T5-SR：一种面向语义解析的统一序列到序列解码策略
T5-SR: A Unified Seq-to-Seq Decoding Strategy for Semantic Parsing
AI总结：
针对seq2seq语义解析存在的模式预测质量差、语义一致性弱的问题，提出含SSQL中间表示和重排序机制的SR解码策略，T5-SR-3b在Spider数据集上取得SOTA结果。
摘要：
近年来，以序列到序列（seq2seq）方式将自然语言查询转化为SQL受到了广泛关注。但与基于抽象语法树的SQL生成方法相比，seq2seq语义解析器面临更多挑战，包括模式信息预测质量较差、自然语言查询与SQL之间语义一致性不足。本文分析了上述难点，提出了一种面向seq2seq的解码策略SR，它包含一种新的中间表示SSQL，以及一种带分数重估计器的重排序方法，分别用于解决上述问题。实验结果证明了所提技术的有效性，其中T5-SR-3b在Spider数据集上取得了新的最优（state-of-the-art）结果。
英文摘要：
Translating natural language queries into SQLs in a seq2seq manner has attracted much attention recently. However, compared with abstract-syntactic-tree-based SQL generation, seq2seq semantic parsers face much more challenges, including poor quality on schematical information prediction and poor semantic coherence between natural language queries and SQLs. This paper analyses the above difficulties and proposes a seq2seq-oriented decoding strategy called SR, which includes a new intermediate representation SSQL and a reranking method with score re-estimator to solve the above obstacles respectively. Experimental results demonstrate the effectiveness of our proposed techniques and T5-SR-3b achieves new state-of-the-art results on the Spider dataset.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
