Related papers: Improving Neural Response Diversity with Frequency…

Medical images commonly exhibit multiple abnormalities. Predicting them requires multi-class classifiers whose training and desired reliable performance can be affected by a combination of factors, such as, dataset size, data source,…

Ensemble learning has gain attention in resent deep learning research as a way to further boost the accuracy and generalizability of deep neural network (DNN) models. Recent ensemble training method explores different training algorithms or…

In this paper, we propose a new loss function called generalized end-to-end (GE2E) loss, which makes the training of speaker verification models more efficient than our previous tuple-based end-to-end (TE2E) loss function. Unlike TE2E, the…

Exemplar-Free Class Incremental Learning (EFCIL) tackles the problem of training a model on a sequence of tasks without access to past data. Existing state-of-the-art methods represent classes as Gaussian distributions in the feature…

To obtain lower inference latency and less memory footprint of deep neural networks, model quantization has been widely employed in deep model deployment, by converting the floating points to low-precision integers. However, previous…

This work proposes a novel approach based on sequence-to-sequence (seq2seq) models for context-aware conversational systems. Exist- ing seq2seq models have been shown to be good for generating natural responses in a data-driven…

Large Language Models (LLMs) often produce inconsistent answers when faced with different phrasings of the same prompt. In this paper, we propose Flip-Flop Consistency ($F^2C$), an unsupervised training method that improves robustness to…

Click-through rate (CTR) prediction is an important task for the companies to recommend products which better match user preferences. User behavior in digital advertising is dynamic and changes over time. It is crucial for the companies to…

In recent times, sequence-to-sequence (seq2seq) models have gained a lot of popularity and provide state-of-the-art performance in a wide variety of tasks such as machine translation, headline generation, text summarization, speech to text…

Cross-domain recommendation (CDR) methods are proposed to tackle the sparsity problem in click through rate (CTR) estimation. Existing CDR methods directly transfer knowledge from the source domains to the target domain and ignore the…

Neural state-of-the-art sequence-to-sequence (seq2seq) models often do not perform well for small training sets. We address paradigm completion, the morphological task of, given a partial paradigm, generating all missing forms. We propose…

Multi-modal learning has made significant advances across diverse pattern recognition applications. However, handling missing modalities, especially under imbalanced missing rates, remains a major challenge. This imbalance triggers a…

Image restoration, which aims to recover high-quality images from their corrupted counterparts, often faces the challenge of being an ill-posed problem that allows multiple solutions for a single input. However, most deep learning based…

Multi-horizon probabilistic time series forecasting has wide applicability to real-world tasks such as demand forecasting. Recent work in neural time-series forecasting mainly focus on the use of Seq2Seq architectures. For example,…

Contrastive representation learning has proven to be an effective self-supervised learning method. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as positives that should be…

Generating diverse, interesting responses to chitchat conversations is a problem for neural conversational agents. This paper makes two substantial contributions to improving diversity in dialogue generation. First, we propose a novel…

Recently, diffusion models have emerged as a new paradigm for generative models. Despite the success in domains using continuous signals such as vision and audio, adapting diffusion models to natural language is under-explored due to the…

Current sequence-to-sequence models are trained to minimize cross-entropy and use softmax to compute the locally normalized probabilities over target sequences. While this setup has led to strong results in a variety of tasks, one…

Unsupervised style transfer aims to change the style of an input sentence while preserving its original content without using parallel training data. In current dominant approaches, owing to the lack of fine-grained control on the influence…

Current neural network-based conversational models lack diversity and generate boring responses to open-ended utterances. Priors such as persona, emotion, or topic provide additional information to dialog models to aid response generation,…