美文网首页
《Fine-grained opinion mining wit

《Fine-grained opinion mining wit

作者: best___me | 来源:发表于2017-12-04 21:55 被阅读0次

论文链接:http://www1.se.cuhk.edu.hk/~hccl/publications/pub/2015_EMNLP168.pdf

fine-grained opinion mining:细粒度意见挖掘

“John says, the hard disk is very noisy”  

John---the opinion holder    target---hard disk    very noisy---opinion

The tasks in fine-grained opinion mining can be regarded as either a token-level sequence labeling problem or as a semantic compositional task at the sequence (e.g., phrase) level


Recurrent neural models:

vocabulary中的每个词都用D维的向量表示,共享的look-up table

look-up table

给定一个输入句子

input sentence

增加上下文,连接上下文三个词的embedding

concatenated vector送到非线性的rnn来学习high-level compositional representations,输出用softmax。

softmax

最小化the negative log likelihood(NLL)

NLL for the sentence s ytk = 1 if the gold label yt=k otherwise 0

1. Elman-type RNN

2. Jordan-type RNN

双向RNN:

实验:

使用laptop和restaurant数据集

大部分aspect term只有一个词,大约三分之一的是有多个词的。在每个数据集中,有些句子是没有aspect terms的,有一些句子有多个aspect terms。

Evaluation metric: 标准的precision,recall,F1

a candidate aspect term is considered to be correct only if it exactly matches with the aspect term annotated by the human.

我有点摸不着头脑。。。题目明明是细粒度的意见提取,但是!实验根本没有做意见提取啊,只做了aspect term extraction,而且意见做标注可行吗,很多句子的意见都是隐性表示的,根本找不到哪个词可以标注诶。

相关文章

网友评论

      本文标题:《Fine-grained opinion mining wit

      本文链接:https://www.haomeiwen.com/subject/mfyxixtx.html