In this paper, we present Smart Compose, a novel system for generating interactive, real-
time suggestions in Gmail that assists users in writing mails by reducing repetitive typing. In …

With the ever‐increasing popularity of mobile computing technology and the wide adoption
of outsourcing strategy in labour‐intensive industrial domains, mobile crowdsourcing has …

With the popularity of mobile devices, personalized speech recognizers have become more
attainable and are highly attractive. Since each mobile device is used primarily by a single …

A context-aware language model uses location, user and/or domain metadata (context) to
adapt its predictions. In neural language models, context information is typically represented …

Completing a sentence, phrase or word after typing few words/characters is very helpful for
Intuit financial experts, while taking notes or having a live chat with users, since they need to …

In this paper, we detail novel strategies for interpolating personalized language models and
methods to handle out-of-vocabulary (OOV) tokens to improve personalized language …

Distributed word representations have been shown to be very useful in various natural
language processing (NLP) application tasks. These word vectors learned from huge …

(57) ABSTRACT A process for context-based autocompletion suggestion includes, based on
initiating an online chat by a user of a computer system, the chat having as participants the …

Abstract In Natural Language Processing (NLP), together with speech, text is one of the
main sources of information. Computational systems that process raw text need to perform a …

抄録 In this paper, we propose a new personalization method for a dialogue system using
external knowledge and Graph Convolutional Networks (GCNs). The proposed system is …