Zobrazeno 1 - 10
of 716
pro vyhledávání: '"Si, Luo"'
Existing knowledge-enhanced methods have achieved remarkable results in certain QA tasks via obtaining diverse knowledge from different knowledge bases. However, limited by the properties of retrieved knowledge, they still have trouble benefiting fro
Externí odkaz:
http://arxiv.org/abs/2305.08135
Autor:
Li, Jinyang, Hui, Binyuan, Cheng, Reynold, Qin, Bowen, Ma, Chenhao, Huo, Nan, Huang, Fei, Du, Wenyu, Si, Luo, Li, Yongbin
The task of text-to-SQL parsing, which aims at converting natural language questions into executable SQL queries, has garnered increasing attention in recent years, as it can assist end users in efficiently extracting vital information from databases
Externí odkaz:
http://arxiv.org/abs/2301.07507
We present Pre-trained Machine Reader (PMR), a novel method for retrofitting pre-trained masked language models (MLMs) to pre-trained machine reading comprehension (MRC) models without acquiring labeled data. PMR can resolve the discrepancy between m
Externí odkaz:
http://arxiv.org/abs/2212.04755
Neural machine translation (NMT) is often criticized for failures that happen without awareness. The lack of competency awareness makes NMT untrustworthy. This is in sharp contrast to human translators who give feedback or conduct further investigati
Externí odkaz:
http://arxiv.org/abs/2211.13865
Relation extraction has the potential for large-scale knowledge graph construction, but current methods do not consider the qualifier attributes for each relation triplet, such as time, quantity or location. The qualifiers form hyper-relational facts
Externí odkaz:
http://arxiv.org/abs/2211.10018
Cross-lingual named entity recognition (NER) suffers from data scarcity in the target languages, especially under zero-shot settings. Existing translate-train or knowledge distillation methods attempt to bridge the language gap, but often introduce a
Externí odkaz:
http://arxiv.org/abs/2211.09394
Due to the huge amount of parameters, fine-tuning of pretrained language models (PLMs) is prone to overfitting in the low resource scenarios. In this work, we present a novel method that operates on the hidden representations of a PLM to reduce overf
Externí odkaz:
http://arxiv.org/abs/2211.08794
Out-of-Domain (OOD) intent detection is important for practical dialog systems. To alleviate the issue of lacking OOD training samples, some works propose synthesizing pseudo OOD samples and directly assigning one-hot OOD labels to these pseudo sampl
Externí odkaz:
http://arxiv.org/abs/2211.05561
A wide range of control perspectives have been explored in controllable text generation. Structure-controlled summarization is recently proposed as a useful and interesting research direction. However, current structure-controlling methods have limit
Externí odkaz:
http://arxiv.org/abs/2210.14502
Autor:
Gao, Chang, Li, Bowen, Zhang, Wenxuan, Lam, Wai, Li, Binhua, Huang, Fei, Si, Luo, Li, Yongbin
Text-to-SQL parsing tackles the problem of mapping natural language questions to executable SQL queries. In practice, text-to-SQL parsers often encounter various challenging scenarios, requiring them to be generalizable and robust. While most existin
Externí odkaz:
http://arxiv.org/abs/2210.12674