Related papers: Automatic Discourse Segmentation: Review and Persp…

While neural networks have been employed to handle several different text-to-speech tasks, ours is the first system to use neural networks throughout, for both linguistic and acoustic processing. We divide the text-to-speech task into three…

Existing work on probing of pretrained language models (LMs) has predominantly focused on sentence-level syntactic tasks. In this paper, we introduce document-level discourse probing to evaluate the ability of pretrained LMs to capture…

There is a huge amount of historical documents in libraries and in various National Archives that have not been exploited electronically. Although automatic reading of complete pages remains, in most cases, a long-term objective, tasks such…

In this paper, we propose the scheme for annotating large-scale multi-party chat dialogues for discourse parsing and machine comprehension. The main goal of this project is to help understand multi-party dialogues. Our dataset is based on…

Direct speech-to-text translation (ST) models are usually trained on corpora segmented at sentence level, but at inference time they are commonly fed with audio split by a voice activity detector (VAD). Since VAD segmentation is not…

This paper aims to achieve universal segmentation of arbitrary semantic level. Despite significant progress in recent years, specialist segmentation approaches are limited to specific tasks and data distribution. Retraining a new model for…

Sentence splitting is a major simplification operator. Here we present a simple and efficient splitting algorithm based on an automatic semantic parser. After splitting, the text is amenable for further fine-tuned simplification operations.…

In the domain of unsupervised learning most work on speech has focused on discovering low-level constructs such as phoneme inventories or word-like units. In contrast, for written language, where there is a large body of work on…

The present study proposes an annotation scheme for classifying the content and discourse contribution of question-answer pairs. We propose detailed guidelines for using the scheme and apply them to dialogues in English, Spanish, and Dutch.…

Speech summarization has become an essential tool for efficiently managing and accessing the growing volume of spoken and audiovisual content. However, despite its increasing importance, speech summarization remains loosely defined. The…

Our goal is to isolate individual speakers from multi-talker simultaneous speech in videos. Existing works in this area have focussed on trying to separate utterances from known speakers in controlled environments. In this paper, we propose…

This paper extends the task of probing sentence representations for linguistic insight in a multilingual domain. In doing so, we make two contributions: first, we provide datasets for multilingual probing, derived from Wikipedia, in five…

Automated discourse analysis tools based on Natural Language Processing (NLP) aiming at the diagnosis of language-impairing dementias generally extract several textual metrics of narrative transcripts. However, the absence of sentence…

Recent work on unsupervised speech segmentation has used self-supervised models with phone and word segmentation modules that are trained jointly. This paper instead revisits an older approach to word segmentation: bottom-up phone-like unit…

Multilingual pre-trained models could leverage the training data from a rich source language (such as English) to improve performance on low resource languages. However, the transfer quality for multilingual Machine Reading Comprehension…

This project explores the nature of language acquisition in computers, guided by techniques similar to those used in children. While existing natural language processing methods are limited in scope and understanding, our system aims to…

This paper explores the task of language-agnostic speaker replication, a novel endeavor that seeks to replicate a speaker's voice irrespective of the language they are speaking. Towards this end, we introduce a multi-level attention…

Morphological segmentation has traditionally been modeled with non-hierarchical models, which yield flat segmentations as output. In many cases, however, proper morphological analysis requires hierarchical structure -- especially in the…

Sentiment analysis has evolved over past few decades, most of the work in it revolved around textual sentiment analysis with text mining techniques. But audio sentiment analysis is still in a nascent stage in the research community. In this…

Active learning is particularly of interest for semantic segmentation, where annotations are costly. Previous academic studies focused on datasets that are already very diverse and where the model is trained in a supervised manner with a…