arXiv Open Access 2018

Deep Neural Network for Learning to Rank Query-Text Pairs

Baoyang Song

Lihat Sumber

Abstrak

This paper considers the problem of document ranking in information retrieval systems by Learning to Rank. We propose ConvRankNet combining a Siamese Convolutional Neural Network encoder and the RankNet ranking model which could be trained in an end-to-end fashion. We prove a general result justifying the linear test-time complexity of pairwise Learning to Rank approach. Experiments on the OHSUMED dataset show that ConvRankNet outperforms systematically existing feature-based models.

Topik & Kata Kunci

cs.IR

Penulis (1)

Baoyang Song

Format Sitasi

APA MLA BibTeX

Song, B. (2018). Deep Neural Network for Learning to Rank Query-Text Pairs. https://arxiv.org/abs/1802.08988

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2018
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