Related papers: FOCUS: Effective Embedding Initialization for Mono…

Recent advancements in large language models (LLMs) based embedding models have established new state-of-the-art benchmarks for text embedding tasks, particularly in dense vector-based retrieval. However, these models predominantly focus on…

Multimodal Large Language Models (MLLMs) have shown immense promise in universal multimodal retrieval, which aims to find relevant items of various modalities for a given query. But their practical application is often hindered by the…

The advent of vision-language pre-training techniques enhanced substantial progress in the development of models for image captioning. However, these models frequently produce generic captions and may omit semantically important image…

Multimodal large language models (MLLMs) represent images and video frames as visual tokens. Scaling from single images to hour-long videos, however, inflates the token budget far beyond practical limits. Popular pipelines therefore either…

Language models (LMs) are bound to their tokenizer, which maps raw text to a sequence of vocabulary items (tokens). This restricts their flexibility: for example, LMs trained primarily on English may still perform well in other natural and…

Recent multilingual pretrained language models (mPLMs) often avoid using language embeddings -- learnable vectors assigned to individual languages. However, this places a significant burden on token representations to encode all…

As Large Language Models (LLMs) scale, data curation has shifted from maximizing volume to optimizing the signal-to-noise ratio by performing quality filtering. However, for many languages, native high quality data is insufficient to train…

Multilingual semantic parsing is a cost-effective method that allows a single model to understand different languages. However, researchers face a great imbalance of availability of training data, with English being resource rich, and other…

We propose an unsupervised method to obtain cross-lingual embeddings without any parallel data or pre-trained word embeddings. The proposed model, which we call multilingual neural language models, takes sentences of multiple languages as…

We introduce a novel method for multilingual transfer that utilizes deep contextual embeddings, pretrained in an unsupervised fashion. While contextual embeddings have been shown to yield richer representations of meaning compared to their…

Topic modeling is traditionally applied to word counts without accounting for the context in which words appear. Recent advancements in large language models (LLMs) offer contextualized word embeddings, which capture deeper meaning and…

A recent research line has obtained strong results on bilingual lexicon induction by aligning independently trained word embeddings in two languages and using the resulting cross-lingual embeddings to induce word translation pairs through…

Multilingual machine translation enables a single model to translate between different languages. Most existing multilingual machine translation systems adopt a randomly initialized Transformer backbone. In this work, inspired by the recent…

We present a family of neural-network--inspired models for computing continuous word representations, specifically designed to exploit both monolingual and multilingual text. This framework allows us to perform unsupervised training of…

Nowadays, training end-to-end neural models for spoken language translation (SLT) still has to confront with extreme data scarcity conditions. The existing SLT parallel corpora are indeed orders of magnitude smaller than those available for…

We present a language independent, unsupervised approach for transforming word embeddings from source language to target language using a transformation matrix. Our model handles the problem of data scarcity which is faced by many languages…

Transformer has demonstrated its great power to learn contextual word representations for multiple languages in a single model. To process multilingual sentences in the model, a learnable vector is usually assigned to each language, which…

Cross-lingual word embeddings aim to bridge the gap between high-resource and low-resource languages by allowing to learn multilingual word representations even without using any direct bilingual signal. The lion's share of the methods are…

We propose Masker, an unsupervised text-editing method for style transfer. To tackle cases when no parallel source-target pairs are available, we train masked language models (MLMs) for both the source and the target domain. Then we find…

Biological multimodal large language models (MLLMs) have emerged as powerful foundation models for scientific discovery. However, existing models are specialized to a single modality, limiting their ability to solve inherently cross-modal…