Related papers: Building Odia Shallow Parser
The paper reviews the hurdles while trying to implement the OLAC extension for Dravidian / Indian languages. The paper further explores the possibilities which could minimise or solve these problems. In this context, the Chinese system of…
Developing explainability methods for Natural Language Processing (NLP) models is a challenging task, for two main reasons. First, the high dimensionality of the data (large number of tokens) results in low coverage and in turn small…
Singlish, or Colloquial Singapore English, is a language formed from oral and social communication within multicultural Singapore. In this work, we work on a fundamental Natural Language Processing (NLP) task: Parts-Of-Speech (POS) tagging…
Semantic segmentation is an import task in the medical field to identify the exact extent and orientation of significant structures like organs and pathology. Deep neural networks can perform this task well by leveraging the information…
Pixel-wise annotations are notoriously labourious and costly to obtain in the medical domain. To mitigate this burden, weakly supervised approaches based on bounding box annotations-much easier to acquire-offer a practical alternative.…
Academic research tends to focus on new models for document understanding creating a wide gap in the literature between model definition and running models at production scale. To close that gap, we present a microservice architecture that…
The integration of Large Language Models (LLMs) into autonomous driving systems offers promising enhancements in environmental understanding and decision-making. However, the substantial computational demands of deploying LLMs locally on…
We investigate the question of whether advances in NLP over the last few years make it possible to vastly increase the size of data usable for research in historical syntax. This brings together many of the usual tools in NLP - word…
Cloze task is a widely used task to evaluate an NLP system's language understanding ability. However, most of the existing cloze tasks only require NLP systems to give the relative best prediction for each input data sample, rather than the…
This paper introduces UQA, a novel dataset for question answering and text comprehension in Urdu, a low-resource language with over 70 million native speakers. UQA is generated by translating the Stanford Question Answering Dataset…
Ontologies are useful for automatic machine processing of domain knowledge as they represent it in a structured format. Yet, constructing ontologies requires substantial manual effort. To automate part of this process, large language models…
Transliteration is a task in the domain of NLP where the output word is a similar-sounding word written using the letters of any foreign language. Today this system has been developed for several language pairs that involve English as…
Speculative decoding accelerates Large Language Model (LLM) inference by using a small draft model to predict multiple tokens, and a large target model to verify these tokens in parallel. Recent studies leverage the hidden state of the…
Classical OCR pipelines decompose document reading into detection, segmentation, and recognition stages, which makes them sensitive to localization errors and difficult to extend to interactive querying. This work investigates whether a…
Indecipherable black boxes are common in machine learning (ML), but applications increasingly require explainable artificial intelligence (XAI). The core of XAI is to establish transparent and interpretable data-driven algorithms. This work…
Optical Character Recognition (OCR) systems have been widely used in various of application scenarios. Designing an OCR system is still a challenging task. In previous work, we proposed a practical ultra lightweight OCR system (PP-OCR) to…
Document Layout analysis (DLA), is the process by which a page is parsed into meaningful elements, often using machine learning models. Typically, the quality of a model is judged using general object detection metrics such as IoU, F1 or…
Training datasets for semantic parsing are typically small due to the higher expertise required for annotation than most other NLP tasks. As a result, models for this application usually need additional prior knowledge to be built into the…
This document describes a couple of tools that help to quickly design and develop computer (formalized) languages. The first one use Flex to perform lexical analysis and the second is an extention of Prolog DCGs to perfom syntactical…
Complex feature extractors are widely employed for text representation building. However, these complex feature extractors make the NLP systems prone to overfitting especially when the downstream training datasets are relatively small,…