Abstract Recurrent Neural Networks (RNNs) have become competitive forecasting methods,
as most notably shown in the winning method of the recent M4 competition. However …

The task of automatic document summarization aims at generating short summaries for
originally long documents. A good summary should cover the most important information of …

In this paper, we propose TopicRNN, a recurrent neural network (RNN)-based language
model designed to directly capture the global semantic meaning relating words in a …

We introduce a new class of models called multiresolution recurrent neural networks, which
explicitly model natural language generation at multiple levels of abstraction. The models …

Implicit discourse relation classification is one of the most difficult tasks in discourse parsing.
Previous studies have generally focused on extracting better representations of the …

In a dialog system, dialog act recognition and sentiment classification are two correlative
tasks to capture speakers' intentions, where dialog act and sentiment can indicate the …

Recent work in Dialogue Act classification has treated the task as a sequence labeling
problem using hierarchical deep neural networks. We build on this prior work by leveraging …

Neural abstractive summarization has been increasingly studied, where the prior work
mainly focused on summarizing single-speaker documents (news, scientific publications …

In dialog system, dialog act recognition and sentiment classification are two correlative tasks
to capture speakers' intentions, where dialog act and sentiment can indicate the explicit and …

Dialogue Act recognition associate dialogue acts (ie, semantic labels) to utterances in a
conversation. The problem of associating semantic labels to utterances can be treated as a …