.png){kind=icon}
返回
Unified Instance and Knowledge Alignment Pretraining for Aspect-Based Sentiment Analysis
.png){kind=icon}
OA
AI
DOI：10.1109/TASLP.2023.3290431.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The goal of aspect-based sentiment analysis (ABSA) is to determine the sentiment polarity towards an aspect. Because of the expensive and limited amounts of labelled data, the pretraining strategy has become the de facto standard for ABSA. However, there always exists a severe domain shift between the pretraining and downstream ABSA datasets, which hinders effective knowledge transfer when directly fine-tuning, making the downstream task suboptimal. To mitigate this domain shift, we introduce a unified alignment pretraining framework into the vanilla pretrain-finetune pipeline, that has both instance- and knowledge-level alignments. Specifically, we first devise a novel coarse-to-fine retrieval sampling approach to select target domain-related instances from the large-scale pretraining dataset, thus aligning the instances between pretraining and the target domains (First Stage). Then, we introduce a knowledge guidance-based strategy to further bridge the domain gap at the knowledge level. In practice, we formulate the model pretrained on the sampled instances into a knowledge guidance model and a learner model. On the target dataset, we design an on-the-fly teacher-student joint fine-tuning approach to progressively transfer the knowledge from the knowledge guidance model to the learner model (Second Stage). Therefore, the learner model can maintain more domain-invariant knowledge when learning new knowledge from the target dataset. In the Third Stage, the learner model is finetuned to better adapt its learned knowledge to the target dataset. Extensive experiments and analyses on several ABSA benchmarks demonstrate the effectiveness and universality of our proposed pretraining framework.
Keyword:
Aspect-based sentiment analysis
domain shift
instance alignment
knowledge alignment
pretraining
期刊
I
IF:
5.1
论文数:
2.6K
被引数:
1.1W
机构
引用论文
Simultaneous Dust and Pollutant Transport over East Asia: The Tripartite Environment Ministers Meeting March 2014 Case Study.png)
SOLA
OAAI
SOLAIF0
OAAI分享收藏分享收藏
查看更多内容