January 9, 2022 By: Xiaohui Zhang, Frank Zhang, Chunxi Liu, Kjell Schubert, Julian Chan, Pradyot Prakash, Jun Liu, Ching-Feng Yeh, Fuchun Peng, Yatharth Saraf, Geoffrey Zweig Abstract In this work, to measure the accuracy and efficiency for a latency-controlled streaming automatic speech recognition (ASR) application, we perform comprehensive evaluations on three popular training criteria: LF-MMI, CTC and RNN-T. In transcribing social media videos of 7 languages with training data 3K – 14K hours, we conduct large-scale controlled experimentation across each […]

News 👋 Hi there, welcome to the 12th issue of the 🤗 newsletter! Here’s what’s been brewing this month: Part 2 of the 🤗 course AutoNLP Free Tier for one week We welcome GPT-J to the 🤗 Transformers family … and more! 🎓 November 15-19: Part 2 of the 🤗 course goes live! We’re excited to release the second    

Abstract Recent work in open-domain conversational agents has demonstrated that significant improvements in humanness and user preference can be achieved via massive scaling in both pre-training data and model size (Adiwardana et al., 2020; Roller et al., 2020). However, if we want to build agents with human-like abilities, we must expand beyond handling just text. A particularly important topic is the ability to see images and communicate about what is perceived. With the goal of getting humans to engage in […]

Abstract Despite showing increasingly human-like conversational abilities, state-of-the-art dialogue models often suffer from factual incorrectness and hallucination of knowledge. In this work we explore the use of neural-retrieval-in-the-loop architectures – recently shown to be effective in open-domain QA – for knowledge-grounded dialogue, a task that is arguably more challenging as it requires querying based on complex multi-turn dialogue context and generating conversationally coherent responses. We study various types of architectures with multiple components – retrievers, rankers, and encoder-decoders – with […]

November 7, 2021 By: Soumya Batra, Shashank Jain, Peyman Heidari, Ankit Arun, Catharine Youngs, Xintong Li, Pinar Donmez, Shawn Mei, Shiun-Zu Kuo, Vikas Bhardwaj, Anuj Kumar, Michael White Abstract We propose a novel framework to train models to classify acceptability of responses generated by natural language generation (NLG) models, improving upon existing sentence transformation and model-based approaches. An NLG response is considered acceptable if it is both semantically correct and grammatical. We don’t make use of any human references making […]