Related papers: Lightweight Connective Detection Using Gradient Bo…

Speech recognition systems have achieved high recognition performance for several tasks. However, the performance of such systems is dependent on the tremendously costly development work of preparing vast amounts of task-matched transcribed…

Dialogue systems can benefit from being able to search through a corpus of text to find information relevant to user requests, especially when encountering a request for which no manually curated response is available. The state-of-the-art…

We present a simple unified framework for multi-class cost-sensitive boosting. The minimum-risk class is estimated directly, rather than via an approximation of the posterior distribution. Our method jointly optimizes binary weak learners…

In many applications of supervised learning, multiple classification or regression outputs have to be predicted jointly. We consider several extensions of gradient boosting to address such problems. We first propose a straightforward…

We consider the problem of communication efficient distributed optimization where multiple nodes exchange important algorithm information in every iteration to solve large problems. In particular, we focus on the stochastic variance-reduced…

Language model fusion helps smart assistants recognize words which are rare in acoustic data but abundant in text-only corpora (typed search logs). However, such corpora have properties that hinder downstream performance, including being…

Retrieval-based conversational systems learn to rank response candidates for a given dialogue context by computing the similarity between their vector representations. However, training on a single textual form of the multi-turn context…

The gradient boosting machine is one of the powerful tools for solving regression problems. In order to cope with its shortcomings, an approach for constructing ensembles of gradient boosting models is proposed. The main idea behind the…

Distributed model training suffers from communication bottlenecks due to frequent model updates transmitted across compute nodes. To alleviate these bottlenecks, practitioners use gradient compression techniques like sparsification,…

Nontrivial connectivity has allowed the training of very deep networks by addressing the problem of vanishing gradients and offering a more efficient method of reusing parameters. In this paper we make a comparison between residual…

This paper presents a novel technique based on gradient boosting to train the final layers of a neural network (NN). Gradient boosting is an additive expansion algorithm in which a series of models are trained sequentially to approximate a…

Voice-based interfaces rely on a wake-up word mechanism to initiate communication with devices. However, achieving a robust, energy-efficient, and fast detection remains a challenge. This paper addresses these real production needs by…

Without discourse connectives, classifying implicit discourse relations is a challenging task and a bottleneck for building a practical discourse parser. Previous research usually makes use of one kind of discourse framework such as PDTB or…

Dialogue act recognition is an important part of natural language understanding. We investigate the way dialogue act corpora are annotated and the learning approaches used so far. We find that the dialogue act is context-sensitive within…

Long-range semantic coherence remains a challenge in automatic language generation and understanding. We demonstrate that large language models have insufficiently learned the effect of distant words on next-token prediction. We present…

Unlike Object Detection, Visual Grounding task necessitates the detection of an object described by complex free-form language. To simultaneously model such complex semantic and visual representations, recent state-of-the-art studies adopt…

Network consensus optimization has received increasing attention in recent years and has found important applications in many scientific and engineering fields. To solve network consensus optimization problems, one of the most well-known…

This paper evaluates the viability of using fixed language models for training text classification networks on low-end hardware. We combine language models with a CNN architecture and put together a comprehensive benchmark with 8 datasets…

In recent years, distributed optimization is proven to be an effective approach to accelerate training of large scale machine learning models such as deep neural networks. With the increasing computation power of GPUs, the bottleneck of…

Diffusion Models (DMs) have achieved state-of-the-art generative performance across multiple modalities, yet their sampling process remains prohibitively slow due to the need for hundreds of function evaluations. Recent progress in…