no code implementations • EMNLP (DeeLIO) 2020 • Basemah Alshemali, Jugal Kalita
Our findings show that replacing the embeddings of the important words in the input samples with the average of their synonyms’ embeddings can significantly improve the generalization of DNN-based classifiers.
no code implementations • ICON 2020 • Kaden Griffith, Jugal Kalita
This paper outlines the use of Transformer networks trained to translate math word problems to equivalent arithmetic expressions in infix, prefix, and postfix notations.
no code implementations • 28 Mar 2024 • Atnafu Lambebo Tonja, Olga Kolesnikova, Alexander Gelbukh, Jugal Kalita
Recent research in natural language processing (NLP) has achieved impressive performance in tasks such as machine translation (MT), news classification, and question-answering in high-resource languages.
1 code implementation • 9 Feb 2024 • Joshua Zingale, Jugal Kalita
Controlled text generation (CTG) seeks to guide large language model (LLM) output to produce text that conforms to desired criteria.
1 code implementation • 29 Dec 2023 • Logan Golia, Jugal Kalita
In addition, this paper introduces three novel methods for dividing up long transcripts into topic-based sections to improve the time efficiency of our algorithm, as well as to resolve the issue of large language models (LLMs) forgetting long-term dependencies.
no code implementations • 8 Dec 2023 • Atnafu Lambebo Tonja, Melkamu Mersha, Ananya Kalita, Olga Kolesnikova, Jugal Kalita
This paper presents the creation of initial bilingual corpora for thirteen very low-resource languages of India, all from Northeast India.
no code implementations • 20 Oct 2023 • Hellina Hailu Nigatu, Atnafu Lambebo Tonja, Jugal Kalita
Multilingual Language Models offer a way to incorporate multiple languages in one model and utilize cross-language transfer learning to improve performance for different Natural Language Processing (NLP) tasks.
no code implementations • 24 Jul 2023 • Abby Newcomb, Jugal Kalita
Automated math word problem solvers based on neural networks have successfully managed to obtain 70-80\% accuracy in solving arithmetic word problems.
1 code implementation • 1 Jun 2023 • Aaron Serianni, Jugal Kalita
Ultimately, our analysis shows that the architecture search space and the training-free metric must be developed together in order to achieve effective results.
no code implementations • 27 May 2023 • Atnafu Lambebo Tonja, Hellina Hailu Nigatu, Olga Kolesnikova, Grigori Sidorov, Alexander Gelbukh, Jugal Kalita
This paper describes CIC NLP's submission to the AmericasNLP 2023 Shared Task on machine translation systems for indigenous languages of the Americas.
no code implementations • 23 May 2023 • Khang Nhut Lam, Thieu Gia Doan, Khang Thua Pham, Jugal Kalita
This paper presents a straightforward but effective technique to improve abstractive summaries by fine-tuning pre-trained language models, and training them with the BRIO paradigm.
no code implementations • 5 May 2023 • Daniel Boyle, Jugal Kalita
Financial markets are an intriguing place that offer investors the potential to gain large profits if timed correctly.
no code implementations • 24 Dec 2022 • Gabriel Mantione-Holmes, Justin Leo, Jugal Kalita
While efforts are being made to quell catastrophic forgetting, there is a lack of research that looks into the importance of class ordering when training on new classes for incremental learning.
no code implementations • 22 Dec 2022 • Dan DeGenaro, Jugal Kalita
Large language models having hundreds of millions, and even billions, of parameters have performed extremely well on a variety of natural language processing (NLP) tasks.
no code implementations • 12 Aug 2022 • Khang Nhut Lam, Nguyen Hoang Huynh, Nguyen Bao Ngoc, To Thi Huynh Nhu, Nguyen Thanh Thao, Pham Hoang Hao, Vo Van Kiet, Bui Xuan Huynh, Jugal Kalita
The research reported in this paper transforms a normal trash bin into a smarter one by applying computer vision technology.
no code implementations • 12 Aug 2022 • Khang Nhut Lam, Feras Al Tarouti, Jugal Kalita
This paper proposes approaches to automatically create a large number of new bilingual dictionaries for low-resource languages, especially resource-poor and endangered languages, from a single input bilingual dictionary.
no code implementations • 12 Aug 2022 • Khang Nhut Lam, Nam Nhat Le, Jugal Kalita
In this study, we build a chatbot system in a closed domain with the RASA framework, using several models such as SVM for classifying intents, CRF for extracting entities and LSTM for predicting action.
no code implementations • 12 Aug 2022 • Khang Nhut Lam, Kim-Ngoc Thi Nguyen, Loc Huu Nguy, Jugal Kalita
Our study shows that YOLOv5 achieves better results than a traditional CNN for all emotions on the KDEF dataset.
no code implementations • ACL 2014 • Khang Nhut Lam, Feras Al Tarouti, Jugal Kalita
Manually constructing a Wordnet is a difficult task, needing years of experts' time.
no code implementations • NAACL 2013 • Khang Nhut Lam, Jugal Kalita
Bilingual dictionaries are expensive resources and not many are available when one of the languages is resource-poor.
no code implementations • WS 2014 • Khang Nhut Lam, Feras Al Tarouti, Jugal Kalita
This paper examines approaches to generate lexical resources for endangered languages.
no code implementations • WS 2015 • Khang Nhut Lam, Feras Al Tarouti, Jugal Kalita
Past approaches to translate a phrase in a language L1 to a language L2 using a dictionary-based approach require grammar rules to restructure initial translations.
no code implementations • ICON 2021 • Wes Robbins, Zanyar Zohourianshahzadi, Jugal Kalita
To address this, recent work has used optical character recognition to supplement visual information with text extracted from an image.
