Related papers: Toward Fast and Accurate Neural Discourse Segmenta…

Discourse parsing, the task of analyzing the internal rhetorical structure of texts, is a challenging problem in natural language processing. Despite the recent advances in neural models, the lack of large-scale, high-quality corpora for…

Instance segmentation is the problem of detecting and delineating each distinct object of interest appearing in an image. Current instance segmentation approaches consist of ensembles of modules that are trained independently of each other,…

To promote and further develop RST-style discourse parsing models, we need a strong baseline that can be regarded as a reference for reporting reliable experimental results. This paper explores a strong baseline by integrating existing…

Breaking down a document or a conversation into multiple contiguous segments based on its semantic structure is an important and challenging problem in NLP, which can assist many downstream tasks. However, current works on topic…

Referring image segmentation is an advanced semantic segmentation task where target is not a predefined class but is described in natural language. Most of existing methods for this task rely heavily on convolutional neural networks, which…

Recently, segmentation neural networks have been significantly improved by demonstrating very promising accuracies on public benchmarks. However, these models are very heavy and generally suffer from low inference speed, which limits their…

Visual speech recognition models traditionally consist of two stages, feature extraction and classification. Several deep learning approaches have been recently presented aiming to replace the feature extraction stage by automatically…

While the community keeps promoting end-to-end models over conventional hybrid models, which usually are long short-term memory (LSTM) models trained with a cross entropy criterion followed by a sequence discriminative training criterion,…

Referring Expression Segmentation (RES) is a core vision-language segmentation task that enables pixel-level understanding of targets via free-form linguistic expressions, supporting critical applications such as human-robot interaction and…

The Conformer model is an excellent architecture for speech recognition modeling that effectively utilizes the hybrid losses of connectionist temporal classification (CTC) and attention to train model parameters. To improve the decoding…

We propose a segmental neural language model that combines the generalization power of neural networks with the ability to discover word-like units that are latent in unsegmented character sequences. In contrast to previous segmentation…

In this work we use the recent advances in representation learning to propose a neural architecture for the problem of natural language inference. Our approach is aligned to mimic how a human does the natural language inference process…

Designing machine intelligence to converse with a human user necessarily requires an understanding of how humans participate in conversation, and thus conversation modeling is an important task in natural language processing. New…

We present an unsupervised word segmentation model, in which the learning objective is to maximize the generation probability of a sentence given its all possible segmentation. Such generation probability can be factorized into the…

This paper presents a novel design of neural network system for fine-grained style modeling, transfer and prediction in expressive text-to-speech (TTS) synthesis. Fine-grained modeling is realized by extracting style embeddings from the…

Text segmentation aims to divide text into contiguous, semantically coherent segments, while segment labeling deals with producing labels for each segment. Past work has shown success in tackling segmentation and labeling for documents and…

Attention-based models have been gaining popularity recently for their strong performance demonstrated in fields such as machine translation and automatic speech recognition. One major challenge of attention-based models is the need of…

Self-supervised learning has been proved to benefit a wide range of speech processing tasks, such as speech recognition/translation, speaker verification and diarization, etc. However, most of current approaches are computationally…

Breaking down the structure of long texts into semantically coherent segments makes the texts more readable and supports downstream applications like summarization and retrieval. Starting from an apparent link between text coherence and…

Current object segmentation algorithms are based on the hypothesis that one has access to a very large amount of data. In this paper, we aim to segment objects using only tiny datasets. To this extent, we propose a new automatic part-based…