-
NeurIPS 2020 Workshop on Machine Learning for Creativity and Design 4.02020The conventional approach to symbolic music generation uses the Transformer, an autoregressive model that is commonly trained by minimizing the negative log-likelihood (NLL) of the observed sequence. The quality of samples from these models tends to degrade significantly for long sequences, a phenomenon attributed to exposure bias. However, we are able to detect these failures with classifiers trained to
-
COLING 20202020End-to-end neural data-to-text (D2T) generation has recently emerged as an alternative to pipeline-based architectures. However, it has faced challenges generalizing to new domains and generating semantically consistent text. In this work, we present DATATUNER, a neural, end-to-end data-to-text generation system that makes minimal assumptions about the data representation and target domain. We take a two-stage
-
SLT 20212020Pre-trained language models have demonstrated outstanding performance in many NLP tasks recently. However, their social intelligence, which requires commonsense reasoning about the current situation and mental states of others, is still developing. Towards improving language models’ social intelligence, in this study we focus on the Social IQA dataset, a task requiring social and emotional commonsense reasoning
-
COLING 20202020With the recent explosion in popularity of voice assistant devices, there is a growing interest in making them available to user populations in additional countries and languages. However, to provide the highest accuracy and best performance for specific user populations, most existing voice assistant models are developed individually for each region or language, which requires linear investment of effort
-
ICON 20202020Data sparsity is one of the key challenges associated with model development in natural language understanding (NLU) for conversational agents. The challenge is made more complex by the demand for high quality annotated utterances commonly required for supervised learning, usually resulting in weeks of manual labor and high cost. In this paper, we present our results on boosting NLU model performance through
Related content
-
April 27, 2026A new framework provides a statistical method for estimating the likelihood of catastrophic failures in large language models in adversarial conversations.
-
April 15, 2026A single, optimized LLM unifies what previously required multiple models and can serve as a reasoning partner for medical chemists.
-
April 1, 2026Low-rank adaptation, data augmentation, and chain-of-thought reasoning are among the techniques enabling accent-free polyglot outputs, improved expressiveness, and reliable synthesis.
-
March 16, 2026By learning the idiosyncrasies of accumulated layers of legacy systems, AI agents can preserve institutional knowledge and provide a unified interface to a range of services.
-
March 11, 2026As AI agents become more autonomous, the key challenge isn't what they can do; it's how to design the human side of the equation.
-
January 13, 2026Leveraging existing environment simulators and reward functions based on verifiable ground truth boosts task success rate, even with small models and small training datasets.