ALEE: Any-Language Evaluation of Embeddings via English-Centric Minimal Pairs

• URL: http://arxiv.org/abs/2607.00171v1
• Date: Tue, 30 Jun 2026 20:45:17 GMT
• Title: ALEE: Any-Language Evaluation of Embeddings via English-Centric Minimal Pairs
• Abstract summary: ALEE is a framework that extends Sentence Smith to the cross-lingual and paragraph level.<n>We conduct a large-scale empirical study across a diverse set of embedding models and 275+ languages.<n>On ALEE, performance varies substantially across languages, text lengths, and linguistic phenomena.
• Score: 31.61859333702968
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text embeddings are standard for semantic similarity tasks, yet their evaluation remains an open challenge. Current benchmarks are static, cover only a limited set of languages, are often domain-specific, susceptible to overfitting, and poorly representative of low-resource languages. To address these limitations, we introduce ALEE, a framework that extends Sentence Smith (Li et al., 2025) to the cross-lingual and paragraph level. ALEE uses Abstract Meaning Representations (AMR) to generate English minimal pairs with controlled, fine-grained semantic shifts, which are paired with translations in target languages. This approach enables targeted diagnostics for models in any language with English parallel data. We conduct a large-scale empirical study across a diverse set of embedding models and 275+ languages spanning three parallel datasets. On ALEE, performance varies substantially across languages, text lengths, and linguistic phenomena, exposing persistent gaps in cross-lingual semantic representation that track language prevalence in training resources and subword tokenization. We release ALEE at https://github.com/Andrian0s/any-lang-embed-eval

Related papers

• What Language is This? Ask Your Tokenizer [32.28976119949841]
  Language Identification (LID) is an important component of many multilingual natural language processing pipelines.<n>We introduce UniLID, a simple and efficient LID method based on the UnigramLM tokenization algorithm.<n>Our formulation is data- and compute-efficient, supports incremental addition of new languages without retraining existing models.
  arXiv  Detail & Related papers  (2026-02-19T18:58:39Z)
• How Good is BLI as an Alignment Measure: A Study in Word Embedding Paradigm [1.4712349476860904]
  We explore the strengths and limitations of BLI as a measure to evaluate the degree of alignment of two embedding spaces.<n>We evaluate how well traditional embedding alignment techniques, novel multilingual models, and combined alignment techniques perform BLI tasks.<n>We propose a novel stem-based BLI approach to evaluate two aligned embedding spaces that take into account the inflected nature of languages.
  arXiv  Detail & Related papers  (2025-11-17T06:41:41Z)
• Cross-Lingual Word Alignment for ASEAN Languages with Contrastive Learning [5.5119571570277826]
  Cross-lingual word alignment plays a crucial role in various natural language processing tasks. Recent study proposes a BiLSTM-based encoder-decoder model that outperforms pre-trained language models in low-resource settings. We propose incorporating contrastive learning into the BiLSTM-based encoder-decoder framework.
  arXiv  Detail & Related papers  (2024-07-06T11:56:41Z)
• Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models [62.91524967852552]
  Large language models (LLMs) are typically multilingual due to pretraining on diverse multilingual corpora.<n>But can these models relate corresponding concepts across languages, i.e., be crosslingual?<n>This study evaluates state-of-the-art LLMs on inherently crosslingual tasks.
  arXiv  Detail & Related papers  (2024-06-23T15:15:17Z)
• Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning [98.60739735409243]
  Cross-lingual transfer of language models trained on high-resource languages like English has been widely studied for many NLP tasks. We introduce XSGD for cross-lingual alignment pretraining, a parallel and large-scale multilingual conversation dataset. To facilitate aligned cross-lingual representations, we develop an efficient prompt-tuning-based method for learning alignment prompts.
  arXiv  Detail & Related papers  (2023-04-03T18:46:01Z)
• EASE: Entity-Aware Contrastive Learning of Sentence Embedding [37.7055989762122]
  EASE is a novel method for learning sentence embeddings via contrastive learning between sentences and their related entities. We show that EASE exhibits competitive or better performance in English semantic textual similarity (STS) and short text clustering (STC) tasks.
  arXiv  Detail & Related papers  (2022-05-09T13:22:44Z)
• Exposing Cross-Lingual Lexical Knowledge from Multilingual Sentence Encoders [85.80950708769923]
  We probe multilingual language models for the amount of cross-lingual lexical knowledge stored in their parameters, and compare them against the original multilingual LMs. We also devise a novel method to expose this knowledge by additionally fine-tuning multilingual models. We report substantial gains on standard benchmarks.
  arXiv  Detail & Related papers  (2022-04-30T13:23:16Z)
• AM2iCo: Evaluating Word Meaning in Context across Low-ResourceLanguages with Adversarial Examples [51.048234591165155]
  We present AM2iCo, Adversarial and Multilingual Meaning in Context. It aims to faithfully assess the ability of state-of-the-art (SotA) representation models to understand the identity of word meaning in cross-lingual contexts. Results reveal that current SotA pretrained encoders substantially lag behind human performance.
  arXiv  Detail & Related papers  (2021-04-17T20:23:45Z)
• UNKs Everywhere: Adapting Multilingual Language Models to New Scripts [103.79021395138423]
  Massively multilingual language models such as multilingual BERT (mBERT) and XLM-R offer state-of-the-art cross-lingual transfer performance on a range of NLP tasks. Due to their limited capacity and large differences in pretraining data, there is a profound performance gap between resource-rich and resource-poor target languages. We propose novel data-efficient methods that enable quick and effective adaptation of pretrained multilingual models to such low-resource languages and unseen scripts.
  arXiv  Detail & Related papers  (2020-12-31T11:37:28Z)
• Learning Contextualised Cross-lingual Word Embeddings and Alignments for Extremely Low-Resource Languages Using Parallel Corpora [63.5286019659504]
  We propose a new approach for learning contextualised cross-lingual word embeddings based on a small parallel corpus. Our method obtains word embeddings via an LSTM encoder-decoder model that simultaneously translates and reconstructs an input sentence.
  arXiv  Detail & Related papers  (2020-10-27T22:24:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.