IRCLMay 26, 2020

A Study of Neural Matching Models for Cross-lingual IR

arXiv:2005.12994v127 citations
Originality Synthesis-oriented
AI Analysis

This work addresses cross-lingual search challenges for users needing information in multiple languages, but it is incremental as it builds on existing neural and embedding methods.

The study tackled cross-lingual information retrieval by investigating interaction-based neural matching models using cross-lingual word embeddings, evaluating them on the CLEF collection across four language pairs to provide insights into architectures and similarity distributions.

In this study, we investigate interaction-based neural matching models for ad-hoc cross-lingual information retrieval (CLIR) using cross-lingual word embeddings (CLWEs). With experiments conducted on the CLEF collection over four language pairs, we evaluate and provide insight into different neural model architectures, different ways to represent query-document interactions and word-pair similarity distributions in CLIR. This study paves the way for learning an end-to-end CLIR system using CLWEs.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes