Cross-lingual Document Retrieval using Regularized Wasserstein Distance

05/11/2018
by   Georgios Balikas, et al.
0

Many information retrieval algorithms rely on the notion of a good distance that allows to efficiently compare objects of different nature. Recently, a new promising metric called Word Mover's Distance was proposed to measure the divergence between text passages. In this paper, we demonstrate that this metric can be extended to incorporate term-weighting schemes and provide more accurate and computationally efficient matching between documents using entropic regularization. We evaluate the benefits of both extensions in the task of cross-lingual document retrieval (CLDR). Our experimental results on eight CLDR problems suggest that the proposed methods achieve remarkable improvements in terms of Mean Reciprocal Rank compared to several baselines.

READ FULL TEXT
research
11/02/2020

Cross-Lingual Document Retrieval with Smooth Learning

Cross-lingual document search is an information retrieval task in which ...
research
05/26/2020

A Study of Neural Matching Models for Cross-lingual IR

In this study, we investigate interaction-based neural matching models f...
research
10/24/2019

Wasserstein distances for evaluating cross-lingual embeddings

Word embeddings are high dimensional vector representations of words tha...
research
04/03/2023

Simple Yet Effective Neural Ranking and Reranking Baselines for Cross-Lingual Information Retrieval

The advent of multilingual language models has generated a resurgence of...
research
07/13/2020

A Feature Analysis for Multimodal News Retrieval

Content-based information retrieval is based on the information containe...
research
04/23/2019

Wasserstein-Fisher-Rao Document Distance

As a fundamental problem of natural language processing, it is important...
research
09/14/2017

T^2K^2: The Twitter Top-K Keywords Benchmark

Information retrieval from textual data focuses on the construction of v...

Please sign up or login with your details

Forgot password? Click here to reset