Search Results for author:
Found 50 papers, 7 papers with code
Generalization to Mitigate Synonym Substitution Attacks
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.
Solving Arithmetic Word Problems Using Transformer and Pre-processing of Problem Texts
This paper outlines the use of Transformer networks trained to translate math word problems to equivalent arithmetic expressions in infix, prefix, and postfix notations.
Explaining Math Word Problem Solvers
Automated math word problem solvers based on neural networks have successfully managed to obtain 70-80\% accuracy in solving arithmetic word problems.
Training-free Neural Architecture Search for RNNs and Transformers
Ultimately, our analysis shows that the architecture search space and the training-free metric must be developed together in order to achieve effective results.
Enhancing Translation for Indigenous Languages: Experiments with Multilingual Models
This paper describes CIC NLP's submission to the AmericasNLP 2023 Shared Task on machine translation systems for indigenous languages of the Americas.
Abstractive Text Summarization Using the BRIO Training Paradigm
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.
Spatiotemporal Transformer for Stock Movement Prediction
Financial markets are an intriguing place that offer investors the potential to gain large profits if timed correctly.
Utilizing Priming to Identify Optimal Class Ordering to Alleviate Catastrophic Forgetting
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.
CAMeMBERT: Cascading Assistant-Mediated Multilingual BERT
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.
Building a Chatbot on a Closed Domain using RASA
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.
Facial Expression Recognition and Image Description Generation in Vietnamese
Our study shows that YOLOv5 achieves better results than a traditional CNN for all emotions on the KDEF dataset.
Automatically Creating a Large Number of New Bilingual Dictionaries
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.
Using Artificial Intelligence and IoT for Constructing a Smart Trash Bin
The research reported in this paper transforms a normal trash bin into a smarter one by applying computer vision technology.
Creating Reverse Bilingual Dictionaries
Bilingual dictionaries are expensive resources and not many are available when one of the languages is resource-poor.
Creating Lexical Resources for Endangered Languages
This paper examines approaches to generate lexical resources for endangered languages.
Automatically constructing Wordnet synsets
Manually constructing a Wordnet is a difficult task, needing years of experts' time.
Phrase translation using a bilingual dictionary and n-gram data: A case study from Vietnamese to English
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.
Towards Multimodal Vision-Language Models Generating Non-Generic Text
To address this, recent work has used optical character recognition to supplement visual information with text extracted from an image.
ZoDIAC: Zoneout Dropout Injection Attention Calculation
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.
Using Random Perturbations to Mitigate Adversarial Attacks on Sentiment Analysis Models
After applying our defense methods, the accuracy of the model is returned to the original accuracy within statistical significance.
Incremental Deep Neural Network Learning using Classification Confidence Thresholding
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.
Improving Computer Generated Dialog with Auxiliary Loss Functions and Custom Evaluation Metrics
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.
Language Model Metrics and Procrustes Analysis for Improved Vector Transformation of NLP Embeddings
Artificial Neural networks are mathematical models at their core.
Solving Arithmetic Word Problems with Transformers and Preprocessing of Problem Text
This paper outlines the use of Transformer networks trained to translate math word problems to equivalent arithmetic expressions in infix, prefix, and postfix notations.
Classifying Malware Images with Convolutional Neural Network Models
In this paper, we use several convolutional neural network (CNN) models for static malware classification.
Multi-task learning for natural language processing in the 2020s: where are we going?
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.
Abstractive and mixed summarization for long-single documents
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.
Introducing Aspects of Creativity in Automatic Poetry Generation
Specifically, we generate poems that express emotion and elicit the same in readers, and poems that use the language of dreams---called dream poetry.
Adversarial Analysis of Natural Language Inference Systems
So it is no surprise that many adversarial (challenge) datasets have been created that cause models trained on standard datasets to fail dramatically.
Solving Arithmetic Word Problems Automatically Using Transformer and Unambiguous Representations
This paper outlines the use of Transformer networks trained to translate math word problems to equivalent arithmetic expressions in infix, prefix, and postfix notations.
Moving Towards Open Set Incremental Learning: Readily Discovering New Authors
This paper also develops a new metric that measures multiple attributes of clustering open set data.
Toward Robust Image Classification
Neural networks are frequently used for image classification, but can be vulnerable to misclassification caused by adversarial images.
Noise Flooding for Detecting Audio Adversarial Examples Against Automatic Speech Recognition
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
Parallel Attention Mechanisms in Neural Machine Translation
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).
Hierarchical Text Generation using an Outline
We find that the usage of an outline improves perplexity.
Abstractive Summarization Using Attentive Neural Techniques
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.
Exploring Sentence Vector Spaces through Automatic Summarization
To our knowledge, this is the first time specific dimensions of sentence embeddings have been connected to sentence properties.
Isolated and Ensemble Audio Preprocessing Methods for Detecting Adversarial Examples against Automatic Speech Recognition
In 2017, a genetic attack was shown to be quite potent against the Speech Commands Model.
Genre Identification and the Compositional Effect of Genre in Literature
We introduce the Gutenberg Dataset for Genre Identification.
Exploring Sentence Vectors Through Automatic Summarization
Vector semantics, especially sentence vectors, have recently been used successfully in many areas of natural language processing.
Deep Learning applied to NLP
Convolutional Neural Network (CNNs) are typically associated with Computer Vision.
Detecting and Extracting Events from Text Documents
Events of various kinds are mentioned and discussed in text documents, whether they are books, news articles, blogs or microblog feeds.
