hierarchy
发表于 2025-3-21 20:03:10
书目名称Natural Language Processing and Chinese Computing影响因子(影响力)<br> http://figure.impactfactor.cn/if/?ISSN=BK0661809<br><br> <br><br>书目名称Natural Language Processing and Chinese Computing影响因子(影响力)学科排名<br> http://figure.impactfactor.cn/ifr/?ISSN=BK0661809<br><br> <br><br>书目名称Natural Language Processing and Chinese Computing网络公开度<br> http://figure.impactfactor.cn/at/?ISSN=BK0661809<br><br> <br><br>书目名称Natural Language Processing and Chinese Computing网络公开度学科排名<br> http://figure.impactfactor.cn/atr/?ISSN=BK0661809<br><br> <br><br>书目名称Natural Language Processing and Chinese Computing被引频次<br> http://figure.impactfactor.cn/tc/?ISSN=BK0661809<br><br> <br><br>书目名称Natural Language Processing and Chinese Computing被引频次学科排名<br> http://figure.impactfactor.cn/tcr/?ISSN=BK0661809<br><br> <br><br>书目名称Natural Language Processing and Chinese Computing年度引用<br> http://figure.impactfactor.cn/ii/?ISSN=BK0661809<br><br> <br><br>书目名称Natural Language Processing and Chinese Computing年度引用学科排名<br> http://figure.impactfactor.cn/iir/?ISSN=BK0661809<br><br> <br><br>书目名称Natural Language Processing and Chinese Computing读者反馈<br> http://figure.impactfactor.cn/5y/?ISSN=BK0661809<br><br> <br><br>书目名称Natural Language Processing and Chinese Computing读者反馈学科排名<br> http://figure.impactfactor.cn/5yr/?ISSN=BK0661809<br><br> <br><br>
漂浮
发表于 2025-3-21 21:36:03
https://doi.org/10.1007/978-3-319-99501-4artificial intelligence; classification; data mining; HCI; human-computer interaction; information retrie
nephritis
发表于 2025-3-22 03:56:08
http://reply.papertrans.cn/67/6619/661809/661809_3.png
Pelvic-Floor
发表于 2025-3-22 07:20:01
http://reply.papertrans.cn/67/6619/661809/661809_4.png
移动
发表于 2025-3-22 11:07:46
http://reply.papertrans.cn/67/6619/661809/661809_5.png
indenture
发表于 2025-3-22 14:24:56
http://reply.papertrans.cn/67/6619/661809/661809_6.png
Admonish
发表于 2025-3-22 18:13:54
http://reply.papertrans.cn/67/6619/661809/661809_7.png
PANIC
发表于 2025-3-22 21:53:06
http://reply.papertrans.cn/67/6619/661809/661809_8.png
abstemious
发表于 2025-3-23 05:19:57
Which Embedding Level is Better for Semantic Representation? An Empirical Research on Chinese Phrased investigate the performance of the two basic units. Empirical results show that with all composing methods, word embedding out performs character embedding on both tasks, which indicates that word level is more suitable for composing semantic representation.
破布
发表于 2025-3-23 08:06:02
Improving Word Embeddings for Antonym Detection Using Thesauri and SentiWordNetord in SentiWordNet. We conduct evaluations on three relevant tasks, namely GRE antonym detection, word similarity, and semantic textual similarity. The experiment results show that our antonym-sensitive embedding outperforms common word embeddings in these tasks, demonstrating the efficacy of our methods.