Related papers: RomeBERT: Robust Training of Multi-Exit BERT

Financial dialogue transcripts pose a unique challenge for sentence-level information extraction due to their informal structure, domain-specific vocabulary, and variable intent density. We introduce Fin-ExBERT, a lightweight and modular…

This paper demonstrates that multilingual denoising pre-training produces significant performance gains across a wide variety of machine translation (MT) tasks. We present mBART -- a sequence-to-sequence denoising auto-encoder pre-trained…

In this paper, we present our submission to Shared Metrics Task: RoBLEURT (Robustly Optimizing the training of BLEURT). After investigating the recent advances of trainable metrics, we conclude several aspects of vital importance to obtain…

As a simple technique to accelerate inference of large-scale pre-trained models, early exiting has gained much attention in the NLP community. It allows samples to exit early at internal classifiers without passing through the entire model.…

With the rapid development of artificial intelligence, conversational bots have became prevalent in mainstream E-commerce platforms, which can provide convenient customer service timely. To satisfy the user, the conversational bots need to…

Recently, the bidirectional encoder representations from transformers (BERT) model has attracted much attention in the field of natural language processing, owing to its high performance in language understanding-related tasks. The BERT…

Pre-trained language models such as BERT have exhibited remarkable performances in many tasks in natural language understanding (NLU). The tokens in the models are usually fine-grained in the sense that for languages like English they are…

Recent innovations in architecture, pre-training, and fine-tuning have led to the remarkable in-context learning and reasoning abilities of large auto-regressive language models such as LLaMA and DeepSeek. In contrast, encoders like BERT…

Time is an important aspect of documents and is used in a range of NLP and IR tasks. In this work, we investigate methods for incorporating temporal information during pre-training to further improve the performance on time-related tasks.…

Deep learning-based language models pretrained on large unannotated text corpora have been demonstrated to allow efficient transfer learning for natural language processing, with recent approaches such as the transformer-based BERT model…

In natural language processing, it has been observed recently that generalization could be greatly improved by finetuning a large-scale language model pretrained on a large unlabeled corpus. Despite its recent success and wide adoption,…

Recent advancements in dialogue response selection (DRS) are based on the \textit{task-adaptive pre-training (TAP)} approach, by first initializing their model with BERT~\cite{devlin-etal-2019-bert}, and adapt to dialogue data with…

Large pre-trained language models have recently gained significant traction due to their improved performance on various down-stream tasks like text classification and question answering, requiring only few epochs of fine-tuning. However,…

The large pre-trained BERT has achieved remarkable performance on Natural Language Processing (NLP) tasks but is also computation and memory expensive. As one of the powerful compression approaches, binarization extremely reduces the…

In this paper, we show that Multilingual BERT (M-BERT), released by Devlin et al. (2018) as a single language model pre-trained from monolingual corpora in 104 languages, is surprisingly good at zero-shot cross-lingual model transfer, in…

Transfer learning in natural language processing (NLP), as realized using models like BERT (Bi-directional Encoder Representation from Transformer), has significantly improved language representation with models that can tackle challenging…

Pre-trained language models like BERT have achieved great success in a wide variety of NLP tasks, while the superior performance comes with high demand in computational resources, which hinders the application in low-latency IR systems. We…

The recently proposed BERT has shown great power on a variety of natural language understanding tasks, such as text classification, reading comprehension, etc. However, how to effectively apply BERT to neural machine translation (NMT) lacks…

Encoder-decoder transformer models have achieved great success on various vision-language (VL) tasks, but they suffer from high inference latency. Typically, the decoder takes up most of the latency because of the auto-regressive decoding.…

Prompting has shown impressive success in enabling large pretrained language models (LMs) to perform diverse NLP tasks, especially when only few downstream data are available. Automatically finding the optimal prompt for each task, however,…