Unified Semantic Typing with Meaningful Label Inference
Unified Semantic Typing with Meaningful Label Inference
复制标题
DOI：
10.48550/arxiv.2205.01826
复制
发表时间：
2022-05
期刊：
影响因子：
--
通讯作者：
James Y. Huang;Bangzheng Li;Jiashu Xu;Muhao Chen
中科院分区：
文献类型：
--
作者：
James Y. Huang;Bangzheng Li;Jiashu Xu;Muhao Chen
语义分类的目的是将文本上下文中感兴趣的标记或跨度分类为语义类别，例如关系，实体类型和事件类型。语义类别的推断标签有意义地解释了机器如何理解文本的组成部分。在本文中，我们提出了UniST，一个统一的框架，捕捉标签语义的语义类型，将输入和标签投射到一个联合语义嵌入空间。为了将不同的词汇和关系语义分类任务制定为一个统一的任务，我们将任务描述与输入联合编码，使UniST能够适应不同的任务，而无需引入特定于任务的模型组件。UniST优化了边际排名损失，使得输入和标签的语义相关性从它们的嵌入相似性中反映出来。我们的实验表明，UniST在三个语义分类任务：实体分类，关系分类和事件分类方面取得了很好的性能。同时，UniST有效地传递了标签的语义知识，并大大提高了推断罕见和不可见类型的泛化能力。此外，多个语义分类任务可以在统一框架内联合训练，从而形成一个单一的紧凑型多任务模型，该模型可以执行专用的单任务模型，同时提供更好的可移植性。
Semantic typing aims at classifying tokens or spans of interest in a textual context into semantic categories such as relations, entity types, and event types. The inferred labels of semantic categories meaningfully interpret how machines understand components of text. In this paper, we present UniST, a unified framework for semantic typing that captures label semantics by projecting both inputs and labels into a joint semantic embedding space. To formulate different lexical and relational semantic typing tasks as a unified task, we incorporate task descriptions to be jointly encoded with the input, allowing UniST to be adapted to different tasks without introducing task-specific model components. UniST optimizes a margin ranking loss such that the semantic relatedness of the input and labels is reflected from their embedding similarity. Our experiments demonstrate that UniST achieves strong performance across three semantic typing tasks: entity typing, relation classification and event typing. Meanwhile, UniST effectively transfers semantic knowledge of labels and substantially improves generalizability on inferring rarely seen and unseen types. In addition, multiple semantic typing tasks can be jointly trained within the unified framework, leading to a single compact multi-tasking model that performs comparably to dedicated single-task models, while offering even better transferability.