相关论文: Generate to Understand for Representation

Spoken language understanding (SLU) treats automatic speech recognition (ASR) and natural language understanding (NLU) as a unified task and usually suffers from data scarcity. We exploit an ASR and NLU joint training method based on meta…

State-of-the-art natural language understanding classification models follow two-stages: pre-training a large language model on an auxiliary task, and then fine-tuning the model on a task-specific labeled dataset using cross-entropy loss.…

Self-supervised pre-training, such as BERT, MASS and BART, has emerged as a powerful technique for natural language understanding and generation. Existing pre-training techniques employ autoencoding and/or autoregressive objectives to train…

Recent advances in natural language processing (NLP) can be largely attributed to the advent of pre-trained language models such as BERT and RoBERTa. While these models demonstrate remarkable performance on general datasets, they can…

Linguistic sequence labeling is a general modeling approach that encompasses a variety of problems, such as part-of-speech tagging and named entity recognition. Recent advances in neural networks (NNs) make it possible to build reliable…

Neural network based approaches to data-to-text natural language generation (NLG) have gained popularity in recent years, with the goal of generating a natural language prompt that accurately realizes an input meaning representation. To…

Vehicle make and model recognition (VMMR) is an important task in intelligent transportation systems, but existing approaches struggle to adapt to newly released models. Contrastive Language-Image Pretraining (CLIP) provides strong…

Vision-language pre-training (VLP) has attracted increasing attention recently. With a large amount of image-text pairs, VLP models trained with contrastive loss have achieved impressive performance in various tasks, especially the…

Word vectors and Language Models (LMs) pretrained on a large amount of unlabelled data can dramatically improve various Natural Language Processing (NLP) tasks. However, the measure and impact of similarity between pretraining data and…

Recently, pre-trained models have been the dominant paradigm in natural language processing. They achieved remarkable state-of-the-art performance across a wide range of related tasks, such as textual entailment, natural language inference,…

Language model pre-training has been shown to capture a surprising amount of world knowledge, crucial for NLP tasks such as question answering. However, this knowledge is stored implicitly in the parameters of a neural network, requiring…

Many natural language processing applications use language models to generate text. These models are typically trained to predict the next word in a sequence, given the previous words and some context such as an image. However, at test time…

Although Large Language Models (LLMs) exhibit remarkable adaptability across domains, these models often fall short in structured knowledge extraction tasks such as named entity recognition (NER). This paper explores an innovative,…

Iterative evaluation of LLMs during training is essential to ensure expected capability development, but can be time- and compute-intensive. While NLU tasks, where the model selects from fixed answer choices, are cheap to evaluate,…

Query rewriting (QR) is an increasingly important technique to reduce customer friction caused by errors in a spoken language understanding pipeline, where the errors originate from various sources such as speech recognition errors,…

While recent research on natural language inference has considerably benefited from large annotated datasets, the amount of inference-related knowledge (including commonsense) provided in the annotated data is still rather limited. There…

Recently, generative graph models have shown promising results in learning graph representations through self-supervised methods. However, most existing generative graph representation learning (GRL) approaches rely on random masking across…

The major paradigm of applying a pre-trained language model to downstream tasks is to fine-tune it on labeled task data, which often suffers instability and low performance when the labeled examples are scarce.~One way to alleviate this…

It is generally thought that transformer-based large language models benefit from pre-training by learning generic linguistic knowledge that can be focused on a specific task during fine-tuning. However, we propose that much of the benefit…

With the development of large language models (LLMs), zero-shot learning has attracted much attention for various NLP tasks. Different from prior works that generate training data with billion-scale natural language generation (NLG) models,…