Weakly-Supervised Scientific Document Classification via Retrieval-Augmented Multi-Stage Training
Weakly-Supervised Scientific Document Classification via Retrieval-Augmented Multi-Stage Training
复制标题
DOI：
10.1145/3539618.3592085
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Ran Xu;Yue Yu;Joyce Ho;Carl Yang
中科院分区：
文献类型：
--
作者：
Ran Xu;Yue Yu;Joyce Ho;Carl Yang
科学文档分类对于广泛的应用来说是一项关键任务，但收集人工标记数据的成本可能过高。我们只使用标签名称来研究科学文档分类。在科学领域中，标签名称通常包含可能不会出现在文档语料库中的特定领域概念，因此难以精确匹配标签和文档。为了解决这个问题，我们提出了WanDeR，它利用密集检索在嵌入空间中执行匹配，以捕获标签名称的语义。我们进一步设计了标签名扩展模块，以丰富其表示。最后，使用自训练步骤来改进预测。在三个数据集上的实验表明，WanDeR比最佳基线高出11.9%。我们的代码将在https://github.com/ritaranx/wander上发布。
Scientific document classification is a critical task for a wide range of applications, but the cost of collecting human-labeled data can be prohibitive. We study scientific document classification using label names only. In scientific domains, label names often include domain-specific concepts that may not appear in the document corpus, making it difficult to match labels and documents precisely. To tackle this issue, we propose WanDeR, which leverages dense retrieval to perform matching in the embedding space to capture the semantics of label names. We further design the label name expansion module to enrich its representations. Lastly, a self-training step is used to refine the predictions. The experiments on three datasets show that WanDeR outperforms the best baseline by 11.9%. Our code will be published at https://github.com/ritaranx/wander.