Related papers: Homepage2Vec: Language-Agnostic Website Embedding …
Hate speech detection is a challenging problem with most of the datasets available in only one language: English. In this paper, we conduct a large scale analysis of multilingual hate speech in 9 languages from 16 different sources. We…
We introduce the Massive Audio Embedding Benchmark (MAEB), a large-scale benchmark covering 30 tasks across speech, music, environmental sounds, and cross-modal audio-text reasoning in 100+ languages. We evaluate 50+ models and find that no…
Malware classification is an important and challenging problem in information security. Modern malware classification techniques rely on machine learning models that can be trained on features such as opcode sequences, API calls, and byte…
Existing approaches to automatic VerbNet-style verb classification are heavily dependent on feature engineering and therefore limited to languages with mature NLP pipelines. In this work, we propose a novel cross-lingual transfer method for…
Referring Expression Comprehension (REC) requires models to localize objects in images based on natural language descriptions. Research on the area remains predominantly English-centric, despite increasing global deployment demands. This…
Recent multilingual named entity recognition (NER) work has shown that large language models (LLMs) can provide effective synthetic supervision, yet such datasets have mostly appeared as by-products of broader experiments rather than as…
We introduce the multilingual Granite Embedding R2 models, a family of encoder-based embedding models for enterprise-scale dense retrieval across 200+ languages. Extending our English-focused R2 release, these models add enhanced support…
PubMed is the biggest and most used bibliographic database worldwide, hosting more than 26M biomedical publications. One of its useful features is the "similar articles" section, allowing the end-user to find scientific articles linked to…
The World Wide Web is not only one of the most important platforms of communication and information at present, but also an area of growing interest for scientific research. This motivates a lot of work and projects that require large…
Making an informed choice of pre-trained language model (LM) is critical for performance, yet environmentally costly, and as such widely underexplored. The field of Computer Vision has begun to tackle encoder ranking, with promising forays…
Large multimodal models trained on natural documents, which interleave images and text, outperform models trained on image-text pairs on various multimodal benchmarks. However, the datasets used to train these models have not been released,…
We propose emotion2vec, a universal speech emotion representation model. emotion2vec is pre-trained on open-source unlabeled emotion data through self-supervised online distillation, combining utterance-level loss and frame-level loss…
The evaluation of English text embeddings has transitioned from evaluating a handful of datasets to broad coverage across many tasks through benchmarks such as MTEB. However, this is not the case for multilingual text embeddings due to a…
Most work in text classification and Natural Language Processing (NLP) focuses on English or a handful of other languages that have text corpora of hundreds of millions of words. This is creating a new version of the digital divide: the…
Existing work on automated hate speech detection typically focuses on binary classification or on differentiating among a small set of categories. In this paper, we propose a novel method on a fine-grained hate speech classification task,…
English is the predominant language on the web, powering nearly half of the world's top ten million websites. Support for multilingual content is nevertheless growing, with many websites increasingly combining English with regional or…
Recent advances in large language models (LLMs) have shown significant promise, yet their evaluation raises concerns, particularly regarding data contamination due to the lack of access to proprietary training data. To address this issue,…
We present Tweet2Vec, a novel method for generating general-purpose vector representation of tweets. The model learns tweet embeddings using character-level CNN-LSTM encoder-decoder. We trained our model on 3 million, randomly selected…
Large text corpora are increasingly important for a wide variety of Natural Language Processing (NLP) tasks, and automatic language identification (LangID) is a core technology needed to collect such datasets in a multilingual context.…
This paper presents a novel approach for multi-lingual sentiment classification in short texts. This is a challenging task as the amount of training data in languages other than English is very limited. Previously proposed multi-lingual…