SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models
By Jingfeng Yang, Haoming Jiang, Qingyu Yin, Danqing Zhang, Bing Yin, Diyi Yang. 2022
59 citations recorded by the source corpus.
Recent research showed promising results on combining pretrained language models (LMs) with canonical utterance for few-shot semantic parsing. The canonical utterance is often lengthy and complex due to the compositional structure of formal languages. Learning to generate such canonical utterance requires significant amount of data to reach high performance. Fine-tuning with only few-shot samples, the LMs can easily forget pretrained knowledge, overfit spurious biases, and suffer from compositionally out-of-distribution generalization errors. To tackle these issues, we propose a novel few-shot semantic parsing method -- SeqZero. SeqZero decomposes the problem into a sequence of sub-problems, which correspond to the sub-clauses of the formal language. Based on the decomposition, the LMs only need to generate short answers using prompts for predicting sub-clauses. Thus, SeqZero avoids generating a long canonical utterance at once. Moreover, SeqZero employs not only a few-shot model but also a zero-shot model to alleviate the overfitting. In particular, SeqZero brings out the merits from both models via ensemble equipped with our proposed constrained rescaling. SeqZero achieves SOTA performance of BART-based models on GeoQuery and EcommerceQuery, which are two few-shot datasets with compositional data split.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Prompting & Reasoning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Mohit Bansal
- Luke S. Zettlemoyer
- Jianfeng Gao
- Yejin Choi
- Denny Zhou
- Timo Schick
- Hinrich Schütze
- Xinyun Chen
In Computer Vision and Pattern Recognition
- Mohit Bansal
- Ramakanth Pasunuru
- Jianfeng Gao
- Luc Van Gool
- Dacheng Tao
- Edouard Grave
- Trevor Darrell
- Jitendra Malik
In Natural Language Processing
- Timo Schick
- Asli Celikyilmaz
- Thomas Scialom
- Hinrich Schütze
- Edouard Grave
- Maria Lomeli
- Yejin Choi
- Denny Zhou
In Prompting & Reasoning
- Xinyun Chen
- Denny Zhou
- Jie Huang
- Thomas Scialom
- Ramakanth Pasunuru
- Kevin Chen-Chuan Chang
- Jane Dwivedi-Yu
- Nathanael Scharli
Citations in the corpus
- Augmented Language Models: a Survey (2023, methodology): “Re3 (Yang et al., 2022c) exploits this idea to automatically generate stories of over two thousand words.”
- Compositional Semantic Parsing with Large Language Models (2022, background): “Furthermore, SeqZero is an ensemble of a finetuned BART and a zero-shot model while we use only prompting with large language models and forego finetuning entirely.”
- Reasoning with Language Model Prompting: A Survey (2022, unknown): “, 2022), compositional reasoning (Yang et al., 2022a), etc.”
- Towards Reasoning in Large Language Models: A Survey (2022, methodology): “…or method being used, e.g., deductive reasoning (Cobbe et al., 2021; Creswell et al., 2022; Han et al., 2022b, inter alia ), inductive reasoning (Yang et al., 2022; Misra et al., 2022, inter alia ) or abductive reasoning (Wiegreffe et al., 2022; Lampinen et al., 2022; Jung et al., 2022, inter…”
- Decomposition Enhances Reasoning via Self-Evaluation Guided Decoding (2023, unknown): “Various decomposition techniques have been explored, such as question reduction (Zhou et al., 2022; Yang et al., 2022), iterative prompting (Wang et al., 2022a), and chaining the steps (Wu et al., 2022).”