Abstract
Existing PTLM-based models for TSC can be categorized into two groups: 1) fine-tuning-based models that adopt PTLM as the context encoder; 2) prompting-based models that transfer the classification task to the text/word generation task. In this paper, we present a new perspective of leveraging PTLM for TSC: simultaneously leveraging the merits of both language modeling and explicit target-context interactions via contextual target attributes. Specifically, we design the domain- and target-constrained cloze test, which can leverage the PTLMs' strong language modeling ability to generate the given target's attributes pertaining to the review context. The attributes contain the background and property information of the target, which can help to enrich the semantics of the review context and the target. To exploit the attributes for tackling TSC, we first construct a heterogeneous information graph by treating the attributes as nodes and combining them with (1) the syntax graph automatically produced by the off-the-shelf dependency parser and (2) the semantics graph of the review context, which is derived from the self-attention mechanism. Then we propose a heterogeneous information gated graph convolutional network to model the interactions among the attribute information, the syntactic information, and the contextual information. The experimental results on three benchmark datasets demonstrate the superiority of our model, which achieves new state-of-the-art performance.
Abstract (translated)
现有的基于PTLM的TCS模型可以分为两组:1)基于微调的模型,它们采用PTLM作为上下文编码器;2)基于提示的模型,它们将分类任务转移到文本/单词生成任务。在本文中,我们提出了一个新的利用PTLM的视角:通过上下文目标属性同时利用语言建模和明确的目标上下文交互的优点。具体来说,我们设计了一个域-和目标约束的闭包测试,该测试可以利用PTLM在给定评论上下文生成目标属性的强大语言建模能力。属性包含目标的背景和属性信息,这可以帮助丰富评论上下文和目标的语义。为了应对TC,我们首先通过将属性视为节点,将它们与(1)由普通依赖解析器自动生成的语法图和(2)来自自我注意机制生成的评论语义图合并,构建了一个异质信息图。然后,我们提出了一个异质信息卷积网络来建模属性信息、语义信息以及上下文信息的交互。在三个基准数据集上的实验结果表明,我们的模型具有优越的性能,实现了最新的 state-of-the-art 水平。
URL
https://arxiv.org/abs/2312.13766