Position-aware Attention and Supervised Data Improve Slot Filling

作者:stanford
来源:EMNLP2017

本文贡献:公布了一批SF关系分类的语料,the TAC KBP Relation Extraction Dataset(TACRED),共有119474examples,存放于LDC
创新:将位置注意力机制与LSTM结合

已有工作的问题;
1、Although modern sequence models such as Long Short-Term Memory(LSTM) networks have gating mechanisms to control the relative influence of each individual word to the final sentence representation (Hochreiter and Schmidhuber, 1997), these controls are not explicitly conditioned on the entire sentence being classified;
2、Most existing work either does not explicitly model the positions of entities (i.e., subject and object) in the sequence, or models the positions only within a local region.

position encoder:

ps=is1,0,is2,i<s1s1is2i>s2

ui=vTtanh(Whhi+Wqq+WsPsi+Wspoi)

ai=exp(ui)j=1nexp(uj)

z=ni=1aihi

最后在z上加个全连接层,然后softmax分类

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值