Related papers: Deep Open Intent Classification with Adaptive Deci…

Robot understanding of human intentions is essential for fluid human-robot interaction. Intentions, however, cannot be directly observed and must be inferred from behaviors. We learn a model of adaptive human behavior conditioned on the…

We build a theoretical framework for designing and understanding practical meta-learning methods that integrates sophisticated formalizations of task-similarity with the extensive literature on online convex optimization and sequential…

New Intent Discovery (NID) aims to recognize known and infer new intent categories with the help of limited labeled and large-scale unlabeled data. The task is addressed as a feature-clustering problem and recent studies augment instance…

Implicit discourse relation classification is one of the most difficult parts in shallow discourse parsing as the relation prediction without explicit connectives requires the language understanding at both the text span level and the…

Automatically and accurately identifying user intents and filling the associated slots from their spoken language are critical to the success of dialogue systems. Traditional methods require manually defining the DOMAIN-INTENT-SLOT schema…

Out-of-Domain (OOD) intent detection is important for practical dialog systems. To alleviate the issue of lacking OOD training samples, some works propose synthesizing pseudo OOD samples and directly assigning one-hot OOD labels to these…

Recognizing customer intent accurately with language models based on customer-agent conversational data is essential in today's digital customer service marketplace, but it is often hindered by the lack of sufficient labeled data. In this…

Adversarial training has become the primary method to defend against adversarial samples. However, it is hard to practically apply due to many shortcomings. One of the shortcomings of adversarial training is that it will reduce the…

Conversational systems have a Natural Language Understanding (NLU) module. In this module, there is a task known as an intent classification that aims at identifying what a user is attempting to achieve from an utterance. Previous works use…

Conversational systems are of primary interest in the AI community. Chatbots are increasingly being deployed to provide round-the-clock support and to increase customer engagement. Many of the commercial bot building frameworks follow a…

Deep Learning methods are renowned for their performances, yet their lack of interpretability prevents them from high-stakes contexts. Recent model agnostic methods address this problem by providing post-hoc interpretability methods by…

We study the problem of adapting to a known sub-rational opponent during online play while remaining robust to rational opponents. We focus on large imperfect-information (zero-sum) games, which makes it impossible to inspect the whole game…

Modern language model deployments must often balance competing objectives, for example, helpfulness versus harmlessness, cost versus accuracy, and reward versus safety. We introduce Conformal Arbitrage, a post hoc framework that learns a…

Domain adaptation tasks such as cross-domain sentiment classification aim to utilize existing labeled data in the source domain and unlabeled or few labeled data in the target domain to improve the performance in the target domain via…

Deep neural models (e.g. Transformer) naturally learn spurious features, which create a ``shortcut'' between the labels and inputs, thus impairing the generalization and robustness. This paper advances the self-attention mechanism to its…

Intent discovery is a crucial task in natural language processing, and it is increasingly relevant for various of industrial applications. Identifying novel, unseen intents from user inputs remains one of the biggest challenges in this…

An adversarial attack paradigm explores various scenarios for the vulnerability of deep learning models: minor changes of the input can force a model failure. Most of the state of the art frameworks focus on adversarial attacks for images…

Task-oriented dialog systems need to know when a query falls outside their range of supported intents, but current text classification corpora only define label sets that cover every example. We introduce a new dataset that includes queries…

This paper addresses the problem of modeling textual conversations and detecting emotions. Our proposed model makes use of 1) deep transfer learning rather than the classical shallow methods of word embedding; 2) self-attention mechanisms…

In collaborative human-robot manipulation, a robot must predict human intents and adapt its actions accordingly to smoothly execute tasks. However, the human's intent in turn depends on actions the robot takes, creating a chicken-or-egg…