Related papers: ColBERT-XM: A Modular Multi-Vector Representation …

Multi-modal pretraining for learning high-level multi-modal representation is a further step towards deep learning and artificial intelligence. In this work, we propose a novel model, namely InterBERT (BERT for Interaction), which is the…

Visual target navigation in unknown environments is a crucial problem in robotics. Despite extensive investigation of classical and learning-based approaches in the past, robots lack common-sense knowledge about household objects and…

Neural 'dense' retrieval models are state of the art for many datasets, however these models often exhibit limited domain transfer ability. Existing approaches to adaptation are unwieldy, such as requiring explicit supervision, complex…

Transfer learning based on pretraining language models on a large amount of raw data has become a new norm to reach state-of-the-art performance in NLP. Still, it remains unclear how this approach should be applied for unseen languages that…

We present a multilingual bag-of-entities model that effectively boosts the performance of zero-shot cross-lingual text classification by extending a multilingual pre-trained language model (e.g., M-BERT). It leverages the multilingual…

We propose procedures for evaluating and strengthening contextual embedding alignment and show that they are useful in analyzing and improving multilingual BERT. In particular, after our proposed alignment procedure, BERT exhibits…

Massively multilingual models are promising for transfer learning across tasks and languages. However, existing methods are unable to fully leverage training data when it is available in different task-language combinations. To exploit such…

Multilingual large language models (MLLMs), trained on multilingual balanced data, demonstrate better zero-shot learning performance in non-English languages compared to large language models trained on English-dominant data. However, the…

Recently, neural machine translation (NMT) has been extended to multilinguality, that is to handle more than one translation direction with a single system. Multilingual NMT showed competitive performance against pure bilingual systems.…

Large-scale vision-language models (VLMs) have shown a strong zero-shot generalization capability on unseen-domain data. However, adapting pre-trained VLMs to a sequence of downstream tasks often leads to the forgetting of previously…

Massively multilingual Transformers (MMTs), such as mBERT and XLM-R, are widely used for cross-lingual transfer learning. While these are pretrained to represent hundreds of languages, end users of NLP systems are often interested only in…

Aligning language models (LMs) based on human-annotated preference data is a crucial step in obtaining practical and performant LM-based systems. However, multilingual human preference data are difficult to obtain at scale, making it…

The recent mainstream adoption of large language model (LLM) technology is enabling novel applications in the form of chatbots and virtual assistants across many domains. With the aim of grounding LLMs in trusted domains and avoiding the…

Neural Machine Translation (NMT) approaches employing monolingual data are showing steady improvements in resource rich conditions. However, evaluations using real-world low-resource languages still result in unsatisfactory performance.…

We present a new zero-shot dense retrieval (ZeroDR) method, COCO-DR, to improve the generalization ability of dense retrieval by combating the distribution shifts between source training tasks and target scenarios. To mitigate the impact of…

This paper shows how diffusion language models (DLMs) can be used as effective and efficient retrievers. Existing DLM-based retrievers (e.g., DiffEmbed) follow BERT-style encoding, representing each query or passage as a single mean-pooled…

Effective cross-modal retrieval is essential for applications like information retrieval and recommendation systems, particularly in specialized domains such as manufacturing, where product information often consists of visual samples…

The recently proposed massively multilingual neural machine translation (NMT) system has been shown to be capable of translating over 100 languages to and from English within a single model. Its improved translation performance on low…

Conversational search requires accurate interpretation of user intent from complex multi-turn contexts. This paper presents ChatRetriever, which inherits the strong generalization capability of large language models to robustly represent…

Utilizing large language models (LLMs) for zero-shot document ranking is done in one of two ways: (1) prompt-based re-ranking methods, which require no further training but are only feasible for re-ranking a handful of candidate documents…