-
Notifications
You must be signed in to change notification settings - Fork 900
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
句子的相似度计算方法是什么? #64
Comments
请问这个平滑策略的根据是什么呢,谢谢! |
曲线形状 |
还有两个问题想问一下您,您的代码中_flat_sum_array这个函数是将句子中各个词的词向量叠加吗? |
请教一下,是我用法不对还是词库的问题,"舒服"的近义词为什么是"难受"? |
计算依据非监督的word2vec, 是利用前后词作为特征,所以也会出现反义词的时候。使用机器学习会有准确率的问题,并不保证100%都是准确的近义词。
…------------------
Cheers.
Hai Liang Wang, CEO, Chatopera
------------------ Original ------------------
From: "fremcode";
Date: 2019年1月15日(星期二) 上午10:46
To: "huyingxi/Synonyms";
Cc: "Samurais"; "State change";
Subject: Re: [huyingxi/Synonyms] 句子的相似度计算方法是什么? (#64)
请教一下,是我用法不对还是词库的问题,"舒服"的近义词为什么是"难受"?
—
You are receiving this because you modified the open/close state.
Reply to this email directly, view it on GitHub, or mute the thread.
|
句子相似度比较每次得到的结果居然不一致。。。 第二次运行结果: 第三次运行结果: |
为什么是词向量相似度和编辑距离相似度相乘而不是相加呢? |
在这个问题下学到很多,我的理解是: |
比如,句子的向量表示为每个词的vector取平均,然后cos
或者用softcos、WMD之类?
The text was updated successfully, but these errors were encountered: