Task-Oriented Dialogue as Dataflow Synthesis

@article{Andreas2020TaskOrientedDA,
  title={Task-Oriented Dialogue as Dataflow Synthesis},
  author={Jacob Andreas and Johannes Bufe and David Burkett and Charles C. Chen and Joshua Clausman and Jean Crawford and Kate Crim and Jordan DeLoach and Leah Dorner and Jason Eisner and Hao Fang and Alan Guo and David Leo Wright Hall and Kristin Delia Hayes and Kellie Hill and Diana Ho and Wendy Iwaszuk and Smriti Jha and Dan Klein and Jayant Krishnamurthy and Theo Lanman and Percy Liang and C. H. Lin and Ilya Lintsbakh and Andy McGovern and Aleksandr Nisnevich and Adam Pauls and Dmitrij Petters and Brent Read and Dan Roth and Subhro Roy and Jesse Rusak and Beth Ann Short and Div Slomin and B Snyder and Stephon Striplin and Yu Su and Zachary Tellman and Sam Thomson and A. A. Vorobev and Izabela Witoszko and Jason Wolfe and Abby Wray and Yuchen Zhang and Alexander Zotov},
  journal={Transactions of the Association for Computational Linguistics},
  year={2020},
  volume={8},
  pages={556-571}
}
Abstract We describe an approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph. A dialogue agent maps each user utterance to a program that extends this graph. Programs include metacomputation operators for reference and revision that reuse dataflow fragments from previous turns. Our graph-based state enables the expression and manipulation of complex user intents, and explicit metacomputation makes these intents easier for learned models to predict. We… Expand
Value-Agnostic Conversational Semantic Parsing
TLDR
This work proposes a model that abstracts over values to focus prediction on type and function-level context, which provides a compact encoding of dialogue histories and predicted programs, improving generalization and computational efficiency. Expand
Few-Shot Bot: Prompt-Based Learning for Dialogue Systems
TLDR
An end-to-end chatbot named the Few-Shot Bot is created, which automatically selects the most appropriate conversational skill, queries different knowledge bases or the internet, and uses the retrieved knowledge to generate a human-like response, all using only few dialogue examples per skill. Expand
Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQL
TLDR
This paper proposes a novel decoupled multi-turn Text-to-SQL framework, where an utterance rewrite model first explicitly solves completion of dialogue context, and then a single-turn textscript parser follows to address the data sparsity problem. Expand
Towards Transparent Interactive Semantic Parsing via Step-by-Step Correction
TLDR
This work investigates an interactive semantic parsing framework that explains the predicted logical form step by step in natural language and enables the user to make corrections through natural-language feedback for individual steps, aiming to increase the transparency of the parsing process and help the user appropriately trust the final answer. Expand
TicketTalk: Toward human-level performance with end-to-end, transaction-based dialog systems
TLDR
A data-driven, end-to-end approach to transaction-based dialog systems that performs at near-human levels in terms of verbal response quality and factual grounding accuracy and how API prediction and response generation scores improve as the dataset size incrementally increases from 5000 to 21,000 dialogs is presented. Expand
Semi-supervised Interactive Intent Labeling
TLDR
This work extends the Deep Aligned Clustering work with a better backbone BERT model, explores techniques to select the seed data for labeling, and develops a data balancing method using an oversampling technique that utilizes paraphrasing models. Expand
Semantic Parsing in Task-Oriented Dialog with Recursive Insertion-based Encoder
TLDR
Recursive INsertion-based Encoder (RINE), a novel approach for semantic parsing in task-oriented dialog, achieves state-ofthe-art exact match accuracy on low and high-resource versions of the conversational semantic parsing benchmark TOP (Gupta et al. 2018). Expand
GOLD: Improving Out-of-Scope Detection in Dialogues using Data Augmentation
TLDR
This work introduces GOLD as an orthogonal technique that augments existing data to train better OOS detectors operating in low-data regimes and analyzes the unique properties of OOS data to identify key factors for optimally applying this method. Expand
The Lab vs The Crowd: An Investigation into Data Quality for Neural Dialogue Models
TLDR
This study compares the performance of dialogue models for the same interaction task but collected in two different settings: in the lab vs. crowd-sourced, and finds that fewer lab dialogues are needed to reach similar accuracy, less than half the amount of lab data as crowd'sourced data. Expand
Pretraining the Noisy Channel Model for Task-Oriented Dialogue
TLDR
It is argued for the use of Bayes’ theorem to factorize the dialogue task into two models, the distribution of the context given the response, and the prior for the response itself, as an instantiation of the noisy channel model. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 80 REFERENCES
Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems
TLDR
A Transferable Dialogue State Generator (TRADE) that generates dialogue states from utterances using copy mechanism, facilitating transfer when predicting (domain, slot, value) triplets not encountered during training. Expand
Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset
TLDR
This work introduces the initial release of the Taskmaster-1 dataset which includes 13,215 task-based dialogs comprising six domains and offers several baseline models including state of the art neural seq2seq architectures with benchmark performance as well as qualitative human evaluations. Expand
A Network-based End-to-End Trainable Task-oriented Dialogue System
TLDR
This work introduces a neural network-based text-in, text-out end-to-end trainable goal-oriented dialogue system along with a new way of collecting dialogue data based on a novel pipe-lined Wizard-of-Oz framework that can converse with human subjects naturally whilst helping them to accomplish tasks in a restaurant search domain. Expand
MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling
TLDR
The Multi-Domain Wizard-of-Oz dataset (MultiWOZ), a fully-labeled collection of human-human written conversations spanning over multiple domains and topics is introduced, at a size of 10k dialogues, at least one order of magnitude larger than all previous annotated task-oriented corpora. Expand
Learning End-to-End Goal-Oriented Dialog
TLDR
It is shown that an end-to-end dialog system based on Memory Networks can reach promising, yet imperfect, performance and learn to perform non-trivial operations and be compared to a hand-crafted slot-filling baseline on data from the second Dialog State Tracking Challenge. Expand
MultiWOZ 2.1: A Consolidated Multi-Domain Dialogue Dataset with State Corrections and State Tracking Baselines
TLDR
This work uses crowdsourced workers to re-annotate state and utterances based on the original utterances in the dataset, and benchmark a number of state-of-the-art dialogue state tracking models on the MultiWOZ 2.1 dataset and show the joint state tracking performance on the corrected state annotations. Expand
HyST: A Hybrid Approach for Flexible and Accurate Dialogue State Tracking
TLDR
This work analyzes the performance of these two alternative dialogue state tracking methods, and presents a hybrid approach (HyST) which learns the appropriate method for each slot type and shows that HyST scales to multi-domain applications. Expand
Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning
TLDR
Neural Assistant is developed: a single neural network model that takes conversation history and an external knowledge source as input and jointly produces both text response and action to be taken by the system as output that significantly improves language generation performance. Expand
CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases
TLDR
CoSQL is presented, a corpus for building cross-domain, general-purpose database (DB) querying dialogue systems that includes SQL-grounded dialogue state tracking, response generation from query results, and user dialogue act prediction and a set of strong baselines are evaluated. Expand
Dialogue act modeling for automatic tagging and recognition of conversational speech
TLDR
A probabilistic integration of speech recognition with dialogue modeling is developed, to improve both speech recognition and dialogue act classification accuracy. Expand
...
1
2
3
4
5
...