相关论文: A New Data Normalization Method to Improve Dialogu…

The ability of a dialog system to express consistent language style during conversations has a direct, positive impact on its usability and on user satisfaction. Although previous studies have demonstrated that style transfer is feasible…

Large language models (LLMs) have shown remarkable performance across various sentence-based linguistic phenomena, yet their ability to capture cross-sentence paradigmatic patterns, such as verb alternations, remains underexplored. In this…

Nowadays, data augmentation through synthetic data has been widely used in the field of Grammatical Error Correction (GEC) to alleviate the problem of data scarcity. However, these synthetic data are mainly used in the pre-training phase…

Decision-making is often dependent on uncertain data, e.g. data associated with confidence scores or probabilities. We present a comparison of different information presentations for uncertain data and, for the first time, measure their…

Dialogue summarization helps readers capture salient information from long conversations in meetings, interviews, and TV series. However, real-world dialogues pose a great challenge to current summarization models, as the dialogue length…

For many new application domains for data-to-text generation, the main obstacle in training neural models consists of a lack of training data. While usually large numbers of instances are available on the data side, often only very few text…

This study aimed to investigate the influence of the presence of informal language, such as emoticons and slang, on the performance of sentiment analysis models applied to social media text. A convolutional neural network (CNN) model was…

Dialogue generation has been successfully learned from scratch by neural networks, but tends to produce the same general response, e.g., "what are you talking about?", in many conversations. To reduce this homogeneity, external knowledge…

QA models based on pretrained language mod-els have achieved remarkable performance on various benchmark datasets.However, QA models do not generalize well to unseen data that falls outside the training distribution, due to distributional…

Machine learning techniques have conquered many different tasks in speech and natural language processing, such as speech recognition, information extraction, text and speech generation, and human machine interaction using natural language…

To effectively use large language models (LLMs) for real-world queries, it is imperative that they generalize to the long-tail distribution, i.e. rare examples where models exhibit low confidence. In this work, we take the first step…

We propose a method for natural language generation, choosing the most representative output rather than the most likely output. By viewing the language generation process from the voting theory perspective, we define representativeness…

Speech enhancement using neural networks is recently receiving large attention in research and being integrated in commercial devices and applications. In this work, we investigate data augmentation techniques for supervised deep…

Dialogue is an essential part of human communication and cooperation. Existing research mainly focuses on short dialogue scenarios in a one-on-one fashion. However, multi-person interactions in the real world, such as meetings or…

Large language models (LLMs) demonstrate remarkable text comprehension and generation capabilities but often lack the ability to utilize up-to-date or domain-specific knowledge not included in their training data. To address this gap, we…

The success of deep learning depends on large-scale and well-curated training data, while data in real-world applications are commonly long-tailed and noisy. Many methods have been proposed to deal with long-tailed data or noisy data, while…

Balancing training on long-tail data distributions remains a long-standing challenge in deep learning. While methods such as re-weighting and re-sampling help alleviate the imbalance issue, limited sample diversity continues to hinder…

Natural language understanding systems struggle with low-resource languages, including many dialects of high-resource ones. Dialect-to-standard normalization attempts to tackle this issue by transforming dialectal text so that it can be…

In recent years, the availability of large-scale annotated datasets, such as the Stanford Natural Language Inference and the Multi-Genre Natural Language Inference, coupled with the advent of pre-trained language models, has significantly…

Data augmentation is an essential technique in natural language processing (NLP) for enriching training datasets by generating diverse samples. This process is crucial for improving the robustness and generalization capabilities of NLP…