Related papers: Improving Topic Segmentation by Injecting Discours…

A statistical model for segmentation and word discovery in continuous speech is presented. An incremental unsupervised learning algorithm to infer word boundaries based on this model is described. Results of empirical tests showing that the…

Recently, discrete latent variable models have received a surge of interest in both Natural Language Processing (NLP) and Computer Vision (CV), attributed to their comparable performance to the continuous counterparts in representation…

Foundation models such as Segment Anything Model 3 (SAM3) enable flexible text-guided medical image segmentation, yet their predictions remain highly sensitive to prompt formulation. Even semantically equivalent descriptions can yield…

Distributional models are derived from co-occurrences in a corpus, where only a small proportion of all possible plausible co-occurrences will be observed. This results in a very sparse vector space, requiring a mechanism for inferring…

We show how to learn a neural topic model with discrete random variables---one that explicitly models each word's assigned topic---using neural variational inference that does not rely on stochastic backpropagation to handle the discrete…

Word segmentation is a low-level NLP task that is non-trivial for a considerable number of languages. In this paper, we present a sequence tagging framework and apply it to word segmentation for a wide range of languages with different…

Unsupervised semantic segmentation aims to achieve high-quality semantic grouping without human-labeled annotations. With the advent of self-supervised pre-training, various frameworks utilize the pre-trained features to train prediction…

Sentiment-aware intelligent systems are essential to a wide array of applications. These systems are driven by language models which broadly fall into two paradigms: Lexicon-based and contextual. Although recent contextual models are…

Self-supervised pre-trained transformers have improved the state of the art on a variety of speech tasks. Due to the quadratic time and space complexity of self-attention, they usually operate at the level of relatively short (e.g.,…

The recent tremendous success of unsupervised word embeddings in a multitude of applications raises the obvious question if similar methods could be derived to improve embeddings (i.e. semantic representations) of word sequences as well. We…

Advances in topic modeling have yielded effective methods for characterizing the latent semantics of textual data. However, applying standard topic modeling approaches to sentence-level tasks introduces a number of challenges. In this…

Dialogue related Machine Reading Comprehension requires language models to effectively decouple and model multi-turn dialogue passages. As a dialogue development goes after the intentions of participants, its topic may not keep constant…

Traditional neural topic models are typically optimized by reconstructing the document's Bag-of-Words (BoW) representations, overlooking contextual information and struggling with data sparsity. In this work, we propose a novel approach to…

Topic models aim to reveal latent structures within a corpus of text, typically through the use of term-frequency statistics over bag-of-words representations from documents. In recent years, conceptual entities -- interpretable,…

Extracting and identifying latent topics in large text corpora has gained increasing importance in Natural Language Processing (NLP). Most models, whether probabilistic models similar to Latent Dirichlet Allocation (LDA) or neural topic…

Recent work incorporates pre-trained word embeddings such as BERT embeddings into Neural Topic Models (NTMs), generating highly coherent topics. However, with high-quality contextualized document representations, do we really need…

Topic models are often used to identify human-interpretable topics to help make sense of large document collections. We use knowledge distillation to combine the best attributes of probabilistic topic models and pretrained transformers. Our…

The Transformer-based models with the multi-head self-attention mechanism are widely used in natural language processing, and provide state-of-the-art results. While the pre-trained language backbones are shown to implicitly capture certain…

Recently, deep learning-based beamforming algorithms have shown promising performance in target speech extraction tasks. However, most systems do not fully utilize spatial information. In this paper, we propose a target speech extraction…

Providing technologies to communities or domains where training data is scarce or protected e.g., for privacy reasons, is becoming increasingly important. To that end, we generalise methods for unsupervised transfer from multiple input…