1 code implementation • 28 Jun 2022 • Zanyar Zohourianshahzadi, Jugal Kalita
Recently the use of self-attention has yielded to state-of-the-art results in vision-language tasks such as image captioning as well as natural language understanding and generation (NLU and NLG) tasks and computer vision tasks such as image classification.
no code implementations • ICON 2021 • Abigail Swenor, Jugal Kalita
After applying our defense methods, the accuracy of the model is returned to the original accuracy within statistical significance.
no code implementations • 21 Jun 2021 • Justin Leo, Jugal Kalita
This in turn leads to the concept of incremental learning where a model with its own architecture and initial trained set of data can identify unknown classes during the testing phase and autonomously update itself if evidence of a new class is detected.
no code implementations • ICON 2020 • Thomas Conley, Jugal Kalita
Artificial Neural networks are mathematical models at their core.
no code implementations • 4 Jun 2021 • Thomas Conley, Jack St. Clair, Jugal Kalita
This research joins the quest by creating a dialog generating Recurrent Neural Network (RNN) and by enhancing the ability of this network with auxiliary loss functions and a beam search.
no code implementations • 2 Jun 2021 • Kaden Griffith, Jugal Kalita
This paper outlines the use of Transformer networks trained to translate math word problems to equivalent arithmetic expressions in infix, prefix, and postfix notations.
no code implementations • 30 Oct 2020 • Ahmed Bensaoud, Nawaf Abudawaood, Jugal Kalita
In this paper, we use several convolutional neural network (CNN) models for static malware classification.
no code implementations • 22 Jul 2020 • Joseph Worsham, Jugal Kalita
Multi-task learning (MTL) significantly pre-dates the deep learning era, and it has seen a resurgence in the past few years as researchers have been applying MTL to deep learning solutions for natural language tasks.
no code implementations • 3 Jul 2020 • Roger Barrull, Jugal Kalita
The lack of diversity in the datasets available for automatic summarization of documents has meant that the vast majority of neural models for automatic summarization have been trained with news articles.
1 code implementation • ICON 2019 • Brendan Bena, Jugal Kalita
Specifically, we generate poems that express emotion and elicit the same in readers, and poems that use the language of dreams---called dream poetry.
no code implementations • 7 Dec 2019 • Tiffany Chien, Jugal Kalita
So it is no surprise that many adversarial (challenge) datasets have been created that cause models trained on standard datasets to fail dramatically.
1 code implementation • 2 Dec 2019 • Kaden Griffith, Jugal Kalita
This paper outlines the use of Transformer networks trained to translate math word problems to equivalent arithmetic expressions in infix, prefix, and postfix notations.
no code implementations • 28 Oct 2019 • Justin Leo, Jugal Kalita
This paper also develops a new metric that measures multiple attributes of clustering open set data.
no code implementations • 19 Sep 2019 • Basemah Alshemali, Alta Graham, Jugal Kalita
Neural networks are frequently used for image classification, but can be vulnerable to misclassification caused by adversarial images.
no code implementations • 25 Dec 2018 • Krishan Rajaratnam, Jugal Kalita
Limited-vocabulary speech classifiers, such as the Speech Commands model, are used quite frequently in a variety of applications, particularly in managing automated attendants in telephony contexts.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 29 Oct 2018 • Julian Richard Medina, Jugal Kalita
Recent papers in neural machine translation have proposed the strict use of attention mechanisms over previous standards such as recurrent and convolutional neural networks (RNNs and CNNs).
2 code implementations • 20 Oct 2018 • Jacob Krantz, Jugal Kalita
However, we show that these metrics are limited in their ability to effectively score abstractive summaries, and propose a new approach based on the intuition that an abstractive model requires an abstractive evaluation.
1 code implementation • 20 Oct 2018 • Mehdi Drissi, Olivia Watkins, Jugal Kalita
We find that the usage of an outline improves perplexity.
no code implementations • 16 Oct 2018 • Adly Templeton, Jugal Kalita
To our knowledge, this is the first time specific dimensions of sentence embeddings have been connected to sentence properties.
no code implementations • ROCLINGIJCLCLP 2018 • Krishan Rajaratnam, Kunal Shah, Jugal Kalita
In 2017, a genetic attack was shown to be quite potent against the Speech Commands Model.
no code implementations • COLING 2018 • Joseph Worsham, Jugal Kalita
We introduce the Gutenberg Dataset for Genre Identification.
no code implementations • ICLR 2018 • Adly Templeton, Jugal Kalita
Vector semantics, especially sentence vectors, have recently been used successfully in many areas of natural language processing.
2 code implementations • 9 Mar 2017 • Marc Moreno Lopez, Jugal Kalita
Convolutional Neural Network (CNNs) are typically associated with Computer Vision.
no code implementations • 15 Jan 2016 • Jugal Kalita
Events of various kinds are mentioned and discussed in text documents, whether they are books, news articles, blogs or microblog feeds.