Related papers: Weakly Supervised POS Taggers Perform Poorly on Tr…

A current problem in NLP is massaging and processing low-resource languages which lack useful training attributes such as supervised data, number of native speakers or experts, etc. This review paper concisely summarizes previous…

In Weak Supervised Learning (WSL), a model is trained over noisy labels obtained from semantic rules and task-specific pre-trained models. Rules offer limited generalization over tasks and require significant manual efforts while…

Spoken dialog systems are slowly becoming and integral part of the human experience due to their various advantages over textual interfaces. Spoken language understanding (SLU) systems are fundamental building blocks of spoken dialog…

This paper describes Centre for Development of Advanced Computing's (CDACM) submission to the shared task-'Tool Contest on POS tagging for Code-Mixed Indian Social Media (Facebook, Twitter, and Whatsapp) Text', collocated with ICON-2016.…

We report our development of a simple but fast and efficient inductive unsupervised semantic tagger for Chinese words. A POS hand-tagged corpus of 348,000 words is used. The corpus is being tagged in two steps. First, possible semantic tags…

The performance of a Part-of-speech (POS) tagger is highly dependent on the domain ofthe processed text, and for many domains there is no or only very little training data available. This work addresses the problem of POS tagging noisy…

We present a bootstrapping method to develop an annotated corpus, which is specially useful for languages with few available resources. The method is being applied to develop a corpus of Spanish of over 5Mw. The method consists on taking…

As a fundamental tool for natural language processing (NLP), the part-of-speech (POS) tagger assigns the POS label to each word in a sentence. A novel lightweight POS tagger based on word embeddings is proposed and named GWPT (green…

Large Language Models are transforming NLP for a variety of tasks. However, how LLMs perform NLP tasks for low-resource languages (LRLs) is less explored. In line with the goals of the AmericasNLP workshop, we focus on 12 LRLs from Brazil,…

We present Expected Statistic Regularization (ESR), a novel regularization technique that utilizes low-order multi-task structural statistics to shape model distributions for semi-supervised learning on low-resource datasets. We study ESR…

Sparsity is one of the major problems in natural language processing. The problem becomes even more severe in agglutinating languages that are highly prone to be inflected. We deal with sparsity in Turkish by adopting morphological features…

While language identification is a fundamental speech and language processing task, for many languages and language families it remains a challenging task. For many low-resource and endangered languages this is in part due to resource…

Cross-lingual knowledge transfer, especially between high- and low-resource languages, remains challenging in natural language processing (NLP). This study offers insights for improving cross-lingual NLP applications through the combination…

We investigate how large language models perform on low-resource languages by benchmarking eight LLMs across five experimental conditions in English, Kazakh, and Mongolian. Using 50 hand-crafted questions spanning factual, reasoning,…

Text-to-audio grounding (TAG) task aims to predict the onsets and offsets of sound events described by natural language. This task can facilitate applications such as multimodal information retrieval. This paper focuses on weakly-supervised…

This study investigates the use of Visually Grounded Speech (VGS) models for keyword localisation in speech. The study focusses on two main research questions: (1) Is keyword localisation possible with VGS models and (2) Can keyword…

Most social media users come from the Global South, where harmful content usually appears in local languages. Yet, AI-driven moderation systems struggle with low-resource languages spoken in these regions. Through semi-structured interviews…

We present an algorithm that automatically learns context constraints using statistical decision trees. We then use the acquired constraints in a flexible POS tagger. The tagger is able to use information of any degree: n-grams,…

Text spotting end-to-end methods have recently gained attention in the literature due to the benefits of jointly optimizing the text detection and recognition components. Existing methods usually have a distinct separation between the…

Speech-to-text translation has many potential applications for low-resource languages, but the typical approach of cascading speech recognition with machine translation is often impossible, since the transcripts needed to train a speech…