相关论文: Improving Pre-Trained Multilingual Models with Voc…

We present a new approach for neural machine translation (NMT) using the morphological and grammatical decomposition of the words (factors) in the output side of the neural network. This architecture addresses two main problems occurring in…

Although pre-trained language models~(PLMs) have shown impressive performance by text-only self-supervised training, they are found lack of visual semantics or commonsense. Existing solutions often rely on explicit images for visual…

Recent advances in multimodal large language models (MLLMs) have demonstrated remarkable multi- and cross-modal integration capabilities. However, their potential for fine-grained emotion understanding remains systematically underexplored.…

Achieving universal translation between all human language pairs is the holy-grail of machine translation (MT) research. While recent progress in massively multilingual MT is one step closer to reaching this goal, it is becoming evident…

Pretraining on large-scale datasets can boost the performance of object detectors while the annotated datasets for object detection are hard to scale up due to the high labor cost. What we possess are numerous isolated filed-specific…

Scaling up the number of parameters of language models has proven to be an effective approach to improve performance. For dense models, increasing model size proportionally increases the model's computation footprint. In this work, we seek…

Language model pre-training has proven to be useful in learning universal language representations. As a state-of-the-art language model pre-training model, BERT (Bidirectional Encoder Representations from Transformers) has achieved amazing…

Recent progress in universal multilingual named entity recognition (NER) has been driven by advances in multilingual transformer models and task-specific architectures, loss functions, and training datasets. Despite substantial prior work,…

Recent studies have proposed different methods to improve multilingual word representations in contextualized settings including techniques that align between source and target embedding spaces. For contextualized embeddings, alignment…

Occlusion perception, a critical foundation for human-level spatial understanding, embodies the challenge of integrating visual recognition and reasoning. Though multimodal large language models (MLLMs) have demonstrated remarkable…

State-of-the-art unsupervised multilingual models (e.g., multilingual BERT) have been shown to generalize in a zero-shot cross-lingual setting. This generalization ability has been attributed to the use of a shared subword vocabulary and…

The performance of multilingual pretrained models is highly dependent on the availability of monolingual or parallel text present in a target language. Thus, the majority of the world's languages cannot benefit from recent progress in NLP…

Fine-tuned pre-trained language models can suffer from severe miscalibration for both in-distribution and out-of-distribution (OOD) data due to over-parameterization. To mitigate this issue, we propose a regularized fine-tuning method. Our…

The extensive memory footprint of language model (LM) fine-tuning poses a challenge for both researchers and practitioners. LMs use an embedding matrix to represent extensive vocabularies, forming a substantial proportion of the model…

Pre-training large-scale neural language models on raw texts has made a significant contribution to improving transfer learning in natural language processing (NLP). With the introduction of transformer-based language models, such as…

In recent years, vision-language models have made significant strides, excelling in tasks like optical character recognition and geometric problem-solving. However, several critical issues remain: 1) Proprietary models often lack…

The usage of more than one language in the same text is referred to as Code Mixed. It is evident that there is a growing degree of adaption of the use of code-mixed data, especially English with a regional language, on social media…

Deep neural language models such as BERT have enabled substantial recent advances in many natural language processing tasks. Due to the effort and computational cost involved in their pre-training, language-specific models are typically…

The Bag-of-Words (BoW) representation is well applied to recent state-of-the-art image retrieval works. Typically, multiple vocabularies are generated to correct quantization artifacts and improve recall. However, this routine is corrupted…

Despite the remarkable success of pre-trained language models (PLMs), they still face two challenges: First, large-scale PLMs are inefficient in terms of memory footprint and computation. Second, on the downstream tasks, PLMs tend to rely…