-
The transformer is a powerful data-modeling framework responsible for remarkable performance on a wide range of tasks. However, transformers are limited in terms of scalability as it is suboptimal and inefficient to process long-sequence data. To this purpose we introduce BLRP (Bidirectional Long-Range Parser), a novel and versatile attention mechanism designed to increase performance and efficiency on
-
EACL 20242024Users of AI-based virtual assistants and search systems encounter challenges in articulating their intents while seeking information on unfamiliar topics, possibly due to complexity of the user’s intent or the lack of meta-information on the topic. We posit that an iterative suggested question-answering (SQA) conversation can improve the trade-off between the satisfaction of the user’s intent while keeping
-
2024Vision-Language (VL) models have gained significant research focus, enabling remarkable advances in multimodal reasoning. These architectures typically comprise a vision encoder, a Large Language Model (LLM), and a projection module that aligns visual features with the LLM’s representation space. Despite their success, a critical limitation persists: the vision encoding process remains decoupled from user
-
2024Large Language models (LLMs) have demonstrated impressive in-context learning (ICL) capabilities, where a LLM makes predictions for a given test input together with a few input-output pairs (demonstrations). Nevertheless, the inclusion of demonstrations leads to a quadratic increase in the computational overhead of the self-attention mechanism. Existing solutions attempt to distill lengthy demonstrations
-
Information retrieval (IR) is a pivotal component in various applications. Recent advances in machine learning (ML) have enabled the integration of ML algorithms into IR, particularly in ranking systems. While there is a plethora of research on the robustness of ML-based ranking systems, these studies largely neglect commercial e-commerce systems and fail to establish a connection between real-world and
Related content
-
July 03, 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. -
June 26, 2023How phonetically blended results (PBR) help ensure customers find the content they were actually asking for.
-
June 09, 2023In a top-3% paper at ICASSP, Amazon researchers adapt graph-based label propagation to improve speech recognition on underrepresented pronunciations.
-
June 07, 2023Team earned $500,000 for its performance in a challenge focused on advancing next-generation virtual assistants that help humans complete real-world tasks by continuously learning.
-
June 07, 2023Combining semi-supervised learning, data augmentation, and reinforcement learning using rewards based on implicit customer feedback and natural-language-understanding semantics reduces word error rate by more than 10%.
-
June 02, 2023Topics such as code generation, commonsense reasoning, and self-learning complement the usual focus on speech recognition and acoustic-event classification.
