Related papers: TreeSeg: Hierarchical Topic Segmentation of Large …

Autoregressive (AR) encoder-decoder neural networks have proved successful in many NLP problems, including Semantic Parsing -- a task that translates natural language to machine-readable parse trees. However, the sequential prediction…

This paper investigates one of the most fundamental computer vision problems: image segmentation. We propose a supervised hierarchical approach to object-independent image segmentation. Starting with over-segmenting superpixels, we use a…

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…

Dealing with datasets of very high dimension is a major challenge in machine learning. In this paper, we consider the problem of feature selection in applications where the memory is not large enough to contain all features. In this…

Our work addresses the problem of unsupervised Aspect Category Detection using a small set of seed words. Recent works have focused on learning embedding spaces for seed words and sentences to establish similarities between sentences and…

The growing demand for effective tools to parse PDF-formatted texts, particularly structured documents such as textbooks, reveals the limitations of current methods developed mainly for research paper segmentation. This work addresses the…

This paper explores the development and application of an automated system designed to extract information from semi-structured interview transcripts. Given the labor-intensive nature of traditional qualitative analysis methods, such as…

We present LlamaSeg, a visual autoregressive framework that unifies multiple image segmentation tasks via natural language instructions. We reformulate image segmentation as a visual generation problem, representing masks as "visual" tokens…

In this work, we showcase a cost-effective method for generating training data for speech processing tasks. First, we transcribe unlabeled speech using a state-of-the-art Automatic Speech Recognition (ASR) model. Next, we align generated…

The lack of training data gives rise to the system cold-start problem in recommendation systems, making them struggle to provide effective recommendations. To address this problem, Large Language Models (LLMs) can model recommendation tasks…

We introduce Tokenization with Split Trees (ToaST), a subword tokenization method that directly optimizes compression under a new recursive inference procedure. ToaST greedily splits each pretoken into a full binary tree using precomputed…

Audio features have been proven useful for increasing the performance of automated topic segmentation systems. This study explores the novel task of using audio embeddings for automated, topically coherent segmentation of radio shows. We…

The prosperity of Multimodal Large Language Models (MLLMs) has stimulated the demand for video reasoning segmentation, which aims to segment video objects based on human instructions. Previous studies rely on unidirectional and implicit…

Past work on unsupervised parsing is constrained to written form. In this paper, we present the first study on unsupervised spoken constituency parsing given unlabeled spoken sentences and unpaired textual data. The goal is to determine the…

In this work, we focus on improving ASR output segmentation in the context of low-resource language speech-to-text translation. ASR output segmentation is crucial, as ASR systems segment the input audio using purely acoustic information and…

Automatic Speech Recognition (ASR) has reached impressive accuracy for high-resource languages, yet its utility in linguistic fieldwork remains limited. Recordings collected in fieldwork contexts present unique challenges, including…

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…

We present HyperSeg, a hyperdimensional computing (HDC) approach to unsupervised dialogue topic segmentation. HDC is a class of vector symbolic architectures that leverages the probabilistic orthogonality of randomly drawn vectors at…

In human-computer conversation systems, the context of a user-issued utterance is particularly important because it provides useful background information of the conversation. However, it is unwise to track all previous utterances in the…

Mining a set of meaningful topics organized into a hierarchy is intuitively appealing since topic correlations are ubiquitous in massive text corpora. To account for potential hierarchical topic structures, hierarchical topic models…