Customer-obsessed science
Research areas
-
November 16, 202611 min readNew open-source tool turns existing test suites into sets of formal-verification tasks, which catch buggy solutions that tests alone would miss.
-
November 11, 20265 min read
-
-
-
Featured news
-
EMNLP 2021 Workshop on NLP for Conversational AI2021The recent advancement of digital assistant technologies has opened new possibilities in the experiences they can provide. One of them is the ability to converse with a persona, e.g., celebrities, famous fictional characters, etc. This experience requires that the replies are answered from the point of view of the persona, i.e., the first person. Since the facts about characters are typically found expressed
-
ASRU 20212021End-to-end (E2E) automatic speech recognition (ASR) systems often have difficulty recognizing uncommon words, that appear infrequently in the training data. One promising method, to improve the recognition accuracy on such rare words, is to latch onto personalized/contextual information at inference. In this work, we present a novel context-aware transformer transducer (CATT) network that improves the state-of-the-art
-
Operations Research Forum2021We present a set of new instances of the maximum weight independent set problem. These instances are derived from a real-world vehicle routing problem and are challenging to solve in part because of their large size. We present instances with up to 881 thousand nodes and 383 million edges.
-
ASRU 20212021End-to-end spoken language understanding (E2E SLU) systems predict the utterance semantics directly from speech. So far, to the best of our knowledge, E2E models have only been trained to recognize the semantics for a single language. In this work we introduce the first multilingual E2E SLU system and present results across three languages – English, Spanish and French. We propose a transformer-based, multilingual
-
EMNLP 2021 Workshop on NLP for Conversational AI2021Large-scale pretrained transformer models have demonstrated state-of-the-art (SOTA) performance in a variety of NLP tasks. Nowadays, numerous pretrained models are available in different model flavors and different languages, and can be easily adapted to one’s downstream task. However, only a limited number of models are available for dialogue tasks, and in particular, goal-oriented dialogue tasks. In addition
Collaborations
View allWhether you're a faculty member or student, there are number of ways you can engage with Amazon.
View all