Recently, there has been significant progress in studying neural networks to translate text descriptions into SQL queries. Despite achieving good performance on some public benchmarks, existing text-to-SQL models typically rely on the lexical matching between words in natural language (NL) questions and tokens in table schemas, which may render the models vulnerable to attacks that break the schema linking mechanism. In this work, we investigate the robustness of text-to-SQL models to synonym substitution. In particular, we introduce Spider-Syn, a human-curated dataset based on the Spider benchmark for text-to-SQL translation. NL questions in Spider-Syn are modified from Spider, by replacing their schema-related words with manually selected synonyms that reflect real-world question paraphrases. We observe that the accuracy dramatically drops by eliminating such explicit correspondence between NL questions and table schemas, even if the synonyms are not adversarially selected to conduct worst-case adversarial attacks 1 . Finally, we present two categories of approaches to improve the model robustness. The first category of approaches utilizes additional synonym annotations for table schemas by modifying the model input, while the second category is based on adversarial training. We demonstrate that both categories of approaches significantly outperform their counterparts without the defense, and the first category of approaches are more effective. 2
This paper investigates the recognition of unknown words in Chinese parsing. Two methods are proposed to handle this problem. One is the modification of a character-based model. We model the emission probability of an unknown word using the first and last characters in the word. It aims to reduce the POS tag ambiguities of unknown words to improve the parsing performance. In addition, a novel method, using graph-based semisupervised learning (SSL), is proposed to improve the syntax parsing of unknown words. Its goal is to discover additional lexical knowledge from a large amount of unlabeled data to help the syntax parsing. The method is mainly to propagate lexical emission probabilities to unknown words by building the similarity graphs over the words of labeled and unlabeled data. The derived distributions are incorporated into the parsing process. The proposed methods are effective in dealing with the unknown words to improve the parsing. Empirical results for Penn Chinese Treebank and TCT Treebank revealed its effectiveness.
Recently, there has been significant progress in studying neural networks to translate text descriptions into SQL queries. Despite achieving good performance on some public benchmarks, existing text-to-SQL models typically rely on the lexical matching between words in natural language (NL) questions and tokens in table schemas, which may render the models vulnerable to attacks that break the schema linking mechanism. In this work, we investigate the robustness of text-to-SQL models to synonym substitution. In particular, we introduce Spider-Syn, a human-curated dataset based on the Spider benchmark for text-to-SQL translation. NL questions in Spider-Syn are modified from Spider, by replacing their schema-related words with manually selected synonyms that reflect real-world question paraphrases. We observe that the accuracy dramatically drops by eliminating such explicit correspondence between NL questions and table schemas, even if the synonyms are not adversarially selected to conduct worst-case adversarial attacks 1 . Finally, we present two categories of approaches to improve the model robustness. The first category of approaches utilizes additional synonym annotations for table schemas by modifying the model input, while the second category is based on adversarial training. We demonstrate that both categories of approaches significantly outperform their counterparts without the defense, and the first category of approaches are more effective. 2
It is significant to identify the running-states by obtaining and analyzing the vibration signals to avoid the faults. In this paper, the state recognition system is built based on the feature extraction with Varying Scale (VS) theory and Hidden Semi-Markov model (HSMM) with the exam pie of bushing abrasion on diesel engine. The veracity of state identification can be improved effectively by banding them together. According to experiment and simulation researches, it indicates that the veracity of identification is 97.5% in the 120 test samples after training with 80 training sam pies. It is satisfied for the demand to the engineering domain and it can be applied for vibration analysis for other complex machineries.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.