Gemini Sports Analytics Uses Machine Learning to Help Sports Teams Make … cloud computing and DataRobot's artificial intelligence, Gemini adds a …

The Institute for Augmented Intelligence in Medicine has established the … will develop comprehensive AI and machine learning (ML) models, …

AWS has unveiled a host of enhancements for Amazon SageMaker, its end-to-end machine learning offering.

The scientists looked at their glucose measurements over time and developed machine learning models to see if those values could be used to determine …

This machine-learning capability is available at the preview stage via an Access Reviews feature for users of the Azure Identity Governance service, …

The gap between human creativity and artificial intelligence seems to be narrowing.

Agencies and marketing departments have long used machine learning algorithms to sift through data, spot trends and steer creative campaigns.

Amazon Web Services Machine Learning University launched a free program on Nov. 30 that will teach database, artificial intelligence and machine …

Multi-modal named entity recognition (NER) and relation extraction (RE) aim to leverage relevant image information to improve the performance of NER and RE. Most existing efforts largely focused on directly extracting potentially useful information from images (such as pixel-level features, identified objects, and associated captions). However, such extraction processes may not be knowledge aware, resulting in information that may not be highly relevant. In this paper, we propose a novel Multi-modal Retrieval based framework (MoRe). MoRe contains a text retrieval module and an image-based retrieval module, which retrieve related knowledge of the input text and image in the knowledge corpus respectively. Next, the retrieval results are sent to the textual and visual models respectively for predictions. Finally, a Mixture of Experts (MoE) module combines the predictions from the two models to make the final decision. Our experiments show that both our textual model and visual model can achieve state-of-the-art performance on four multi-modal NER datasets and one multi-modal RE dataset. With MoE, the model performance can be further improved and our analysis demonstrates the benefits of integrating both textual and visual cues for such tasks.

In this work we propose a novel token-based training strategy that improves Transformer-Transducer (T-T) based speaker change detection (SCD) performance. The conventional T-T based SCD model loss optimizes all output tokens equally. Due to the sparsity of the speaker changes in the training data, the conventional T-T based SCD model loss leads to sub-optimal detection accuracy. To mitigate this issue, we use a customized edit-distance algorithm to estimate the token-level SCD false accept (FA) and false reject (FR) rates during training and optimize model parameters to minimize a weighted combination of the FA and FR, focusing the model on accurately predicting speaker changes. We also propose a set of evaluation metrics that align better with commercial use cases. Experiments on a group of challenging real-world datasets show that the proposed training method can significantly improve the overall performance of the SCD model with the same number of parameters.