471 citations · 800 across the 20 of their papers we have counts for
21 papers
Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuning
Mingyu Derek Ma, Jiun-Yu Kao, Shuyang Gao +4
Dialogue state tracking (DST) is an important step in dialogue management to keep track of users' beliefs. Existing works fine-tune all language model (LM) parameters to tackle the…
Context-Situated Pun Generation
Jiao Sun, Anjali Narayan-Chen, Shereen Oraby +5
Previous work on pun generation commonly begins with a given pun word (a pair of homophones for heterographic pun generation and a polyseme for homographic pun generation) and seek…
Towards Textual Out-of-Domain Detection without In-Domain Labels
Di Jin, Shuyang Gao, Seokhwan Kim +2
In many real-world settings, machine learning models need to identify user inputs that are out-of-domain (OOD) so as to avoid performing wrong actions. This work focuses on a chall…
Building Goal-Oriented Dialogue Systems with Situated Visual Context
Sanchit Agarwal, Jan Jezabek, Arijit Biswas +3
Most popular goal-oriented dialogue agents are capable of understanding the conversational context. However, with the surge of virtual assistants with screen, the next generation o…
Towards Zero and Few-shot Knowledge-seeking Turn Detection in Task-orientated Dialogue Systems
Di Jin, Shuyang Gao, Seokhwan Kim +2
Most prior work on task-oriented dialogue systems is restricted to supporting domain APIs. However, users may have requests that are out of the scope of these APIs. This work focus…
Simpler, Faster, Stronger: Breaking The log-K Curse On Contrastive Learners With FlatNCE
Junya Chen, Zhe Gan, Xuan Li +10
InfoNCE-based contrastive representation learners, such as SimCLR, have been tremendously successful in recent years. However, these contrastive schemes are notoriously resource de…
Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systems
Anish Acharya, Suranjit Adhikari, Sanchit Agarwal +28
Traditional goal-oriented dialogue systems rely on various components such as natural language understanding, dialogue state tracking, policy learning and response generation. Trai…
From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gap
Shuyang Gao, Sanchit Agarwal, Tagyoung Chung +2
Dialogue state tracking (DST) is at the heart of task-oriented dialogue systems. However, the scarcity of labeled data is an obstacle to building accurate and robust state tracking…
MMM: Multi-stage Multi-task Learning for Multi-choice Reading Comprehension
Di Jin, Shuyang Gao, Jiun-Yu Kao +2
Machine Reading Comprehension (MRC) for question answering (QA), which aims to answer a question given the relevant context passages, is an important way to test the ability of int…
Controlled Text Generation for Data Augmentation in Intelligent Artificial Agents
Nikolaos Malandrakis, Minmin Shen, Anuj Goyal +3
Data availability is a bottleneck during early stages of development of new capabilities for intelligent artificial agents. We investigate the use of text generation techniques to…
Dialog State Tracking: A Neural Reading Comprehension Approach
Shuyang Gao, Abhishek Sethi, Sanchit Agarwal +2
Dialog state tracking is used to estimate the current belief state of a dialog given all the preceding conversation. Machine reading comprehension, on the other hand, focuses on bu…
Invariant Representations without Adversarial Training
Daniel Moyer, Shuyang Gao, Rob Brekelmans +2
Representations of data that are invariant to changes in specified factors are useful for a wide range of problems: removing potential biases in prediction problems, controlling th…
Modeling Psychotherapy Dialogues with Kernelized Hashcode Representations: A Nonparametric Information-Theoretic Approach
Sahil Garg, Irina Rish, Guillermo Cecchi +5
We propose a novel dialogue modeling framework, the first-ever nonparametric kernel functions based approach for dialogue modeling, which learns kernelized hashcodes as compressed…
Auto-Encoding Total Correlation Explanation
Shuyang Gao, Rob Brekelmans, Greg Ver Steeg +1
Advances in unsupervised learning enable reconstruction and generation of samples from complex distributions, but this success is marred by the inscrutability of the representation…
Kernelized Hashcode Representations for Relation Extraction
Sahil Garg, Aram Galstyan, Greg Ver Steeg +3
Kernel methods have produced state-of-the-art results for a number of NLP tasks such as relation extraction, but suffer from poor scalability due to the high cost of computing kern…
Variational Information Maximization for Feature Selection
Shuyang Gao, Greg Ver Steeg, Aram Galstyan
Feature selection is one of the most fundamental problems in machine learning. An extensive body of work on information-theoretic feature selection exists which is based on maximiz…
Sifting Common Information from Many Variables
Greg Ver Steeg, Shuyang Gao, Kyle Reing +1
Measuring the relationship between any pair of variables is a rich and active area of research that is central to scientific practice. In contrast, characterizing the common inform…
The DARPA Twitter Bot Challenge
V. S. Subrahmanian, Amos Azaria, Skylar Durst +18
A number of organizations ranging from terrorist groups such as ISIS to politicians and nation states reportedly conduct explicit campaigns to influence opinion on social media, po…
Estimating Mutual Information by Local Gaussian Approximation
Shuyang Gao, Greg Ver Steeg, Aram Galstyan
Estimating mutual information (MI) from samples is a fundamental problem in statistics, machine learning, and data analysis. Recently it was shown that a popular class of non-param…
Understanding confounding effects in linguistic coordination: an information-theoretic approach
Shuyang Gao, Greg Ver Steeg, Aram Galstyan
We suggest an information-theoretic approach for measuring stylistic coordination in dialogues. The proposed measure has a simple predictive interpretation and can account for vari…
Efficient Estimation of Mutual Information for Strongly Dependent Variables
Shuyang Gao, Greg Ver Steeg, Aram Galstyan
We demonstrate that a popular class of nonparametric mutual information (MI) estimators based on k-nearest-neighbor graphs requires number of samples that scales exponentially with…