-
NAACL 20192019The task of Natural Language Inference (NLI) is widely modeled as supervised sentence pair classification. While there has been a lot of work recently on generating explanations of the predictions of classifiers on a single piece of text, there have been no attempts to generate explanations of classifiers operating on pairs of sentences. In this paper, we show that it is possible to generate token-level
-
ACL 20192019This paper proposes a novel method to inject custom terminology into neural machine translation at run time. Previous works have mainly proposed modifications to the decoding algorithm in order to constrain the output to include run-time-provided target terms. While being effective, these constrained decoding methods add, however, significant computational overhead to the inference step, and, as we show
-
Interspeech 20192019Grapheme-to-phoneme (G2P) models are a key component in Automatic Speech Recognition (ASR) systems, such as the ASR system in Alexa, as they are used to generate pronunciations for out-of-vocabulary words that do not exist in the pronunciation lexicons (mappings like ”e c h o” → ”E k oU”). Most G2P systems are monolingual and based on traditional joint-sequence-based n-gram models. As an alternative, we
-
SIGDIAL 20192019In a spoken-dialogue system, dialogue state tracker (DST) components track the state of the conversation by updating a distribution of values associated with each of the slots being tracked for the current user turn, using the interactions until then. Much of the previous work has relied on modeling the natural order of the conversation, using distance based offsets as an approximation of time. In this
-
ICASSP 20192019The use of spatial information with multiple microphones can improve far-field automatic speech recognition (ASR) accuracy. However, conventional microphone array techniques degrade speech enhancement performance when there is an array geometry mismatch between design and test conditions. Moreover, such speech enhancement techniques do not always yield ASR accuracy improvement due to the difference between
Related content
-
June 11, 2019As Alexa expands into new countries, she usually has to be trained on new languages. But sometimes, she has to be re-trained on languages she’s already learned. British English, American English, and Indian English, for instance, are different enough that for each of them, we trained a new machine learning model from scratch. -
Animation by O’Reilly Science ArtJune 06, 2019New approach to reference resolution rewrites queries to clarify ambiguous references.
-
June 05, 2019Today, customer exchanges with Alexa are generally either one-shot requests, like “Alexa, what’s the weather?”, or interactions that require multiple requests to complete more complex tasks.
-
May 21, 2019A person’s tone of voice can tell you a lot about how they’re feeling. Not surprisingly, emotion recognition is an increasingly popular conversational-AI research topic.
-
May 16, 2019Text normalization is an important process in conversational AI. If an Alexa customer says, “book me a table at 5:00 p.m.”, the automatic speech recognizer will transcribe the time as “five p m”. Before a skill can handle this request, “five p m” will need to be converted to “5:00PM”. Once Alexa has processed the request, it needs to synthesize the response — say, “Is 6:30 p.m. okay?” Here, 6:30PM will be converted to “six thirty p m” for the text-to-speech synthesizer. We call the process of converting “5:00PM” to “five p m” text normalization and its counterpart — converting “five p m” to “5:00PM” — inverse text normalization.
-
May 13, 2019Recently, we published a paper showing that training a neural network to do language processing in English, then retraining it in German, drastically reduces the amount of German-language training data required to achieve a given level of performance.
