrence and Semantic Correlation Graphs: Neural Topic Modeling for Short Texts
Yiming Wang | Ximing Li | Xiaotang Zhou | Jihong Ouyang
Findings of the Association for Computational Linguistics: EMNLP 2021

Short text nowadays has become a more fashionable form of text data, e.g., Twitter posts, news titles, and product reviews. Extracting semantic topics from short texts plays a significant role in a wide spectrum of NLP applications, and neural topic modeling is now a major tool to achieve it. Motivated by learning more coherent and semantic topics, in this paper we develop a novel neural topic model named Dual Word Graph Topic Model (DWGTM), which extracts topics from simultaneous word co-occurrence and semantic correlation graphs. To be specific, we learn word features from the global word co-occurrence graph, so as to ingest rich word co-occurrence information; we then generate text features with word features, and feed them into an encoder network to get topic proportions per-text; finally, we reconstruct texts and word co-occurrence graph with topical distributions and word features, respectively. Besides, to capture semantics of words, we also apply word features to reconstruct a word semantic correlation graph computed by pre-trained word embeddings. Upon those ideas, we formulate DWGTM in an auto-encoding paradigm and efficiently train it with the spirit of neural variational inference. Empirical results validate that DWGTM can generate more semantically coherent topics than baseline topic models.


pdf bib
A Pseudo Label based Dataless Naive Bayes Algorithm for Text Classification with Seed Words
Ximing Li | Bo Yang
Proceedings of the 27th International Conference on Computational Linguistics

Traditional supervised text classifiers require a large number of manually labeled documents, which are often expensive to obtain. Recently, dataless text classification has attracted more attention, since it only requires very few seed words of categories that are much cheaper. In this paper, we develop a pseudo-label based dataless Naive Bayes (PL-DNB) classifier with seed words. We initialize pseudo-labels for each document using seed word occurrences, and employ the expectation maximization algorithm to train PL-DNB in a semi-supervised manner. The pseudo-labels are iteratively updated using a mixture of seed word occurrences and estimations of label posteriors. To avoid noisy pseudo-labels, we also consider the information of nearest neighboring documents in the pseudo-label update step, i.e., preserving local neighborhood structure of documents. We empirically show that PL-DNB outperforms traditional dataless text classification algorithms with seed words. Especially, PL-DNB performs well on the imbalanced dataset.


pdf bib
Integrating Topic Modeling with Word Embeddings by Mixtures of vMFs
Ximing Li | Jinjin Chi | Changchun Li | Jihong Ouyang | Bo Fu
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Gaussian LDA integrates topic modeling with word embeddings by replacing discrete topic distribution over word types with multivariate Gaussian distribution on the embedding space. This can take semantic information of words into account. However, the Euclidean similarity used in Gaussian topics is not an optimal semantic measure for word embeddings. Acknowledgedly, the cosine similarity better describes the semantic relatedness between word embeddings. To employ the cosine measure and capture complex topic structure, we use von Mises-Fisher (vMF) mixture models to represent topics, and then develop a novel mix-vMF topic model (MvTM). Using public pre-trained word embeddings, we evaluate MvTM on three real-world data sets. Experimental results show that our model can discover more coherent topics than the state-of-the-art baseline models, and achieve competitive classification performance.