Related papers: Musical Phrase Segmentation via Grammatical Induct…
The proliferation of creative video content has driven demand for adapting language models to handle video input and enable multimodal understanding. However, end-to-end models struggle to process long videos due to their size and…
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…
Grammatical inference is a classical problem in computational learning theory and a topic of wider influence in natural language processing. We treat grammars as a model of computation and propose a novel neural approach to induction of…
Reordering is a challenge to machine translation (MT) systems. In MT, the widely used approach is to apply word based language model (LM) which considers the constituent units of a sentence as words. In speech recognition (SR), some phrase…
Many NLP datasets have been found to contain shortcuts: simple decision rules that achieve surprisingly high accuracy. However, it is difficult to discover shortcuts automatically. Prior work on automatic shortcut detection has focused on…
A program is characterized by its input model, and a formal input model can be of use in diverse areas including vulnerability analysis, reverse engineering, fuzzing and software testing, clone detection and refactoring. Unfortunately,…
We consider the problem of fully unsupervised learning of grammatical (part-of-speech) categories from unlabeled text. The standard maximum-likelihood hidden Markov model for this task performs poorly, because of its weak inductive bias and…
Video-aided grammar induction aims to leverage video information for finding more accurate syntactic grammars for accompanying text. While previous work focuses on building systems for inducing grammars on text that are well-aligned with…
Most previous approaches to Chinese word segmentation formalize this problem as a character-based sequence labeling task where only contextual information within fixed sized local windows and simple interactions between adjacent tags can be…
Recent advancements in morpheme segmentation primarily emphasize word-level segmentation, often neglecting the contextual relevance within the sentence. In this study, we redefine the morpheme segmentation task as a sequence-to-sequence…
Music segmentation refers to the dual problem of identifying boundaries between, and labeling, distinct music segments, e.g., the chorus, verse, bridge etc. in popular music. The performance of a range of music segmentation algorithms has…
This paper introduces a novel method for open-vocabulary 3D scene querying in autonomous driving by combining Language Embedded 3D Gaussians with Large Language Models (LLMs). We propose utilizing LLMs to generate both contextually…
We propose a knowledge-driven, model-based approach to segmenting audio into single-category and mixed-category chunks with applications to source separation. "Knowledge" here denotes information associated with the data, such as music…
Finding word boundaries in continuous speech is challenging as there is little or no equivalent of a 'space' delimiter between words. Popular Bayesian non-parametric models for text segmentation use a Dirichlet process to jointly segment…
Given the lack of word delimiters in written Japanese, word segmentation is generally considered a crucial first step in processing Japanese texts. Typical Japanese segmentation algorithms rely either on a lexicon and syntactic analysis or…
Prior methods to text segmentation are mostly at token level. Despite the adequacy, this nature limits their full potential to capture the long-term dependencies among segments. In this work, we propose a novel framework that incrementally…
Intuitionistic grammar logics fuse constructive and multi-modal reasoning while permitting the use of converse modalities, serving as a generalization of standard intuitionistic modal logics. In this paper, we provide definitions of these…
Word segmentation, the problem of finding word boundaries in speech, is of interest for a range of tasks. Previous papers have suggested that for sequence-to-sequence models trained on tasks such as speech translation or speech recognition,…
In this paper, we tackle the singing voice phoneme segmentation problem in the singing training scenario by using language-independent information -- onset and prior coarse duration. We propose a two-step method. In the first step, we…
Conventional spoken language understanding systems consist of two main components: an automatic speech recognition module that converts audio to a transcript, and a natural language understanding module that transforms the resulting text…