Matches in SemOpenAlex for { <https://semopenalex.org/work/W3202120412> ?p ?o ?g. }
- W3202120412 abstract "Pre-trained language models learn informative word representations on a large-scale text corpus through self-supervised learning, which has achieved promising performance in fields of natural language processing (NLP) after fine-tuning. These models, however, suffer from poor robustness and lack of interpretability. We refer to pre-trained language models with knowledge injection as knowledge-enhanced pre-trained language models (KEPLMs). These models demonstrate deep understanding and logical reasoning and introduce interpretability. In this survey, we provide a comprehensive overview of KEPLMs in NLP. We first discuss the advancements in pre-trained language models and knowledge representation learning. Then we systematically categorize existing KEPLMs from three different perspectives. Finally, we outline some potential directions of KEPLMs for future research." @default.
- W3202120412 created "2021-10-11" @default.
- W3202120412 creator A5001456655 @default.
- W3202120412 creator A5012673161 @default.
- W3202120412 creator A5024456332 @default.
- W3202120412 creator A5036862308 @default.
- W3202120412 creator A5042973046 @default.
- W3202120412 creator A5061279323 @default.
- W3202120412 creator A5066482162 @default.
- W3202120412 date "2021-10-01" @default.
- W3202120412 modified "2023-09-27" @default.
- W3202120412 title "A Survey of Knowledge Enhanced Pre-trained Models" @default.
- W3202120412 cites W135333644 @default.
- W3202120412 cites W1486649854 @default.
- W3202120412 cites W1505839237 @default.
- W3202120412 cites W1512387364 @default.
- W3202120412 cites W1533230146 @default.
- W3202120412 cites W1713614699 @default.
- W3202120412 cites W2052217781 @default.
- W3202120412 cites W205829674 @default.
- W3202120412 cites W2064675550 @default.
- W3202120412 cites W2072128103 @default.
- W3202120412 cites W2081580037 @default.
- W3202120412 cites W2113459411 @default.
- W3202120412 cites W2127426251 @default.
- W3202120412 cites W2132339004 @default.
- W3202120412 cites W2133286915 @default.
- W3202120412 cites W2136437513 @default.
- W3202120412 cites W2141599568 @default.
- W3202120412 cites W2145544171 @default.
- W3202120412 cites W2153579005 @default.
- W3202120412 cites W2153595771 @default.
- W3202120412 cites W2157735936 @default.
- W3202120412 cites W2162821268 @default.
- W3202120412 cites W2163455955 @default.
- W3202120412 cites W2163922914 @default.
- W3202120412 cites W2175268987 @default.
- W3202120412 cites W2250342289 @default.
- W3202120412 cites W2250539671 @default.
- W3202120412 cites W2251079237 @default.
- W3202120412 cites W2251648804 @default.
- W3202120412 cites W2251939518 @default.
- W3202120412 cites W2252136820 @default.
- W3202120412 cites W2283196293 @default.
- W3202120412 cites W2433281745 @default.
- W3202120412 cites W2465978385 @default.
- W3202120412 cites W2475757000 @default.
- W3202120412 cites W2493916176 @default.
- W3202120412 cites W2519887557 @default.
- W3202120412 cites W2554952599 @default.
- W3202120412 cites W2557283755 @default.
- W3202120412 cites W2604314403 @default.
- W3202120412 cites W2609826708 @default.
- W3202120412 cites W2620787630 @default.
- W3202120412 cites W2624431344 @default.
- W3202120412 cites W2734823783 @default.
- W3202120412 cites W2766453196 @default.
- W3202120412 cites W2804220263 @default.
- W3202120412 cites W2884668708 @default.
- W3202120412 cites W2888213795 @default.
- W3202120412 cites W2898662126 @default.
- W3202120412 cites W2911489562 @default.
- W3202120412 cites W2912924812 @default.
- W3202120412 cites W2914855263 @default.
- W3202120412 cites W2919115771 @default.
- W3202120412 cites W2922551710 @default.
- W3202120412 cites W2925618549 @default.
- W3202120412 cites W2944815030 @default.
- W3202120412 cites W2945260553 @default.
- W3202120412 cites W2946088473 @default.
- W3202120412 cites W2946545670 @default.
- W3202120412 cites W2950577311 @default.
- W3202120412 cites W2951048068 @default.
- W3202120412 cites W2951105272 @default.
- W3202120412 cites W2951434086 @default.
- W3202120412 cites W2951561177 @default.
- W3202120412 cites W2953356739 @default.
- W3202120412 cites W2954278700 @default.
- W3202120412 cites W2962718483 @default.
- W3202120412 cites W2962739339 @default.
- W3202120412 cites W2962767366 @default.
- W3202120412 cites W2962832505 @default.
- W3202120412 cites W2962881743 @default.
- W3202120412 cites W2962985038 @default.
- W3202120412 cites W2963012544 @default.
- W3202120412 cites W2963026768 @default.
- W3202120412 cites W2963056065 @default.
- W3202120412 cites W2963096510 @default.
- W3202120412 cites W2963310665 @default.
- W3202120412 cites W2963339397 @default.
- W3202120412 cites W2963341956 @default.
- W3202120412 cites W2963403868 @default.
- W3202120412 cites W2963564796 @default.
- W3202120412 cites W2963748441 @default.
- W3202120412 cites W2963769536 @default.
- W3202120412 cites W2963925965 @default.
- W3202120412 cites W2963993699 @default.
- W3202120412 cites W2963995027 @default.
- W3202120412 cites W2964116313 @default.
- W3202120412 cites W2964265128 @default.