相关论文: Never Look Back: An Alternative to Centering

We show that discourse structure, as defined by Rhetorical Structure Theory and provided by an existing discourse parser, benefits text categorization. Our approach uses a recursive neural network and a newly proposed attention mechanism to…

This squib examines the role of limited attention in a theory of discourse structure and proposes a model of attentional state that relates current hierarchical theories of discourse structure to empirical evidence about human discourse…

Many recent deep learning-based solutions have widely adopted the attention-based mechanism in various tasks of the NLP discipline. However, the inherent characteristics of deep learning models and the flexibility of the attention mechanism…

Named entity recognition is one of the core tasks in NLP. Although many improvements have been made on this task during the last years, the state-of-the-art systems do not explicitly take into account the recursive nature of language.…

We introduce an Attention Overload Model that captures the idea that alternatives compete for the decision maker's attention, and hence the attention that each alternative receives decreases as the choice problem becomes larger. Using this…

Reranking, as the final stage of multi-stage recommender systems, refines the initial lists to maximize the total utility. With the development of multimedia and user interface design, the recommendation page has evolved to a multi-list…

Ranking is a central task in machine learning and information retrieval. In this task, it is especially important to present the user with a slate of items that is appealing as a whole. This in turn requires taking into account interactions…

Exploiting information induced from (query-specific) clustering of top-retrieved documents has long been proposed as a means for improving precision at the very top ranks of the returned results. We present a novel language model approach…

We extend the centering model for the resolution of intra-sentential anaphora and specify how to handle complex sentences. An empirical evaluation indicates that the functional information structure guides the search for an antecedent…

Learning to rank is a key component of many e-commerce search engines. In learning to rank, one is interested in optimising the global ordering of a list of items according to their utility for users.Popular approaches learn a scoring…

This paper is a contribution towards interpretability of the deep learning models in different applications of time-series. We propose a temporal attention layer that is capable of selecting the relevant information to perform various…

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…

As the final stage of recommender systems, re-ranking presents ordered item lists to users that best match their interests. It plays such a critical role and has become a trending research topic with much attention from both academia and…

In this paper, we propose a novel sequence-aware recommendation model. Our model utilizes self-attention mechanism to infer the item-item relationship from user's historical interactions. With self-attention, it is able to estimate the…

In the past few years, attention mechanisms have become an indispensable component of end-to-end neural machine translation models. However, previous attention models always refer to some source words when predicting a target word, which…

Speech Quality Assessment (SQA) and Continuous Speech Emotion Recognition (CSER) are two key tasks in speech technology, both relying on listener ratings. However, these ratings are inherently biased due to individual listener factors.…

Attention is the crucial cognitive ability that limits and selects what information we observe. Previous work by Bolander et al. (2016) proposes a model of attention based on dynamic epistemic logic (DEL) where agents are either fully…

We propose a general framework for interactively learning models, such as (binary or non-binary) classifiers, orderings/rankings of items, or clusterings of data points. Our framework is based on a generalization of Angluin's equivalence…

Entity Linking has two main open areas of research: 1) generate candidate entities without using alias tables and 2) generate more contextual representations for both mentions and entities. Recently, a solution has been proposed for the…

The minimization of the length of syntactic dependencies is a well-established principle of word order and the basis of a mathematical theory of word order. Here we complete that theory from the perspective of information theory, adding a…