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
-
Interspeech 20212021Entity Retrieval (ER) in spoken dialog systems is a task that retrieves entities in a catalog for the entity mentions in user utterances. ER systems are susceptible to upstream errors, with Automatic Speech Recognition (ASR) errors being particularly troublesome. In this work, we propose a robust deep learning based ER system by leveraging ASR N-best hypotheses. Specifically, we evaluate different neural
-
ACL-IJCNLP 2021 Workshop on e-Commerce and NLP (ECNLP)2021Automatic Speech Recognition (ASR) robustness toward slot entities are critical in ecommerce voice assistants that involve monetary transactions and purchases. Along with effective domain adaptation, it is intuitive that cross utterance contextual cues play an important role in disambiguating domain specific content words from speech. In this paper, we investigate various techniques to improve contextualization
-
SIGIR 20212021Natural language query grounding in videos is a challenging task that requires comprehensive understanding of the query, video and fusion of information across these modalities. Existing methods mostly emphasize on the query-to-video one-way interaction with a late fusion scheme, lacking effective ways to capture the relationship within and between query and video in a fine-grained manner. Moreover, current
-
SIGIR 20212021We revisit the Bipartite Graph Partitioning approach to document reordering (Dhulipala et al., KDD 2016), and consider a range of algorithmic and heuristic refinements that lead to faster computation of index-minimizing document orderings. Our final implementation executes approximately four times faster than the reference implementation we commence with, and obtains the same, or slightly better, compression
-
ICML 20212021Current low-precision quantization algorithms often have the hidden cost of conversion back and forth from floating-point to quantized integer values. This hidden cost limits the latency improvement realized by quantizing Neural Networks. To address this, we present HAWQ-V3, a novel mixed-precision integer-only quantization framework. The contributions of HAWQ-V3 are the following: (i) An integer-only inference
Collaborations
View allWhether you're a faculty member or student, there are number of ways you can engage with Amazon.
View all