Goto

Collaborating Authors

The Dialog State Tracking Challenge Series

AI Magazine

In spoken dialog systems, dialog state tracking refers to the task of correctly inferring the user's goal at a given turn, given all of the dialog history up to that turn. The Dialog State Tracking Challenge is a research community challenge task that has run for three rounds. The challenge has given rise to a host of new methods for dialog state tracking, and also deeper understandings about the problem itself, including methods for evaluation.


Towards a Grounded Dialog Model for Explainable Artificial Intelligence

arXiv.org Artificial Intelligence

To generate trust with their users, Explainable Artificial Intelligence (XAI) systems need to include an explanation model that can communicate the internal decisions, behaviours and actions to the interacting humans. Successful explanation involves both cognitive and social processes. In this paper we focus on the challenge of meaningful interaction between an explainer and an explainee and investigate the structural aspects of an explanation in order to propose a human explanation dialog model. We follow a bottom-up approach to derive the model by analysing transcripts of 398 different explanation dialog types. We use grounded theory to code and identify key components of which an explanation dialog consists. We carry out further analysis to identify the relationships between components and sequences and cycles that occur in a dialog. We present a generalized state model obtained by the analysis and compare it with an existing conceptual dialog model of explanation.


Reasoning Visual Dialogs with Structural and Partial Observations

arXiv.org Artificial Intelligence

We propose a novel model to address the task of Visual Dialog which exhibits complex dialog structures. To obtain a reasonable answer based on the current question and the dialog history, the underlying semantic dependencies between dialog entities are essential. In this paper, we explicitly formalize this task as inference in a graphical model with partially observed nodes and unknown graph structures (relations in dialog). The given dialog entities are viewed as the observed nodes. The answer to a given question is represented by a node with missing value. We first introduce an Expectation Maximization algorithm to infer both the underlying dialog structures and the missing node values (desired answers). Based on this, we proceed to propose a differentiable graph neural network (GNN) solution that approximates this process. Experiment results on the VisDial and VisDial-Q datasets show that our model outperforms comparative methods. It is also observed that our method can infer the underlying dialog structure for better dialog reasoning.


SYNERGY: Building Task Bots at Scale Using Symbolic Knowledge and Machine Teaching

arXiv.org Artificial Intelligence

In this paper we explore the use of symbolic knowledge and machine teaching to reduce human data labeling efforts in building neural task bots. We propose SYNERGY, a hybrid learning framework where a task bot is developed in two steps: (i) Symbolic knowledge to neural networks: Large amounts of simulated dialog sessions are generated based on task-specific symbolic knowledge which is represented as a task schema consisting of dialog flows and task-oriented databases. Then a pre-trained neural dialog model, SOLOIST, is fine-tuned on the simulated dialogs to build a bot for the task. (ii) Neural learning: The fine-tuned neural dialog model is continually refined with a handful of real task-specific dialogs via machine teaching, where training samples are generated by human teachers interacting with the task bot. We validate SYNERGY on four dialog tasks. Experimental results show that SYNERGY maps task-specific knowledge into neural dialog models achieving greater diversity and coverage of dialog flows, and continually improves model performance with machine teaching, thus demonstrating strong synergistic effects of symbolic knowledge and machine teaching.


Opera Touch for iOS allows users to block annoying cookie dialogs

ZDNet

While the recent introduction of the General Data Protection Regulation (GDPR) may have allowed web users to have better control over their privacy, it has also meant that users have had to contend with complex and confusing popups and dialog screens related to privacy practices and policies. If you find this annoying, then you need Opera Touch, because it is the first major browser allowing people to control whether they want to see those annoying cookie dialogs, or to have them dealt with automatically. Must read: Apple products you shouldn't buy (February 2019 edition) With a simple flip of a switch, Opera Touch can remove those annoying cookie alert dialogs that litter pages, helping to bring annoyance-free web browsing to iPhone and iPad users. According to Opera, the feature "will allow users to block dialog attempts using a combination of CSS rules and JavaScript heuristics," and that it has "been been tested on more than 15000 of the Web's most popular websites," and that this feature is under continuous development to ensure the broadest possible support. This is one of the many new and innovative features that have been added to Opera Touch for iOS and Android since its launch.