Related papers: Canonical and Surface Morphological Segmentation f…

As a fundamental task in computer vision, semantic segmentation is widely applied in fields such as autonomous driving, remote sensing image analysis, and medical image processing. In recent years, Transformer-based segmentation methods…

Linguistic features have shown promising applications for detecting various cognitive impairments. To improve detection accuracies, increasing the amount of data or the number of linguistic features have been two applicable approaches.…

Semantic segmentation is one of the key tasks in computer vision, which is to assign a category label to each pixel in an image. Despite significant progress achieved recently, most existing methods still suffer from two challenging issues:…

Federated Learning (FL) has gained popularity for fine-tuning large language models (LLMs) across multiple nodes, each with its own private data. While LoRA has been widely adopted for parameter efficient federated fine-tuning, recent…

Critical to natural language generation is the production of correctly inflected text. In this paper, we isolate the task of predicting a fully inflected sentence from its partially lemmatized version. Unlike traditional morphological…

Despite an ever growing number of word representation models introduced for a large number of languages, there is a lack of a standardized technique to provide insights into what is captured by these models. Such insights would help the…

Deep convolutional neural networks (CNNs) are the backbone of state-of-art semantic image segmentation systems. Recent work has shown that complementing CNNs with fully-connected conditional random fields (CRFs) can significantly enhance…

As NLP tools become ubiquitous in today's technological landscape, they are increasingly applied to languages with a variety of typological structures. However, NLP research does not focus primarily on typological differences in its…

We present LS-CRF, a new method for very efficient large-scale training of Conditional Random Fields (CRFs). It is inspired by existing closed-form expressions for the maximum likelihood parameters of a generative graphical model with tree…

Segmenting text into Elemental Discourse Units (EDUs) is a fundamental task in discourse parsing. We present a new simple method for identifying EDU boundaries, and hence segmenting them, based on lexical and character n-gram features,…

This paper proposes hybrid semi-Markov conditional random fields (SCRFs) for neural sequence labeling in natural language processing. Based on conventional conditional random fields (CRFs), SCRFs have been designed for the tasks of…

Feature foundation models - usually vision transformers - offer rich semantic descriptors of images, useful for downstream tasks such as (interactive) segmentation and object detection. For computational efficiency these descriptors are…

The success of large pretrained language models (LMs) such as BERT and RoBERTa has sparked interest in probing their representations, in order to unveil what types of knowledge they implicitly capture. While prior research focused on…

Language models are the foundation of current neural network-based models for natural language understanding and generation. However, research on the intrinsic performance of language models on African languages has been extremely limited,…

Many self-supervised speech models (S3Ms) have been introduced over the last few years, improving performance and data efficiency on various speech tasks. However, these empirical successes alone do not give a complete picture of what is…

Face parsing is defined as the per-pixel labeling of images containing human faces. The labels are defined to identify key facial regions like eyes, lips, nose, hair, etc. In this work, we make use of the structural consistency of the human…

This paper presents the submission by the CMU-01 team to the SIGMORPHON 2019 task 2 of Morphological Analysis and Lemmatization in Context. This task requires us to produce the lemma and morpho-syntactic description of each token in a…

Multilingual Machine Translation promises to improve translation quality between non-English languages. This is advantageous for several reasons, namely lower latency (no need to translate twice), and reduced error cascades (e.g., avoiding…

Building multilingual and crosslingual models help bring different languages together in a language universal space. It allows models to share parameters and transfer knowledge across languages, enabling faster and better adaptation to a…

Tokenization is a critical part of modern NLP pipelines. However, contemporary tokenizers for Large Language Models are based on statistical analysis of text corpora, without much consideration to the linguistic features. I propose a…