Related papers: C2C-GenDA: Cluster-to-Cluster Generation for Data …

We examine whether neural natural language processing (NLP) systems reflect historical biases in training data. We define a general benchmark to quantify gender bias in a variety of neural NLP tasks. Our empirical evaluation with…

Continual learning, involving sequential training on diverse tasks, often faces catastrophic forgetting. While knowledge distillation-based approaches exhibit notable success in preventing forgetting, we pinpoint a limitation in their…

Few-shot question answering (QA) aims at precisely discovering answers to a set of questions from context passages while only a few training samples are available. Although existing studies have made some progress and can usually achieve…

Named Entity Recognition (NER) is a critical task in natural language processing, yet it remains particularly challenging for discontinuous entities. The primary difficulty lies in text segmentation, as traditional methods often missegment…

Recent researches on unsupervised domain adaptation (UDA) have demonstrated that end-to-end ensemble learning frameworks serve as a compelling option for UDA tasks. Nevertheless, these end-to-end ensemble learning methods often lack…

Online Class-Incremental (OCI) learning has sparked new approaches to expand the previously trained model knowledge from sequentially arriving data streams with new classes. Unfortunately, OCI learning can suffer from catastrophic…

Commonsense capabilities of pre-trained language models dramatically improve with scale, leading many to believe that scale is the only winning recipe. But is it? Here, we investigate an alternative that a priori seems impossible: can…

Cross-lingual representation learning transfers knowledge from resource-rich data to resource-scarce ones to improve the semantic understanding abilities of different languages. However, previous works rely on shallow unsupervised data…

Linear Transformers have gained attention as efficient alternatives to standard Transformers, but their performance in retrieval and long-context tasks has been limited. To address these limitations, recent work has explored two distinct…

The success of speech assistants requires precise recognition of a number of entities on particular contexts. A common solution is to train a class-based n-gram language model and then expand the classes into specific words or phrases.…

Advancements in conversational systems have revolutionized information access, surpassing the limitations of single queries. However, developing dialogue systems requires a large amount of training data, which is a challenge in low-resource…

The ability to jointly learn from multiple modalities, such as text, audio, and visual data, is a defining feature of intelligent systems. While there have been promising advances in designing neural networks to harness multimodal data, the…

The natural language generation domain has witnessed great success thanks to Transformer models. Although they have achieved state-of-the-art generative quality, they often neglect generative diversity. Prior attempts to tackle this issue…

Continual learning requires balancing plasticity and stability while mitigating catastrophic forgetting. Inspired by human dreaming as a mechanism for internal simulation and knowledge restructuring, we introduce Dream2Learn (D2L), a…

(Natural Language Processing) NLP techniques such as text classification and topic discovery are very useful in many application areas including information retrieval, knowledge discovery, policy formulation, and decision-making. However,…

Manually annotating fine-grained slot-value labels for task-oriented dialogue (ToD) systems is an expensive and time-consuming endeavour. This motivates research into slot-filling methods that operate with limited amounts of labelled data.…

To investigate the role of linguistic knowledge in data augmentation (DA) for Natural Language Processing (NLP), we designed two adapted DA programs and applied them to LCQMC (a Large-scale Chinese Question Matching Corpus) for a binary…

Despite the impressive capabilities of large language models (LLMs), their performance on information extraction tasks is still not entirely satisfactory. However, their remarkable rewriting capabilities and extensive world knowledge offer…

Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…

A common and effective means for improving language model capabilities involves finetuning a ``student'' language model's parameters on generations from a more proficient ``teacher'' model. Termed ``synthetic data'', these generations are…