-
NeurIPS 2022 Workshop on Trustworthy and Socially Responsible Machine Learning (TSRML)2022The domain of joint vision-language understanding, especially in the context of reasoning in Visual Question Answering (VQA) models, has garnered significant attention in the recent past. While most of the existing VQA models focus on improving the accuracy of VQA, the way models arrive at an answer is oftentimes a black box. As a step towards making the VQA task more explainable and interpretable, our
-
NeurIPS 2022 Workshop on Trustworthy and Socially Responsible Machine Learning (TSRML)2022We propose KNN-Kmeans MT, a sample efficient algorithm that improves retrieval based augmentation performance in low resource settings by adding an additional K-means filtering layer after the KNN step. KNN-Kmeans MT like its predecessor retrieval augmented machine translation approaches (Khandelwal et al. [2020]) doesn’t require any additional training and outperforms the existing methods in low resource
-
EMNLP 20222022Multi-modality support has become an integral part of creating a seamless user experience with modern voice assistants with smart displays. Users refer to images, video thumbnails, or the accompanying text descriptions on the screen through voice communication with AI powered devices. This raises the need to either augment existing commercial voice only dialogue systems with state-of-the-art multimodal
-
NeurIPS 2022 Workshop on Efficient Natural Language and Speech Processing (ENLSP), ICASSP 20232022Transformer-based models demonstrate state of the art results on several natural language understanding tasks. However, their deployment comes at the cost of increased footprint and inference latency, limiting their adoption to real-time applications. Early exit strategies are designed to speed-up the inference by routing out a subset of samples at the earlier layers of the model. Exiting early causes losing
-
EMNLP 20222022Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work. The compatibility, often facilitated through leaderboards, thus leads to outdated but standardized evaluation practices. We pose that the standardization is taking place in the wrong spot. Evaluation infrastructure should enable researchers to use the latest methods
Related content
-
July 10, 2023Familiar topics such as question answering and natural-language understanding remain well represented, but a new concentration on language modeling and multimodal models reflect the spread of generative AI. -
July 9, 2023Finding that 70% of attention heads and 20% of feed-forward networks can be excised with minimal effect on in-context learning suggests that large language models are undertrained.
-
July 7, 2023Amazon’s Yang Liu, general chair of this year’s meeting of the Association for Computational Linguistics, on the road ahead for LLMs.
-
July 6, 2023The program exposes students to computer science as they create their own Alexa skills.
-
USCJuly 5, 2023Amazon Research Award recipient Shrikanth Narayanan is on a mission to make inclusive human-AI conversational experiences.
-
July 3, 2023With little training data and no mapping of speech to phonemes, Amazon researchers used voice conversion to generate Irish-accented training data in Alexa’s own voice.
