贵族
发表于 2025-3-26 21:30:37
http://reply.papertrans.cn/67/6619/661811/661811_31.png
过度
发表于 2025-3-27 04:40:17
http://reply.papertrans.cn/67/6619/661811/661811_32.png
NEX
发表于 2025-3-27 09:13:57
http://reply.papertrans.cn/67/6619/661811/661811_33.png
Individual
发表于 2025-3-27 13:25:25
Faster and Better Grammar-Based Text-to-SQL Parsing via Clause-Level Parallel Decoding and Alignmentparallel decoding and alignment loss to enhance two high-performance grammar-based parsers, i.e., RATSQL and LGESQL. Experiments on the Spider dataset show our approach improves the decoding speed of RATSQL and LGESQL by 18.9% and 35.5% respectively, and also achieves consistent improvement in parsing accuracy, especially on complex questions.
Laconic
发表于 2025-3-27 14:49:31
http://reply.papertrans.cn/67/6619/661811/661811_35.png
STERN
发表于 2025-3-27 21:21:56
http://reply.papertrans.cn/67/6619/661811/661811_36.png
粗糙
发表于 2025-3-28 00:15:14
Faster and Better Grammar-Based Text-to-SQL Parsing via Clause-Level Parallel Decoding and Alignmentce the number of actions for building SQL trees are much larger than the number of tokens in SQL queries. Meanwhile, intuitively it is beneficial from the parsing performance perspective to incorporate alignment information between SQL clauses and question segments. This paper proposes clause-level
生意行为
发表于 2025-3-28 03:07:28
Two-Stage Query Graph Selection for Knowledge Base Question Answeringteractive performance requirement. A typical solution is to retrieve the answer by finding the optimal query graph, which is a sub-graph of the knowledge graph. However, existing methods usually generate a considerable number of sub-graph candidates, then fail to find the optimal one effectively, re
intricacy
发表于 2025-3-28 06:31:42
http://reply.papertrans.cn/67/6619/661811/661811_39.png
骇人
发表于 2025-3-28 13:56:33
FuDFEND: Fuzzy-Domain for Multi-domain Fake News Detectione begun to use single domain label for fake news detection recently. Existing works show that using single domain label can improve the accuracy of fake news detection model. However, there are two problems in previous works. Firstly, they ignore that a piece of news may have features from different