go-v.orgdoi

Data for paper: "Evaluating Multilingual Text Encoders for Unsupervised Cross-Lingual Retrieval"

Robert Litschko · UBMA · 2021

  • DOI 10.7801/361
  • Publisher OpenAlex
  • Type dataset
  • Issued 2021

Not cached yet. This record was fetched live for this request and is stored after the lookup. Reopening the page should serve the cached copy.

UBMA · OpenAlex · dataset · 2021

Abstract

Pretrained multilingual text encoders based on neural Transformer architectures, such as multilingual BERT (mBERT) and XLM, have achieved strong performance on a myriad of language understanding tasks. Consequently, they have been adopted as a go-to paradigm for multilingual and cross-lingual representation learning and transfer, rendering cross-lingual word embeddings (CLWEs) effectively obsolete. However, questions remain to which extent this finding generalizes 1) to unsupervised settings and 2) for ad-hoc cross-lingual IR (CLIR) tasks.

Therefore, in this work we present a systematic empirical study focused on the suitability of the state-of-the-art multilingual encoders for cross-lingual document and sentence retrieval tasks across a large number of language pairs. In contrast to supervised language understanding, our results indicate that for unsupervised document-level CLIR -- a setup with no relevance judgments for IR-specific fine-tuning -- pretrained encoders fail to significantly outperform models based on CLWEs. For sentence-level CLIR, we demonstrate that state-of-the-art performance can be achieved.

However, the peak performance is not met using the general-purpose multilingual text encoders `off-the-shelf', but rather relying on their variants that have been further specialized for sentence understanding tasks.

Open the resolved locator · 10.7801/361

Metadata licence: OpenAlex metadata (CC0)

Registry
OpenAlex DOI index + API
Fetched
2026-11-19 22:35 UTC
Cache state
not cached yet (bulk-index+openalex)
Locator
https://madata.bib.uni-mannheim.de/361
Metadata licence
OpenAlex metadata (CC0)
Scope
Metadata as returned by the resolver; abstracts are never generated here.