Cross-Language Question Re-Ranking

TL;DR

This paper investigates cross-language question re-ranking between Arabic and English, comparing kernel-based and neural network approaches, and introduces a cross-language tree kernel to improve performance close to monolingual systems.

Contribution

It introduces a cross-language tree kernel for question re-ranking that significantly improves cross-language performance, bridging the gap with monolingual systems.

Findings

Cross-language tree kernel nearly matches monolingual performance.

Kernel-based system outperforms neural network in all tested scenarios.

Using cross-language embeddings improves neural network results.

Abstract

We study how to find relevant questions in community forums when the language of the new questions is different from that of the existing questions in the forum. In particular, we explore the Arabic-English language pair. We compare a kernel-based system with a feed-forward neural network in a scenario where a large parallel corpus is available for training a machine translation system, bilingual dictionaries, and cross-language word embeddings. We observe that both approaches degrade the performance of the system when working on the translated text, especially the kernel-based system, which depends heavily on a syntactic kernel. We address this issue using a cross-language tree kernel, which compares the original Arabic tree to the English trees of the related questions. We show that this kernel almost closes the performance gap with respect to the monolingual system. On the neural network side, we use the parallel corpus to train cross-language embeddings, which we then use to represent the Arabic input and the English related questions in the same space. The results also improve to close to those of the monolingual neural network. Overall, the kernel system shows a better performance compared to the neural network in all cases.