相关论文: Limited Attention and Discourse Structure

Retrieving spoken content with spoken queries, or query-by- example spoken term detection (STD), is attractive because it makes possible the matching of signals directly on the acoustic level without transcribing them into text. Here, we…

We develop an equilibrium theory of attention and politics. In a spatial model of electoral competition where candidates have varying policy preferences, we examine what kinds of political behaviors capture voters' limited attention and how…

Attention networks have proven to be an effective approach for embedding categorical inference within a deep neural network. However, for many tasks we may want to model richer structural dependencies without abandoning end-to-end training.…

Modern language models rely on the transformer architecture and attention mechanism to perform language understanding and text generation. In this work, we study learning a 1-layer self-attention model from a set of prompts and associated…

The standard content-based attention mechanism typically used in sequence-to-sequence models is computationally expensive as it requires the comparison of large encoder and decoder states at each time step. In this work, we propose an…

Since the advent of ChatGPT, Large Language Models (LLMs) have excelled in various tasks but remain as black-box systems. Understanding the reasoning bottlenecks of LLMs has become a critical challenge, as these limitations are deeply tied…

Machine comprehension is a representative task of natural language understanding. Typically, we are given context paragraph and the objective is to answer a question that depends on the context. Such a problem requires to model the complex…

Recently, topic-grounded dialogue system has attracted significant attention due to its effectiveness in predicting the next topic to yield better responses via the historical context and given topic sequence. However, almost all existing…

Humans and artificial agents must often learn and switch between multiple tasks in dynamic environments. Success in such settings requires cognitive flexibility: the ability to retain prior knowledge (cognitive stability) while also…

Dialogue state tracking is an important component in task-oriented dialogue systems to identify users' goals and requests as a dialogue proceeds. However, as most previous models are dependent on dialogue slots, the model complexity soars…

Speech intelligibility can be degraded due to multiple factors, such as noisy environments, technical difficulties or biological conditions. This work is focused on the development of an automatic non-intrusive system for predicting the…

In this paper, we address the "black-box" problem in predictive process analytics by building interpretable models that are capable to inform both what and why is a prediction. Predictive process analytics is a newly emerged discipline…

Question Under Discussion (QUD), which is originally a linguistic analytic framework, gains increasing attention in the community of natural language processing over the years. Various models have been proposed for implementing QUD for…

Attention plays a fundamental role in both natural and artificial intelligence systems. In deep learning, attention-based neural architectures, such as transformer architectures, are widely used to tackle problems in natural language…

Neural encoder-decoder models of machine translation have achieved impressive results, rivalling traditional translation models. However their modelling formulation is overly simplistic, and omits several key inductive biases built into…

In order to address the chain of thought in the large language model inference cost surge, this research proposes to use a sparse attention mechanism that only focuses on a few relevant tokens. The researcher constructed a new attention…

The recent surge of large language models (LLMs) highlights their ability to perform in-context learning, i.e., "learning" to perform a task from a few demonstrations in the context without any parameter updates. However, their capabilities…

Pre-training models have been proved effective for a wide range of natural language processing tasks. Inspired by this, we propose a novel dialogue generation pre-training framework to support various kinds of conversations, including…

Distantly supervised relation extraction intrinsically suffers from noisy labels due to the strong assumption of distant supervision. Most prior works adopt a selective attention mechanism over sentences in a bag to denoise from wrongly…

Speech contains information that is clinically relevant to some diseases, which has the potential to be used for health assessment. Recent work shows an interest in applying deep learning algorithms, especially pretrained large speech…