-
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 The compatibility, often facilitated through leaderboards, thus leads to outdated but standardized evaluation practices.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
-
EMNLP 20222022Factual and logical errors made by Natural Language Generation (NLG) systems limit their applicability in many settings. We study this problem in a conversational search and recommendation setting, and observe that we can often make two simplifying assumptions in this domain: (i) there exists a body of structured knowledge we can use for verifying factuality of generated text; and (ii) the text to be factually
-
NeurIPS 2022 Workshop on SyntheticData4ML2022Dialogue understanding tasks often necessitate abundant annotated data to achieve good performance and that presents challenges in low-resource settings. To alleviate this barrier, we explore few-shot data augmentation for dialogue understanding by prompting large pre-trained language models and present a novel approach that iterates on augmentation quality by applying weakly-supervised filters. We evaluate
Related content
-
Photo courtesy of Getty ImagesSeptember 10, 2019At next week’s Interspeech, the largest conference on the science and technology of spoken-language processing, Alexa researchers have 16 papers, which span the five core areas of Alexa functionality. -
Animation by Nick LittleSeptember 5, 2019Earlier this year, we reported a speech recognition system trained on a million hours of data, a feat possible through semi-supervised learning, in which training data is annotated by machines rather than by people. These sorts of massive machine learning projects are becoming more common, and they require distributing the training process across multiple processors. Otherwise, training becomes too time consuming.
-
September 4, 2019Earlier this year, at Amazon’s re:MARS conference, Alexa head scientist Rohit Prasad unveiled Alexa Conversations, a new service that allows Alexa skill developers to more easily integrate conversational elements into their skills. The announcement is an indicator of the next stage in Alexa’s evolution: more-natural, dialogue-based engagements that enable Alexa to aggregate data and refine requests to better meet customer needs.
-
August 29, 2019An automatic-speech-recognition system — such as Alexa’s — converts speech into text, and one of its key components is its language model. Given a sequence of words, the language model computes the probability that any given word is the next one. For instance, a language model would predict that a sentence that begins “Toni Morrison won the Nobel” is more likely to conclude “Prize” than “dries”. Language models can thus help decide between competing interpretations of the same acoustic information.
-
August 22, 2019A text-to-speech system, which converts written text into synthesized speech, is what allows Alexa to respond verbally to requests or commands...
-
Animation by Nick LittleAugust 15, 2019Embedding entity names from diverse skills in a shared representations space enables system to suggest neglected entity names with 88.5% accuracy.
