Related papers: Hierarchical Gated Recurrent Neural Tensor Network…

Neural conversation models tend to generate safe, generic responses for most inputs. This is due to the limitations of likelihood-based decoding objectives in generation tasks with diverse outputs, such as conversation. To address this…

Neural network models recently proposed for question answering (QA) primarily focus on capturing the passage-question relation. However, they have minimal capability to link relevant facts distributed across multiple sentences which is…

Multi-hop QA (Question Answering) is the task of finding the answer to a question across multiple documents. In recent years, a number of Deep Learning-based approaches have been proposed to tackle this complex task, as well as a few…

Neural algorithmic reasoning (NAR) is an emerging field that seeks to design neural networks that mimic classical algorithmic computations. Today, graph neural networks (GNNs) are widely used in neural algorithmic reasoners due to their…

Keyword Spotting (KWS) provides the start signal of ASR problem, and thus it is essential to ensure a high recall rate. However, its real-time property requires low computation complexity. This contradiction inspires people to find a…

Real-time emotion recognition (RTER) in conversations is significant for developing emotionally intelligent chatting machines. Without the future context in RTER, it becomes critical to build the memory bank carefully for capturing…

Recurrent Neural Networks (RNNs) with sophisticated units that implement a gating mechanism have emerged as powerful technique for modeling sequential signals such as speech or electroencephalography (EEG). The latter is the focus on this…

Recognising dialogue acts (DA) is important for many natural language processing tasks such as dialogue generation and intention recognition. In this paper, we propose a dual-attention hierarchical recurrent neural network for DA…

In this paper, we propose a novel approach that enhances recurrent neural networks (RNNs) by incorporating path signatures into their gating mechanisms. Our method modifies both Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU)…

Answering questions from university admission exams (Gaokao in Chinese) is a challenging AI task since it requires effective representation to capture complicated semantic relations between questions and answers. In this work, we propose a…

Large neural language models are steadily contributing state-of-the-art performance to question answering and other natural language and information processing tasks. These models are expensive to train. We propose to evaluate whether such…

Breaking domain names such as openresearch into component words open and research is important for applications like Text-to-Speech synthesis and web search. We link this problem to the classic problem of Chinese word segmentation and show…

Generative neural networks have been shown effective on query suggestion. Commonly posed as a conditional generation problem, the task aims to leverage earlier inputs from users in a search session to predict queries that they will likely…

We introduce the multiresolution recurrent neural network, which extends the sequence-to-sequence framework to model natural language generation as two parallel discrete stochastic processes: a sequence of high-level coarse tokens, and a…

Large pre-trained language models (LMs) have been shown to perform surprisingly well when fine-tuned on tasks that require commonsense and world knowledge. However, in end-to-end architectures, it is difficult to explain what is the…

Several deep learning models have been proposed for question answering. However, due to their single-pass nature, they have no way to recover from local maxima corresponding to incorrect answers. To address this problem, we introduce the…

Beyond topical relevance, passage ranking for open-domain factoid question answering also requires a passage to contain an answer (answerability). While a few recent studies have incorporated some reading capability into a ranker to account…

Social recommendation which aims to leverage social connections among users to enhance the recommendation performance. With the revival of deep learning techniques, many efforts have been devoted to developing various neural network-based…

With the increasing research interest in dialogue response generation, there is an emerging branch formulating this task as selecting next sentences, where given the partial dialogue contexts, the goal is to determine the most probable next…

Learning both hierarchical and temporal representation has been among the long-standing challenges of recurrent neural networks. Multiscale recurrent neural networks have been considered as a promising approach to resolve this issue, yet…