Výsledky vyhledávání - "Zhang, Hanchu"

Report

T5-SR: A Unified Seq-to-Seq Decoding Strategy for Semantic Parsing

Autor: Li, Yuntao, Su, Zhenpeng, Li, Yutian, Zhang, Hanchu, Wang, Sirui, Wu, Wei, Zhang, Yan

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

Externí odkaz: http://arxiv.org/abs/2306.08368

Zobrazit plný text záznamu

Report

Pay More Attention to History: A Context Modelling Strategy for Conversational Text-to-SQL

Autor: Li, Yuntao, Zhang, Hanchu, Li, Yutian, Wang, Sirui, Wu, Wei, Zhang, Yan

Conversational text-to-SQL aims at converting multi-turn natural language queries into their corresponding SQL (Structured Query Language) representations. One of the most intractable problems of conversational text-to-SQL is modelling the semantics

Externí odkaz: http://arxiv.org/abs/2112.08735

Zobrazit plný text záznamu

Report

Bootstrapping Named Entity Recognition in E-Commerce with Positive Unlabeled Learning

Autor: Zhang, Hanchu, Hennig, Leonhard, Alt, Christoph, Hu, Changjian, Meng, Yao, Wang, Chao

Named Entity Recognition (NER) in domains like e-commerce is an understudied problem due to the lack of annotated datasets. Recognizing novel entity types in this domain, such as products, components, and attributes, is challenging because of their l

Externí odkaz: http://arxiv.org/abs/2005.11075

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Vyhledávací nástroje:

Upřesnit hledání