Related papers: Tree-Structured Semantic Encoder with Knowledge Sh…

In task-oriented dialogue systems, spoken language understanding, or SLU, refers to the task of parsing natural language user utterances into semantic frames. Making use of context from prior dialogue history holds the key to more effective…

Dialogue agents, which perform specific tasks, are part of the long-term goal of NLP researchers to build intelligent agents that communicate with humans in natural language. Such systems should adapt easily from one domain to another to…

Robust dialogue belief tracking is a key component in maintaining good quality dialogue systems. The tasks that dialogue systems are trying to solve are becoming increasingly complex, requiring scalability to multi domain, semantically rich…

Duplicate question detection is an ongoing challenge in community question answering because semantically equivalent questions can have significantly different words and structures. In addition, the identification of duplicate questions can…

Because of their superior ability to preserve sequence information over time, Long Short-Term Memory (LSTM) networks, a type of recurrent neural network with a more complex computational unit, have obtained strong results on a variety of…

Many domain adaptation approaches rely on learning cross domain shared representations to transfer the knowledge learned in one domain to other domains. Traditional domain adaptation only considers adapting for one task. In this paper, we…

We investigate what kind of structural knowledge learned in neural network encoders is transferable to processing natural language. We design artificial languages with structural properties that mimic natural language, pretrain encoders on…

Deep neural networks based on layer-stacking architectures have historically suffered from poor inherent interpretability. Meanwhile, symbolic probabilistic models function with clear interpretability, but how to combine them with neural…

Long document classification presents challenges in capturing both local and global dependencies due to their extensive content and complex structure. Existing methods often struggle with token limits and fail to adequately model…

In modular dialogue systems, natural language understanding (NLU) and natural language generation (NLG) are two critical components, where NLU extracts the semantics from the given texts and NLG is to construct corresponding natural…

This article presents a stochastic corpus-based model for generating natural language text. Our model first encodes dependency relations from training data through a feature set, then concatenates these features to produce a new dependency…

We use reinforcement learning to learn tree-structured neural networks for computing representations of natural language sentences. In contrast with prior work on tree-structured models in which the trees are either provided as input or…

End-to-End intelligent neural dialogue systems suffer from the problems of generating inconsistent and repetitive responses. Existing dialogue models pay attention to unilaterally incorporating personal knowledge into the dialog while…

We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders. NSE is equipped with a novel memory update rule and has a variable sized encoding memory that evolves over time and maintains the…

One of the biggest challenges in the development and deployment of spoken dialogue systems is the design of the spoken language generation module. This challenge arises from the need for the generator to adapt to many features of the…

The meaning of a word often varies depending on its usage in different domains. The standard word embedding models struggle to represent this variation, as they learn a single global representation for a word. We propose a method to learn…

We propose a new encoder-decoder approach to learn distributed sentence representations that are applicable to multiple purposes. The model is learned by using a convolutional neural network as an encoder to map an input sentence into a…

Most natural language processing systems based on machine learning are not robust to domain shift. For example, a state-of-the-art syntactic dependency parser trained on Wall Street Journal sentences has an absolute drop in performance of…

We investigate how different domains are encoded in modern neural network architectures. We analyze the relationship between natural language domains, model size, and the amount of training data used. The primary analysis tool we develop is…

Recent work on the problem of latent tree learning has made it possible to train neural networks that learn to both parse a sentence and use the resulting parse to interpret the sentence, all without exposure to ground-truth parse trees at…