相关论文: A Massively Multilingual Analysis of Cross-lingual…

Massively Multilingual Language Models (MMLMs) have recently gained popularity due to their surprising effectiveness in cross-lingual transfer. While there has been much work in evaluating these models for their performance on a variety of…

Vision-language models (VLM) align images and text in a shared representation space that is useful for retrieval and zero-shot transfer. Yet, this alignment can encode and amplify social stereotypes in subtle ways that are not obvious from…

Multilingual proficiency presents a significant challenge for large language models (LLMs). English-centric models are usually suboptimal in other languages, particularly those that are linguistically distant from English. This performance…

Scaling existing applications and solutions to multiple human languages has traditionally proven to be difficult, mainly due to the language-dependent nature of preprocessing and feature engineering techniques employed in traditional…

The notions of concreteness and imageability, traditionally important in psycholinguistics, are gaining significance in semantic-oriented natural language processing tasks. In this paper we investigate the predictability of these two…

Cross-lingual consistency should be considered to assess cross-lingual transferability, maintain the factuality of the model knowledge across languages, and preserve the parity of language model performance. We are thus interested in…

Multilingual BERT (mBERT), XLM-RoBERTa (XLMR) and other unsupervised multilingual encoders can effectively learn cross-lingual representation. Explicit alignment objectives based on bitexts like Europarl or MultiUN have been shown to…

Cross-lingual representation learning is an important step in making NLP scale to all the world's languages. Recent work on bilingual lexicon induction suggests that it is possible to learn cross-lingual representations of words based on…

Cross-lingual word embeddings are becoming increasingly important in multilingual NLP. Recently, it has been shown that these embeddings can be effectively learned by aligning two disjoint monolingual vector spaces through linear…

Recent multilingual pretrained language models (mPLMs) have been shown to encode strong language-specific signals, which are not explicitly provided during pretraining. It remains an open question whether it is feasible to employ mPLMs to…

Despite the promising results of current cross-lingual models for spoken language understanding systems, they still suffer from imperfect cross-lingual representation alignments between the source and target languages, which makes the…

We propose a novel scaling law for general-purpose decoder-only language models (LMs) trained on multilingual data, tackling the problem of balancing languages during multilingual pretraining. A primary challenge in studying multilingual…

Modeling relations between languages can offer understanding of language characteristics and uncover similarities and differences between languages. Automated methods applied to large textual corpora can be seen as opportunities for novel…

Typically, a linearly orthogonal transformation mapping is learned by aligning static type-level embeddings to build a shared semantic space. In view of the analysis that contextual embeddings contain richer semantic features, we…

Multilingual BERT (mBERT) has demonstrated considerable cross-lingual syntactic ability, whereby it enables effective zero-shot cross-lingual transfer of syntactic knowledge. The transfer is more successful between some languages, but it is…

Confidence calibration, the alignment of a model's predicted confidence with its actual accuracy, is crucial for the reliable deployment of Large Language Models (LLMs). However, this critical property remains largely under-explored in…

The effects of language mismatch impact speech anti-spoofing systems, while investigations and quantification of these effects remain limited. Existing anti-spoofing datasets are mainly in English, and the high cost of acquiring…

We consider the problem of aligning continuous word representations, learned in multiple languages, to a common space. It was recently shown that, in the case of two languages, it is possible to learn such a mapping without supervision.…

Most of the successful and predominant methods for bilingual lexicon induction (BLI) are mapping-based, where a linear mapping function is learned with the assumption that the word embedding spaces of different languages exhibit similar…

We present a clustering-based language model using word embeddings for text readability prediction. Presumably, an Euclidean semantic space hypothesis holds true for word embeddings whose training is done by observing word co-occurrences.…