53 citations · 78 across the 19 of their papers we have counts for
20 papers
Data Augmentation for Improving Tail-traffic Robustness in Skill-routing for Dialogue Systems
Ting-Wei Wu, Fatemeh Sheikholeslami, Mohammad Kachuee +2
Large-scale conversational systems typically rely on a skill-routing component to route a user request to an appropriate skill and interpretation to serve the request. In such syst…
Open World Classification with Adaptive Negative Samples
Ke Bai, Guoyin Wang, Jiwei Li +5
Open world classification is a task in natural language processing with key practical relevance and impact. Since the open or {\em unknown} category data only manifests in the infe…
Cluster-Guided Label Generation in Extreme Multi-Label Classification
Taehee Jung, Joo-Kyung Kim, Sungjin Lee +1
For extreme multi-label classification (XMC), existing classification-based models poorly perform for tail labels and often ignore the semantic relations among labels, like treatin…
Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Information
Yen-Ting Lin, Alexandros Papangelis, Seokhwan Kim +6
This work focuses on in-context data augmentation for intent detection. Having found that augmentation via in-context prompting of large pre-trained language models (PLMs) alone do…
PENTATRON: PErsonalized coNText-Aware Transformer for Retrieval-based cOnversational uNderstanding
Niranjan Uma Naresh, Ziyan Jiang, Ankit +4
Conversational understanding is an integral part of modern intelligent devices. In a large fraction of the global traffic from customers using smart digital assistants, frictions i…
Constrained Policy Optimization for Controlled Self-Learning in Conversational AI Systems
Mohammad Kachuee, Sungjin Lee
Recently, self-learning methods based on user satisfaction metrics and contextual bandits have shown promising results to enable consistent improvements in conversational AI system…
Learning Personalized Representations using Graph Convolutional Network
Hongyu Shen, Jinoh Oh, Shuai Zhao +3
Generating representations that precisely reflect customers' behavior is an important task for providing personalized skill routing experience in Alexa. Currently, Dynamic Routing…
Scalable and Robust Self-Learning for Skill Routing in Large-Scale Conversational AI Systems
Mohammad Kachuee, Jinseok Nam, Sarthak Ahuja +2
Skill routing is an important component in large-scale conversational systems. In contrast to traditional rule-based skill routing, state-of-the-art systems use a model-based appro…
Domain-Aware Contrastive Knowledge Transfer for Multi-domain Imbalanced Data
Zixuan Ke, Mohammad Kachuee, Sungjin Lee
In many real-world machine learning applications, samples belong to a set of domains e.g., for product reviews each review belongs to a product category. In this paper, we study mu…
Deciding Whether to Ask Clarifying Questions in Large-Scale Spoken Language Understanding
Joo-Kyung Kim, Guoyin Wang, Sungjin Lee +1
A large-scale conversational agent can suffer from understanding user utterances with various ambiguities such as ASR ambiguity, intent ambiguity, and hypothesis ambiguity. When am…
AUGNLG: Few-shot Natural Language Generation using Self-trained Data Augmentation
Xinnuo Xu, Guoyin Wang, Young-Bum Kim +1
Natural Language Generation (NLG) is a key component in a task-oriented dialogue system, which converts the structured meaning representation (MR) to the natural language. For larg…
Learning Slice-Aware Representations with Mixture of Attentions
Cheng Wang, Sungjin Lee, Sunghyun Park +3
Real-world machine learning systems are achieving remarkable performance in terms of coarse-grained metrics like overall accuracy and F-1 score. However, model improvement and deve…
Handling Long-Tail Queries with Slice-Aware Conversational Systems
Cheng Wang, Sun Kim, Taiwoo Park +5
We have been witnessing the usefulness of conversational AI systems such as Siri and Alexa, directly impacting our daily lives. These systems normally rely on machine learning mode…
A scalable framework for learning from implicit user feedback to improve natural language understanding in large-scale conversational AI systems
Sunghyun Park, Han Li, Ameen Patel +5
Natural Language Understanding (NLU) is an established component within a conversational AI or digital assistant system, and it is responsible for producing semantic understanding…
Self-Supervised Contrastive Learning for Efficient User Satisfaction Prediction in Conversational Agents
Mohammad Kachuee, Hao Yuan, Young-Bum Kim +1
Turn-level user satisfaction is one of the most important performance metrics for conversational agents. It can be used to monitor the agent's performance and provide insights abou…
Large-scale Hybrid Approach for Predicting User Satisfaction with Conversational Agents
Dookun Park, Hao Yuan, Dongmin Kim +10
Measuring user satisfaction level is a challenging task, and a critical component in developing large-scale conversational agent systems serving the needs of real users. An widely…
The Eighth Dialog System Technology Challenge
Seokhwan Kim, Michel Galley, Chulaka Gunasekara +18
This paper introduces the Eighth Dialog System Technology Challenge. In line with recent challenges, the eighth edition focuses on applying end-to-end dialog technologies in a prag…
Generating a Common Question from Multiple Documents using Multi-source Encoder-Decoder Models
Woon Sang Cho, Yizhe Zhang, Sudha Rao +2
Ambiguous user queries in search engines result in the retrieval of documents that often span multiple topics. One potential solution is for the search engine to generate multiple…
Contextual Out-of-Domain Utterance Handling With Counterfeit Data Augmentation
Sungjin Lee, Igor Shalyminov
Neural dialog models often lack robustness to anomalous user input and produce inappropriate responses which leads to frustrating user experience. Although there are a set of prior…
Improving Robustness of Neural Dialog Systems in a Data-Efficient Way with Turn Dropout
Igor Shalyminov, Sungjin Lee
Neural network-based dialog models often lack robustness to anomalous, out-of-domain (OOD) user input which leads to unexpected dialog behavior and thus considerably limits such mo…