424 citations · 734 across the 16 of their papers we have counts for
18 papers
Correcting Automated and Manual Speech Transcription Errors using Warped Language Models
Mahdi Namazifar, John Malik, Li Erran Li +2
Masked language models have revolutionized natural language processing systems in the past few years. A recently introduced generalization of masked language models called warped l…
Are We There Yet? Learning to Localize in Embodied Instruction Following
Shane Storks, Qiaozi Gao, Govind Thattai +1
Embodied instruction following is a challenging problem requiring an agent to infer a sequence of primitive actions to achieve a goal environment state from complex language and vi…
Can You be More Social? Injecting Politeness and Positivity into Task-Oriented Conversational Agents
Yi-Chia Wang, Alexandros Papangelis, Runze Wang +3
Goal-oriented conversational agents are becoming prevalent in our daily lives. For these systems to engage users and achieve their goals, they need to exhibit appropriate social be…
LRTA: A Transparent Neural-Symbolic Reasoning Framework with Modular Supervision for Visual Question Answering
Weixin Liang, Feiyang Niu, Aishwarya Reganti +2
The predominant approach to visual question answering (VQA) relies on encoding the image and question with a "black-box" neural encoder and decoding a single token as the answer li…
Language Model is All You Need: Natural Language Understanding as Question Answering
Mahdi Namazifar, Alexandros Papangelis, Gokhan Tur +1
Different flavors of transfer learning have shown tremendous impact in advancing research and applications of machine learning. In this work we study the use of a specific family o…
Warped Language Models for Noise Robust Language Understanding
Mahdi Namazifar, Gokhan Tur, Dilek Hakkani Tür
Masked Language Models (MLM) are self-supervised neural networks trained to fill in the blanks in a given sentence with masked tokens. Despite the tremendous success of MLMs for va…
Improving Embedding Extraction for Speaker Verification with Ladder Network
Fei Tao, Gokhan Tur
Speaker verification is an established yet challenging task in speech processing and a very vibrant research area. Recent speaker verification (SV) systems rely on deep neural netw…
Multi-Task Siamese Neural Network for Improving Replay Attack Detection
Patrick von Platen, Fei Tao, Gokhan Tur
Automatic speaker verification systems are vulnerable to audio replay attacks which bypass security by replaying recordings of authorized speakers. Replay attack detection (RA) det…
Flexibly-Structured Model for Task-Oriented Dialogues
Lei Shu, Piero Molino, Mahdi Namazifar +4
This paper proposes a novel end-to-end architecture for task-oriented dialogue systems. It is based on a simple and practical yet very effective sequence-to-sequence approach, wher…
Collaborative Multi-Agent Dialogue Model Training Via Reinforcement Learning
Alexandros Papangelis, Yi-Chia Wang, Piero Molino +1
We present the first complete attempt at concurrently training conversational agents that communicate only via self-generated language. Using DSTC2 as seed data, we trained natural…
OCC: A Smart Reply System for Efficient In-App Communications
Yue Weng, Huaixiu Zheng, Franziska Bell +1
Smart reply systems have been developed for various messaging platforms. In this paper, we introduce Uber's smart reply system: one-click-chat (OCC), which is a key enhanced featur…
User Modeling for Task Oriented Dialogues
Izzeddin Gur, Dilek Hakkani-Tur, Gokhan Tur +1
We introduce end-to-end neural network based models for simulating users of task-oriented dialogue systems. User simulation in dialogue systems is crucial from two different perspe…
Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems
Bing Liu, Gokhan Tur, Dilek Hakkani-Tur +2
In this work, we present a hybrid learning method for training task-oriented dialogue systems through online user interactions. Popular methods for learning task-oriented dialogues…
Building a Conversational Agent Overnight with Dialogue Self-Play
Pararth Shah, Dilek Hakkani-Tür, Gokhan Tür +4
We propose Machines Talking To Machines (M2M), a framework combining automation and crowdsourcing to rapidly bootstrap end-to-end dialogue agents for goal-oriented dialogues in arb…
End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning
Bing Liu, Gokhan Tur, Dilek Hakkani-Tur +2
In this paper, we present a neural network based task-oriented dialogue system that can be optimized end-to-end with deep reinforcement learning (RL). The system is able to track d…
Towards Zero-Shot Frame Semantic Parsing for Domain Scaling
Ankur Bapna, Gokhan Tur, Dilek Hakkani-Tur +1
State-of-the-art slot filling models for goal-oriented human/machine conversational language understanding systems rely on deep learning methods. While multi-task training of such…
Knowledge as a Teacher: Knowledge-Guided Structural Attention Networks
Yun-Nung Chen, Dilek Hakkani-Tur, Gokhan Tur +3
Natural language understanding (NLU) is a core component of a spoken dialogue system. Recently recurrent neural networks (RNN) obtained strong results on NLU due to their superior…
Prosody-Based Automatic Segmentation of Speech into Sentences and Topics
E. Shriberg, A. Stolcke, D. Hakkani-Tur +1
A crucial step in processing speech audio data for information extraction, topic detection, or browsing/playback is to segment the input into sentence and topic units. Speech segme…