ConversationalAI.svg
Research Area

Conversational AI

Building software and systems that help people communicate with computers naturally, as if communicating with family and friends.

Publications

View all View all
  • Nir Drucker, Shay Gueron
    ACL 2022 Workshop on NLP for Conversational AI, Journal of Cryptography
    2020
    TLS 1.3 allows two parties to establish a shared session key from an out-of-band agreed Pre Shared Key (PSK). The PSK is used to mutually authenticate the parties, under the assumption that it is not shared with others. This allows the parties to skip the certificate verification steps, saving bandwidth, communication rounds, and latency. We identify a security vulnerability in this TLS 1.3 path, by showing
  • ACL 2020 Workshop on NLP for Conversational AI
    2020
    Dialogue response generation models that use template ranking rather than direct sequence generation allow model developers to limit generated responses to pre-approved messages. However, manually creating templates is time consuming and requires domain expertise. To alleviate this problem, we explore automating the process of creating dialogue templates by using unsupervised methods to cluster historical
  • Lifu Tu, Garima Lalwani, Spandana Gella, He He
    Transactions of the Association for Computational Linguistics
    2020
    Recent work has shown that pre-trained language models such as BERT improve robustness to spurious correlations in the dataset. Intrigued by these results, we find that the key to their success is generalization from a small amount of counter examples where the spurious correlations do not hold. When such minority examples are scarce, pre-trained models perform as poorly as models trained from scratch.
  • The Natural Language Understanding (NLU) component in task oriented dialog systems processes a user’s request and converts it into structured information that can be consumed by downstream components such as the Dialog State Tracker (DST). This information is typically represented as a semantic frame that captures the intent and slot-labels provided by the user. We first show that such a shallow representation
  • Felix Hieber, Tobias Domhan, Michael Denkowski, David Vilar
    EAMT 2020
    2020
    We present SOCKEYE2, a modernized and streamlined version of the SOCKEYE neural machine translation (NMT) toolkit.New features include a simplified code base through the use of MXNet’s GluonAPI, a focus on state-of-the-art model architectures, and distributed mixed precision training. These improvements result in faster training and inference, higher automatic metric scores, and a shorter path from research

Related content

GB, MLN, Edinburgh
We’re looking for a Machine Learning Scientist in the Personalization team for our Edinburgh office experienced in generative AI and large models. You will be responsible for developing and disseminating customer-facing personalized recommendation models. This is a hands-on role with global impact working with a team of world-class engineers and scientists across the Edinburgh offices and wider organization. You will lead the design of machine learning models that scale to very large quantities of data, and serve high-scale low-latency recommendations to all customers worldwide. You will embody scientific rigor, designing and executing experiments to demonstrate the technical efficacy and business value of your methods. You will work alongside aRead more