Related papers: A Dual Encoder Sequence to Sequence Model for Open…

Vector representation of sentences is important for many text processing tasks that involve clustering, classifying, or ranking sentences. Recently, distributed representation of sentences learned by neural models from unlabeled data has…

Generative encoder-decoder models offer great promise in developing domain-general dialog systems. However, they have mainly been applied to open-domain conversations. This paper presents a practical and novel framework for building…

While end-to-end neural conversation models have led to promising advances in reducing hand-crafted features and errors induced by the traditional complex system architecture, they typically require an enormous amount of data due to the…

Sequence-to-sequence models have been applied to the conversation response generation problem where the source sequence is the conversation history and the target sequence is the response. Unlike translation, conversation responding is…

Generating long and coherent text is an important but challenging task, particularly for open-ended language generation tasks such as story generation. Despite the success in modeling intra-sentence coherence, existing generation models…

In this paper, we study the problem of data augmentation for language understanding in task-oriented dialogue system. In contrast to previous work which augments an utterance without considering its relation with other utterances, we…

The predominant approach to open-domain dialog generation relies on end-to-end training of neural models on chat datasets. However, this approach provides little insight as to what these models learn (or do not learn) about engaging in…

Language models are often used as the backbone of modern dialogue systems. These models are pre-trained on large amounts of written fluent language. Repetition is typically penalised when evaluating language model generations. However, it…

Neural sequence-to-sequence models are well established for applications which can be cast as mapping a single input sequence into a single output sequence. In this work, we focus on one-to-many sequence transduction problems, such as…

For machine translation to tackle discourse phenomena, models must have access to extra-sentential linguistic context. There has been recent interest in modelling context in neural machine translation (NMT), but models have been principally…

With the availability of massive general-domain dialogue data, pre-trained dialogue generation appears to be super appealing to transfer knowledge from the general domain to downstream applications. In most existing work, such transferable…

Neural sequence-to-sequence models are currently the dominant approach in several natural language processing tasks, but require large parallel corpora. We present a sequence-to-sequence-to-sequence autoencoder (SEQ^3), consisting of two…

Style is ubiquitous in our daily language uses, while what is language style to learning machines? In this paper, by exploiting the second-order statistics of semantic vectors of different corpora, we present a novel perspective on this…

Building a dialogue system that can communicate naturally with humans is a challenging yet interesting problem of agent-based computing. The rapid growth in this area is usually hindered by the long-standing problem of data scarcity as…

In the past few years, audiences from different fields witness the achievements of sequence-to-sequence models (e.g., LSTM+attention, Pointer Generator Networks, and Transformer) to enhance dialogue content generation. While content fluency…

In multi-turn dialog, utterances do not always take the full form of sentences \cite{Carbonell1983DiscoursePA}, which naturally makes understanding the dialog context more difficult. However, it is essential to fully grasp the dialog…

We present a novel response generation system that can be trained end to end on large quantities of unstructured Twitter conversations. A neural network architecture is used to address sparsity issues that arise when integrating contextual…

Many speech synthesis datasets, especially those derived from audiobooks, naturally comprise sequences of utterances. Nevertheless, such data are commonly treated as individual, unordered utterances both when training a model and at…

We model coherent conversation continuation via RNN-based dialogue models equipped with a dynamic attention mechanism. Our attention-RNN language model dynamically increases the scope of attention on the history as the conversation…

Understanding and predicting the emotional trajectory in multi-party multi-turn conversations is of great significance. Such information can be used, for example, to generate empathetic response in human-machine interaction or to inform…