Dilek Hakkani‐Tür

Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems

2018 · arXiv (Cornell University)

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 include applying reinforcement learning with user feedback on supervised pre-training models. …

Leveraging Semantic Web Search and Browse Sessions for Multi-Turn Spoken Dialog Systems

2016 · arXiv (Cornell University)

Training statistical dialog models in spoken dialog systems (SDS) requires large amounts of annotated data. The lack of scalable methods for data mining and annotation poses a significant hurdle for state-of-the-art statistical dialog managers. This …

End-to-End Joint Learning of Natural Language Understanding and Dialogue Manager

2016 · arXiv (Cornell University)

Natural language understanding and dialogue policy learning are both essential in conversational systems that predict the next system actions in response to a current user utterance. Conventional approaches aggregate separate models of natural language understanding …

MMM: Multi-Stage Multi-Task Learning for Multi-Choice Reading Comprehension

2020 · Proceedings of the AAAI Conference on Artificial Intelligence

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 intelligence systems to understand human language. Multiple-Choice …

Using In-Context Learning to Improve Dialogue Safety

2023 · arXiv (Cornell University)

While large neural-based conversational models have become increasingly proficient dialogue agents, recent work has highlighted safety issues with these systems. For example, these systems can be goaded into generating toxic content, which often perpetuates social …

MERCY: Multiple Response Ranking Concurrently in Realistic Open-Domain Conversational Systems

2023

Automatic Evaluation (AE) and Response Selection (RS) models assign quality scores to various candidate responses and rank them in conversational setups. Prior response ranking research compares various models’ performance on synthetically generated test sets. In …

Zero-shot learning of intent embeddings for expansion by convolutional deep structured semantic models

2016

The recent surge of intelligent personal assistants motivates spoken language understanding of dialogue systems. However, the domain constraint along with the inflexible intent schema remains a big issue. This paper focuses on the task of …

End-to-End Memory Networks with Knowledge Carryover for Multi-Turn Spoken Language Understanding

2016

Spoken language understanding (SLU) is a core component of a spoken dialogue system. In the traditional architecture of dialogue systems, the SLU component treats each utterance independent of each other, and then the following components …

MultiWOZ 2.1: Multi-Domain Dialogue State Corrections and State Tracking Baselines

2019

MultiWOZ is a recently-released multidomain dialogue dataset spanning 7 distinct domains and containing over 10000 dialogues, one of the largest resources of its kind to-date. Though an immensely useful resource, while building different classes of …

Dialog State Tracking: A Neural Reading Comprehension Approach

2019

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 building systems that read passages of text …