Related papers: Unsupervised Multilingual Alignment using Wasserst…
Multilingual Word Embeddings (MWEs) represent words from multiple languages in a single distributional vector space. Unsupervised MWE (UMWE) methods acquire multilingual embeddings without cross-lingual supervision, which is a significant…
How to achieve neural machine translation with limited parallel data? Existing techniques often rely on large-scale monolingual corpora, which is impractical for some low-resource languages. In this paper, we turn to connect several…
Existing models of multilingual sentence embeddings require large parallel data resources which are not available for low-resource languages. We propose a novel unsupervised method to derive multilingual sentence embeddings relying only on…
Multilingual models have been widely used for cross-lingual transfer to low-resource languages. However, the performance on these languages is hindered by their underrepresentation in the pretraining data. To alleviate this problem, we…
Word alignments identify translational correspondences between words in a parallel sentence pair and is used, for instance, to learn bilingual dictionaries, to train statistical machine translation systems , or to perform quality…
Multilingual pre-trained models have achieved remarkable performance on cross-lingual transfer learning. Some multilingual models such as mBERT, have been pre-trained on unlabeled corpora, therefore the embeddings of different languages in…
In many applications in statistics and machine learning, the availability of data samples from multiple possibly heterogeneous sources has become increasingly prevalent. On the other hand, in distributionally robust optimization, we seek…
Recent work indicated that pretrained language models (PLMs) such as BERT and RoBERTa can be transformed into effective sentence and word encoders even via simple self-supervised techniques. Inspired by this line of work, in this paper we…
Foundation models have demonstrated remarkable performance across modalities such as language and vision. However, model reuse across distinct modalities (e.g., text and vision) remains limited due to the difficulty of aligning internal…
Multilingual semantic search is the task of retrieving relevant contents to a query expressed in different language combinations. This requires a better semantic understanding of the user's intent and its contextual meaning. Multilingual…
We present an interactive machine translation (MT) system designed for users who are not proficient in the target language. It aims to improve trustworthiness and explainability by identifying potentially mistranslated words and allowing…
A key concern with the concept of "alignment" is the implicit question of "alignment to what?". AI systems are increasingly used across the world, yet safety alignment is often focused on homogeneous monolingual settings. Additionally,…
Efficiently aggregating data from different sources is a challenging problem, particularly when samples from each source are distributed differently. These differences can be inherent to the inference task or present for other reasons:…
Wasserstein barycenter, built on the theory of optimal transport, provides a powerful framework to aggregate probability distributions, and it has increasingly attracted great attention within the machine learning community. However, it…
Large language models (LLMs) have exhibited impressive multilingual reasoning capabilities, driven by extensive multilingual pre-training corpora and instruction fine-tuning data. However, a performance gap exists between high- and…
We introduce Joint Multidimensional Scaling, a novel approach for unsupervised manifold alignment, which maps datasets from two different domains, without any known correspondences between data instances across the datasets, to a common…
Cross-lingual semantic textual similarity systems estimate the degree of the meaning similarity between two sentences, each in a different language. State-of-the-art algorithms usually employ machine translation and combine vast amount of…
We present a stochastic algorithm to compute the barycenter of a set of probability distributions under the Wasserstein metric from optimal transport. Unlike previous approaches, our method extends to continuous input distributions and…
Subword modeling for zero-resource languages aims to learn low-level representations of speech audio without using transcriptions or other resources from the target language (such as text corpora or pronunciation dictionaries). A good…
We propose a hybrid resampling method to approximate finitely supported Wasserstein barycenters on large-scale datasets, which can be combined with any exact solver. Nonasymptotic bounds on the expected error of the objective value as well…