Search Results for author:
Found 7 papers, 0 papers with code
Decoupled Transformer for Scalable Inference in Open-domain Question Answering
To reduce computational cost and latency, we propose decoupling the transformer MRC model into input-component and cross-component.
Improving Opinion-based Question Answering Systems Through Label Error Detection and Overwrite
Importantly, LEDO is computationally efficient compared to methods that require loss function change, and cost-effective as the resulting data can be used in the same continuous training pipeline for production.
Self-Attention Gazetteer Embeddings for Named-Entity Recognition
Recent attempts to ingest external knowledge into neural models for named-entity recognition (NER) have exhibited mixed results.
F10-SGD: Fast Training of Elastic-net Linear Models for Text Classification and Named-entity Recognition
On public datasets, F10-SGD obtains 22% faster training time compared to FastText for text classification.
Active Learning for New Domains in Natural Language Understanding
We explore active learning (AL) for improving the accuracy of new domains in a natural language understanding (NLU) system.
Statistical Model Compression for Small-Footprint Natural Language Understanding
In this paper we investigate statistical model compression applied to natural language understanding (NLU) models.
Just ASK: Building an Architecture for Extensible Self-Service Spoken Language Understanding
This paper presents the design of the machine learning architecture that underlies the Alexa Skills Kit (ASK) a large scale Spoken Language Understanding (SLU) Software Development Kit (SDK) that enables developers to extend the capabilities of Amazon's virtual assistant, Alexa.
