Fusing external knowledge resources for natural language understanding techniques: A survey
Abstract Knowledge resources, eg knowledge graphs, which formally represent essential
semantics and information for logic inference and reasoning, can compensate for the …
semantics and information for logic inference and reasoning, can compensate for the …
Generating knowledge aware explanation for natural language inference
Natural language inference (NLI) is an increasingly important task of natural language
processing, and the explainable NLI generates natural language explanations (NLEs) in …
processing, and the explainable NLI generates natural language explanations (NLEs) in …
Kc-isa: An implicit sentiment analysis model combining knowledge enhancement and context features
M Xu, D Wang, S Feng, Z Yang… - Proceedings of the 29th …, 2022 - aclanthology.org
Sentiment analysis has always been an important research direction in natural language
processing. The research can be divided into explicit sentiment analysis and implicit …
processing. The research can be divided into explicit sentiment analysis and implicit …
A multi-level supervised contrastive learning framework for low-resource natural language inference
Natural Language Inference (NLI) is a growingly essential task in natural language
understanding, which requires inferring the relationship between the sentence pairs …
understanding, which requires inferring the relationship between the sentence pairs …
Multi-type factors representation learning for deep learning-based knowledge tracing
L He, J Tang, X Li, P Wang, F Chen, T Wang - World Wide Web, 2022 - Springer
Abstract Knowledge Tracing (KT) refers to the problem of predicting future learner
performance given their historical interactions with e-learning platforms. Recent years, Deep …
performance given their historical interactions with e-learning platforms. Recent years, Deep …
Reducing disambiguation biases in NMT by leveraging explicit word sense information
Recent studies have shed some light on a common pitfall of Neural Machine Translation
(NMT) models, stemming from their struggle to disambiguate polysemous words without …
(NMT) models, stemming from their struggle to disambiguate polysemous words without …
Knowledge enhanced fact checking and verification
B Zhu, X Zhang, M Gu, Y Deng - IEEE/ACM Transactions on …, 2021 - ieeexplore.ieee.org
As the Internet and social media offer increasing opportunities for organizations and
individuals to publicize online contents, it has become essential to develop effective means …
individuals to publicize online contents, it has become essential to develop effective means …
Prompt-based zero-shot text classification with conceptual knowledge
In recent years, pre-trained language models have garnered significant attention due to their
effectiveness, which stems from the rich knowledge acquired during pre-training. To mitigate …
effectiveness, which stems from the rich knowledge acquired during pre-training. To mitigate …
Network based on the synergy of knowledge and context for natural language inference
H Wu, J Huang - Neurocomputing, 2022 - Elsevier
The goal of natural language inference (NLI) is to judge the logical relationship between
sentence pairs, including entailment, contradiction, and neutral. At present, many …
sentence pairs, including entailment, contradiction, and neutral. At present, many …
A Novel Joint Training Model for Knowledge Base Question Answering
In knowledge base question answering (KBQA) systems, relation detection and entity
recognition are two core components. However, since the relation detection in KBQA …
recognition are two core components. However, since the relation detection in KBQA …