Báo cáo khoa học: "Hierarchical Bayesian Language Modelling for the Linguistically Informed"

Chia sẻ: Nhung Nhung | Ngày: | Loại File: PDF | Số trang:10

0
37
lượt xem
3
download

Báo cáo khoa học: "Hierarchical Bayesian Language Modelling for the Linguistically Informed"

Mô tả tài liệu
  Download Vui lòng tải xuống để xem tài liệu đầy đủ

In this work I address the challenge of augmenting n-gram language models according to prior linguistic intuitions. I argue that the family of hierarchical Pitman-Yor language models is an attractive vehicle through which to address the problem, and demonstrate the approach by proposing a model for German compounds. In an empirical evaluation, the model outperforms the Kneser-Ney model in terms of perplexity, and achieves preliminary improvements in English-German translation.

Chủ đề:
Lưu

Nội dung Text: Báo cáo khoa học: "Hierarchical Bayesian Language Modelling for the Linguistically Informed"

CÓ THỂ BẠN MUỐN DOWNLOAD

Đồng bộ tài khoản