5.7k citations · 8.2k across the 48 of their papers we have counts for
33 papers · 1 filter
Catch Your Breath: Adaptive Computation for Self-Paced Sequence Production
Alexandre Galashov, Matt Jones, Rosemary Ke +3
Within the landscape of inference-time scaling methods for foundation models, a width-based approach to scaling -- which involves the insertion of <pause> tokens in the input strea…
Retrieval Augmented End-to-End Spoken Dialog Models
Mingqiu Wang, Izhak Shafran, Hagen Soltau +4
We recently developed SLM, a joint speech and language model, which fuses a pretrained foundational speech model and a large language model (LLM), while preserving the in-context l…
SLM: Bridge the thin gap between speech and text foundation models
Mingqiu Wang, Wei Han, Izhak Shafran +15
We present a joint Speech and Language Model (SLM), a multitask, multilingual, and dual-modal model that takes advantage of pretrained foundational speech and language models. SLM…
Grammar Prompting for Domain-Specific Language Generation with Large Language Models
Bailin Wang, Zi Wang, Xuezhi Wang +3
Large language models (LLMs) can learn to perform a wide range of natural language tasks from just a handful of in-context examples. However, for generating strings from highly str…
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
Shunyu Yao, Dian Yu, Jeffrey Zhao +4
Language models are increasingly being deployed for general problem solving across a wide range of tasks, but are still confined to token-level, left-to-right decision-making proce…
Binarized Neural Machine Translation
Yichi Zhang, Ankush Garg, Yuan Cao +4
The rapid scaling of language models is motivating research using low-bitwidth quantization. In this work, we propose a novel binarization technique for Transformers applied to mac…
AnyTOD: A Programmable Task-Oriented Dialog System
Jeffrey Zhao, Yuan Cao, Raghav Gupta +6
We propose AnyTOD, an end-to-end, zero-shot task-oriented dialog (TOD) system capable of handling unseen tasks without task-specific training. We view TOD as a program executed by…
Knowledge-grounded Dialog State Tracking
Dian Yu, Mingqiu Wang, Yuan Cao +3
Knowledge (including structured knowledge such as schema and ontology, and unstructured knowledge such as web corpus) is a critical part of dialog understanding, especially for uns…
ReAct: Synergizing Reasoning and Acting in Language Models
Shunyu Yao, Jeffrey Zhao, Dian Yu +4
While large language models (LLMs) have demonstrated impressive capabilities across tasks in language understanding and interactive decision making, their abilities for reasoning (…
Unsupervised Slot Schema Induction for Task-oriented Dialog
Dian Yu, Mingqiu Wang, Yuan Cao +3
Carefully-designed schemas describing how to collect and annotate dialog corpora are a prerequisite towards building task-oriented dialog systems. In practical applications, manual…
The Implicit Length Bias of Label Smoothing on Beam Search Decoding
Bowen Liang, Pidong Wang, Yuan Cao
Label smoothing is ubiquitously applied in Neural Machine Translation (NMT) training. While label smoothing offers a desired regularization effect during model training, in this pa…
Building Machine Translation Systems for the Next Thousand Languages
Ankur Bapna, Isaac Caswell, Julia Kreutzer +21
In this paper we share findings from our effort to build practical machine translation (MT) systems capable of translating across over one thousand languages. We describe results i…
Show, Don't Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented Dialogue
Raghav Gupta, Harrison Lee, Jeffrey Zhao +3
Building universal dialogue systems that operate across multiple domains/APIs and generalize to new ones with minimal overhead is a critical challenge. Recent works have leveraged…
Multilingual Mix: Example Interpolation Improves Multilingual Neural Machine Translation
Yong Cheng, Ankur Bapna, Orhan Firat +3
Multilingual neural machine translation models are trained to maximize the likelihood of a mix of examples drawn from multiple language pairs. The dominant inductive bias applied t…
Description-Driven Task-Oriented Dialog Modeling
Jeffrey Zhao, Raghav Gupta, Yuan Cao +6
Task-oriented dialogue (TOD) systems are required to identify key information from conversations for the completion of given tasks. Such information is conventionally specified in…
Towards the Next 1000 Languages in Multilingual Machine Translation: Exploring the Synergy Between Supervised and Self-Supervised Learning
Aditya Siddhant, Ankur Bapna, Orhan Firat +4
Achieving universal translation between all human language pairs is the holy-grail of machine translation (MT) research. While recent progress in massively multilingual MT is one s…
SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systems
Harrison Lee, Raghav Gupta, Abhinav Rastogi +3
Zero/few-shot transfer to unseen services is a critical challenge in task-oriented dialogue research. The Schema-Guided Dialogue (SGD) dataset introduced a paradigm for enabling mo…
Towards Zero-Label Language Learning
Zirui Wang, Adams Wei Yu, Orhan Firat +1
This paper explores zero-label learning in Natural Language Processing (NLP), whereby no human-annotated data is used anywhere during training and models are trained purely on synt…
Effective Sequence-to-Sequence Dialogue State Tracking
Jeffrey Zhao, Mahdis Mahdieh, Ye Zhang +2
Sequence-to-sequence models have been applied to a wide variety of NLP tasks, but how to properly use them for dialogue state tracking has not been systematically investigated. In…
Improving Longer-range Dialogue State Tracking
Ye Zhang, Yuan Cao, Mahdis Mahdieh +2
Dialogue state tracking (DST) is a pivotal component in task-oriented dialogue systems. While it is relatively easy for a DST model to capture belief states in short conversations,…
Echo State Speech Recognition
Harsh Shrivastava, Ankush Garg, Yuan Cao +2
We propose automatic speech recognition (ASR) models inspired by echo state network (ESN), in which a subset of recurrent neural networks (RNN) layers in the models are randomly in…
Rapid Domain Adaptation for Machine Translation with Monolingual Data
Mahdis Mahdieh, Mia Xu Chen, Yuan Cao +1
One challenge of machine translation is how to quickly adapt to unseen domains in face of surging events like COVID-19, in which case timely and accurate translation of in-domain i…
Deciphering Undersegmented Ancient Scripts Using Phonetic Prior
Jiaming Luo, Frederik Hartmann, Enrico Santus +2
Most undeciphered lost languages exhibit two characteristics that pose significant decipherment challenges: (1) the scripts are not fully segmented into words; (2) the closest know…
Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models
Zirui Wang, Yulia Tsvetkov, Orhan Firat +1
Massively multilingual models subsuming tens or even hundreds of languages pose great challenges to multi-task optimization. While it is a common practice to apply a language-agnos…