我: 朋友终于装上了赫赫有名的谷歌 SytaxNet 中文自动分析器。随手试了一个例子。From syntaxnet, we have this parse: From yours truly, this is the result: To laymen’s eyes, they look alike. They are both dependency trees. Of course. They seem to have used the same or similar tools for dra ...
After I showed the benchmarking results of SyntaxNet and our rule system based on grammar engineering, many people seem to be surprised by the fact that the rule system beats the newest deep-learning based parser in data quality . I then got asked many questions, one question is: Q: We kn ...
众所周知,作为符号系统,自然语言与电脑语言的最大差异和挑战在于其歧义性,有两类,结构歧义(structural ambiguity)和一词多义(相应的消歧任务叫WSD,word sense disambiguation)。如果没有这些随处可见的歧义,自然语言的自动分析就会与电脑语言的编译一样做到精准无误。因此,一般认为,自然语言parsing和NLU(自 ...