Related papers: Guider l'attention dans les modeles de sequence a …

Auto-regressive sequence-to-sequence models with attention mechanism have achieved state-of-the-art performance in many tasks such as machine translation and speech synthesis. These models can be difficult to train. The standard approach,…

We present a novel approach to learn representations for sentence-level semantic similarity using conversational data. Our method trains an unsupervised model to predict conversational input-response pairs. The resulting sentence embeddings…

Using a sequence-to-sequence framework, many neural conversation models for chit-chat succeed in naturalness of the response. Nevertheless, the neural conversation models tend to give generic responses which are not specific to given…

Classic pipeline models for task-oriented dialogue system require explicit modeling the dialogue states and hand-crafted action spaces to query a domain-specific knowledge base. Conversely, sequence-to-sequence models learn to map dialogue…

The DIAlogue MOdel Learning Environment supports an engineering-oriented approach towards dialogue modelling for a spoken-language interface. Major steps towards dialogue models is to know about the basic units that are used to construct a…

This paper describes a method based on a sequence-to-sequence learning (Seq2Seq) with attention and context preservation mechanism for voice conversion (VC) tasks. Seq2Seq has been outstanding at numerous tasks involving sequence modeling…

Voice controlled virtual assistants (VAs) are now available in smartphones, cars, and standalone devices in homes. In most cases, the user needs to first "wake-up" the VA by saying a particular word/phrase every time he or she wants the VA…

Ever since the successful application of sequence to sequence learning for neural machine translation systems, interest has surged in its applicability towards language generation in other problem domains. Recent work has investigated the…

The noetic end-to-end response selection challenge as one track in Dialog System Technology Challenges 7 (DSTC7) aims to push the state of the art of utterance classification for real world goal-oriented dialog systems, for which…

User interests are usually dynamic in the real world, which poses both theoretical and practical challenges for learning accurate preferences from rich behavior data. Among existing user behavior modeling solutions, attention networks are…

When training a model on referential dialogue guessing games, the best model is usually chosen based on its task success. We show that in the popular end-to-end approach, this choice prevents the model from learning to generate…

Current language models are usually trained using a self-supervised scheme, where the main focus is learning representations at the word or sentence level. However, there has been limited progress in generating useful discourse-level…

Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands through the entire…

Text-based dialogues are now widely used to solve real-world problems. In cases where solution strategies are already known, they can sometimes be codified into workflows and used to guide humans or artificial agents through the task of…

Recently, much progress has been made in learning general-purpose sentence representations that can be used across domains. However, most of the existing models typically treat each word in a sentence equally. In contrast, extensive studies…

This paper presents our latest investigations on dialog act (DA) classification on automatically generated transcriptions. We propose a novel approach that combines convolutional neural networks (CNNs) and conditional random fields (CRFs)…

Sequence labeling is a fundamental task in natural language processing and has been widely studied. Recently, RNN-based sequence labeling models have increasingly gained attentions. Despite superior performance achieved by learning the long…

Multi-turn response selection is a challenging task due to its high demands on efficient extraction of the matching features from abundant information provided by context utterances. Since incorporating syntactic information like dependency…

A long-term goal of machine learning research is to build an intelligent dialog agent. Most research in natural language understanding has focused on learning from fixed training sets of labeled data, with supervision either at the word…

Building an intelligent dialogue system with the ability to select a proper response according to a multi-turn context is a great challenging task. Existing studies focus on building a context-response matching model with various neural…