EMNLP Findings2023
Smart "Chef": Verifying the Effect of Role-based Paraphrasing for Aspect Term Extraction
Jiaxiang Chen, Yu Hong, Qingting Xu, Jianmin Yao
Abstract
We tackle Aspect Term Extraction (ATE), a task of automatically extracting aspect terms from sentences. The current Pretrained Language Model (PLM) based extractors have achieved significant improvements. They primarily benefit from context-aware encoding. However, a considerable number of sentences in ATE corpora contain uninformative or low-quality contexts. Such sentences frequently act as "troublemakers" during test. In this study, we explore the context-oriented quality improvement method. Specifically, we propose to automatically rewrite the sentences from the perspectives of virtual experts with different roles, such as a "chef" in the restaurant domain. On this basis, we perform ATE over the paraphrased sentences during test, using the well-trained extractors without any change. In the experiments, we leverage ChatGPT to determine virtual experts in the considered domains, and induce ChatGPT to generate paraphrases conditioned on the roles of virtual experts. We experiment on the benchmark SemEval datasets, including Laptop-domain L14 and Restaurantdomain R14-16. The experimental results show that our approach effectively recalls the inconspicuous aspect terms like "al di la", although it reduces the precision. In addition, it is proven that our approach can be substantially improved by redundancy elimination and multi-role voting. More importantly, our approach can be used to expand the predictions obtained on the original sentences. This yields state-of-the-art performance (i.e., F 1-scores of 86.2%, 89.3%, 77.7%, 82.7% on L14 and R14-16) without retraining or fine-tuning the baseline extractors.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Enhancing Aspect Term Extraction with Soft Prototypes cites Conditional Augmentation for Aspect Term Extraction via Masked Sequence-to-Sequence Generation
- Finetuned Language Models are Zero-Shot Learners cites BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
Builds on10
- Finetuned Language Models are Zero-Shot LearnersJason Wei, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu et al.ICLR 2022 · 4,966 citations
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
- Conditional Augmentation for Aspect Term Extraction via Masked Sequence-to-Sequence GenerationKun Li, Chengbo Chen, Xiaojun Quan, Qing Ling et al.ACL 2020 · 101 citations
- Enhancing Aspect Term Extraction with Soft PrototypesZhuang Chen, Tieyun QianEMNLP 2020 · 56 citations
- A Span-level Bidirectional Network for Aspect Sentiment Triplet ExtractionYuqi Chen, Keming Chen, Xian Sun, Zequn ZhangEMNLP 2022 · 50 citations
Related papers
- Enhancing Automatic Term Extraction with Large Language Models via Syntactic RetrievalYongchan Chun, Minhyuk Kim, Dongjun Kim, Chanjun Park et al.ACL Findings 2025 · 3 citations
- Low-Resource Comparative Opinion Quintuple Extraction by Data Augmentation with PromptingQingting Xu, Yu Hong, Fubang Zhao, Kaisong Song et al.EMNLP Findings 2023 · 4 citations
- MiniConGTS: A Near Ultimate Minimalist Contrastive Grid Tagging Scheme for Aspect Sentiment Triplet ExtractionQiao Sun, Liujia Yang, Minghao Ma, Nanyang Ye et al.EMNLP 2024 · 5 citations
- ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information ExtractionJiabang He, Lei Wang, Yi Hu, Ning Liu et al.ICCV 2023 · 61 citations
- When "A Helpful Assistant" Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language ModelsMingqian Zheng, Jiaxin Pei, Lajanugen Logeswaran, Moontae Lee et al.EMNLP Findings 2024 · 83 citations
