Search Results for author:
Found 95 papers, 26 papers with code
Linguistically-Motivated Yorùbá-English Machine Translation
In this work, we perform fine-grained analysis on how an SMT system compares with two NMT systems (BiLSTM and Transformer) when translating bare nouns in Yorùbá into English.
Interplay of Machine Translation, Diacritics, and Diacritization
We examine these two questions in both high-resource (HR) and low-resource (LR) settings across 55 different languages (36 African languages and 19 European languages).
Distilling Text Style Transfer With Self-Explanation From LLMs
Text Style Transfer (TST) seeks to alter the style of text while retaining its core content.
Peacock: A Family of Arabic Multimodal Large Language Models and Benchmarks
Multimodal large language models (MLLMs) have proven effective in a wide range of tasks requiring complex reasoning and linguistic comprehension.
GreenLLaMA: A Framework for Detoxification with Explanations
We then train a suite of detoxification models with our cross-platform corpus.
SPAR: Personalized Content-Based Recommendation via Long Engagement Attention
Leveraging users' long engagement histories is essential for personalized content recommendations.
FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models
We introduce FinTral, a suite of state-of-the-art multimodal large language models (LLMs) built upon the Mistral-7b model and tailored for financial analysis.
Cheetah: Natural Language Generation for 517 African Languages
The findings of this study contribute to advancing NLP research in low-resource settings, enabling greater accessibility and inclusion for African languages in a rapidly expanding digital landscape.
Beyond English: Evaluating LLMs for Arabic Grammatical Error Correction
Our best model achieves a new SOTA on Arabic GEC, with $73. 29$ and $73. 26$ F$_{1}$ on the 2014 and 2015 QALB datasets, respectively, compared to peer-reviewed published baselines.
CalliPaint: Chinese Calligraphy Inpainting with Diffusion Model
Chinese calligraphy can be viewed as a unique form of visual art.
Fumbling in Babel: An Investigation into ChatGPT's Language Identification Ability
However, the range of languages ChatGPT can handle remains largely a mystery.
Violet: A Vision-Language Model for Arabic Image Captioning with Gemini Decoder
We also manually prepare a new dataset for evaluation.
ProMap: Effective Bilingual Lexicon Induction via Language Model Prompting
We also demonstrate the effectiveness of ProMap in re-ranking results from other BLI methods such as with aligned static word embeddings.
Arabic Fine-Grained Entity Recognition
To compute the baselines of WojoodF ine, we fine-tune three pre-trained Arabic BERT encoders in three settings: flat NER, nested NER and nested NER with subtypes and achieved F1 score of 0. 920, 0. 866, and 0. 885, respectively.
LLM Performance Predictors are good initializers for Architecture Search
We show that HS-NAS performs very similar to SOTA NAS across benchmarks, reduces search hours by 50% roughly, and in some cases, improves latency, GFLOPs, and model size.
NADI 2023: The Fourth Nuanced Arabic Dialect Identification Shared Task
We describe the findings of the fourth Nuanced Arabic Dialect Identification Shared Task (NADI 2023).
Octopus: A Multitask Model and Toolkit for Arabic Natural Language Generation
While many researchers have proposed models and solutions for individual problems, there is an acute shortage of a comprehensive Arabic natural language generation toolkit that is capable of handling a wide range of tasks.
WojoodNER 2023: The First Arabic Named Entity Recognition Shared Task
The winning teams achieved F1 scores of 91. 96 and 93. 73 in FlatNER and NestedNER, respectively.
The Skipped Beat: A Study of Sociopragmatic Understanding in LLMs for 64 Languages
We evaluate the performance of various multilingual pretrained language models (e. g., mT5) and instruction-tuned LLMs (e. g., BLOOMZ, ChatGPT) on SPARROW through fine-tuning, zero-shot, and/or few-shot learning.
VoxArabica: A Robust Dialect-Aware Arabic Speech Recognition System
We train a wide range of models such as HuBERT (DID), Whisper, and XLS-R (ASR) in a supervised setting for Arabic DID and ASR tasks.
ChatGPT for Arabic Grammatical Error Correction
Recently, large language models (LLMs) fine-tuned to follow human instruction have exhibited significant capabilities in various English NLP tasks.
TARJAMAT: Evaluation of Bard and ChatGPT on Machine Translation of Ten Arabic Varieties
Our evaluation covers diverse Arabic varieties such as Classical Arabic (CA), Modern Standard Arabic (MSA), and several country-level dialectal variants.
Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts
In addition, the proposed method achieves the SOTA performance in NAS for building fast machine translation models, yielding better latency-BLEU tradeoff compared to HAT, state-of-the-art NAS for MT.
N-Shot Benchmarking of Whisper on Diverse Arabic Speech Recognition
Whisper, the recently developed multilingual weakly supervised model, is reported to perform well on multiple speech recognition benchmarks in both monolingual and multilingual settings.
On the Robustness of Arabic Speech Dialect Identification
As these pipelines require application of ADI tools to potentially out-of-domain data, we aim to investigate how vulnerable the tools may be to this domain shift.
GPTAraEval: A Comprehensive Evaluation of ChatGPT on Arabic NLP
Although we further explore and confirm the utility of employing GPT-4 as a potential alternative for human evaluation, our work adds to a growing body of research underscoring the limitations of ChatGPT.
Dolphin: A Challenging and Diverse Benchmark for Arabic NLG
We present Dolphin, a novel benchmark that addresses the need for a natural language generation (NLG) evaluation framework dedicated to the wide collection of Arabic languages and varieties.
LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions
The results demonstrate that our proposed LaMini-LM models are comparable to competitive baselines, while being much smaller in size.
Ranked #15 on
Word Sense Disambiguation
on Words in Context
Zero-Shot Slot and Intent Detection in Low-Resource Languages
Intent detection and slot filling are critical tasks in spoken and natural language understanding for task-oriented dialog systems.
UBC-DLNLP at SemEval-2023 Task 12: Impact of Transfer Learning on African Sentiment Analysis
We describe our contribution to the SemEVAl 2023 AfriSenti-SemEval shared task, where we tackle the task of sentiment analysis in 14 different African languages.
JASMINE: Arabic GPT Models for Few-Shot Learning
Scholarship on generative pretraining (GPT) remains acutely Anglocentric, leaving serious gaps in our understanding of the whole class of autoregressive models.
SERENGETI: Massively Multilingual Language Models for Africa
Multilingual pretrained language models (mPLMs) acquire valuable, generalizable linguistic information during pretraining and have advanced the state of the art on task-specific finetuning.
ORCA: A Challenging Benchmark for Arabic Language Understanding
Due to their crucial role in all NLP, several benchmarks have been proposed to evaluate pretrained language models.
Cross-Platform and Cross-Domain Abusive Language Detection with Supervised Contrastive Learning
The prevalence of abusive language on different online platforms has been a major concern that raises the need for automated cross-platform abusive language detection.
A Benchmark Study of Contrastive Learning for Arabic Social Meaning
Contrastive learning (CL) brought significant progress to various NLP tasks.
AfroLID: A Neural Language Identification Tool for African Languages
Problematically, most of the world's 7000+ languages today are not covered by LID technologies.
NADI 2022: The Third Nuanced Arabic Dialect Identification Shared Task
We describe findings of the third Nuanced Arabic Dialect Identification Shared Task (NADI 2022).
AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation
Furthermore, existing MoE works do not consider computational constraints (e. g., FLOPs, latency) to guide their design.
Small Character Models Match Large Word Models for Autocomplete Under Memory Constraints
In this work, we study the more challenging open-domain setting consisting of low frequency user prompt patterns (or broad prompts, e. g., prompt about 93rd academy awards) and demonstrate the effectiveness of character-based language models.
TURJUMAN: A Public Toolkit for Neural Arabic Machine Translation
We present TURJUMAN, a neural toolkit for translating from 20 languages into Modern Standard Arabic (MSA).
Improving Neural Machine Translation of Indigenous Languages with Multilingual Transfer Learning
Machine translation (MT) involving Indigenous languages, including those possibly endangered, is challenging due to lack of sufficient parallel data.
Decay No More: A Persistent Twitter Dataset for Learning Social Meaning
With the proliferation of social media, many studies resort to social media to construct datasets for developing social meaning understanding systems.
Automatic Detection of Entity-Manipulated Text using Factual Knowledge
We propose a neural network based detector that detects manipulated news articles by reasoning about the facts mentioned in the article.
Towards Afrocentric NLP for African Languages: Where We Are and Where We Can Go
Aligning with ACL 2022 special Theme on "Language Diversity: from Low Resource to Endangered Languages", we discuss the major linguistic and sociopolitical challenges facing development of NLP technologies for African languages.
Contrastive Learning of Sociopragmatic Meaning in Social Media
Recent progress in representation and contrastive learning in NLP has not widely considered the class of \textit{sociopragmatic meaning} (i. e., meaning in interaction within different language communities).
Improving Automatic Speech Recognition for Non-Native English with Transfer Learning and Language Model Decoding
ASR systems designed for native English (L1) usually underperform on non-native English (L2).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Speech Technology for Everyone: Automatic Speech Recognition for Non-Native English with Transfer Learning
To address the performance gap of English ASR models on L2 English speakers, we evaluate fine-tuning of pretrained wav2vec 2. 0 models (Baevski et al., 2020; Xu et al., 2021) on L2-ARCTIC, a non-native English speech corpus (Zhao et al., 2018) under different training settings.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
AraT5: Text-to-Text Transformers for Arabic Language Generation
For evaluation, we introduce a novel benchmark for ARabic language GENeration (ARGEN), covering seven important tasks.
Machine Translation of Low-Resource Indo-European Languages
In this work, we investigate methods for the challenging task of translating between low-resource language pairs that exhibit some level of similarity.
Low-Resource Neural Machine Translation
Transfer Learning
+1
Improving Similar Language Translation With Transfer Learning
We investigate transfer learning based on pre-trained neural machine translation models to translate between (low-resource) similar languages.
ARBERT \& MARBERT: Deep Bidirectional Transformers for Arabic
To evaluate our models, we also introduce ARLUE, a new benchmark for multi-dialectal Arabic language understanding evaluation.
Improving Social Meaning Detection with Pragmatic Masking and Surrogate Fine-Tuning
We test our models on $15$ different Twitter datasets for social meaning detection.
Investigating Code-Mixed Modern Standard Arabic-Egyptian to English Machine Translation
Our work is in the context of the Shared Task on Machine Translation in Code-Switching.
Exploring Text-to-Text Transformers for English to Hinglish Machine Translation with Synthetic Code-Mixing
We describe models focused at the understudied problem of translating between monolingual and code-mixed language pairs.
AraStance: A Multi-Country and Multi-Domain Dataset of Arabic Stance Detection for Fact Checking
With the continuing spread of misinformation and disinformation online, it is of increasing importance to develop combating mechanisms at scale in the form of automated systems that support multiple languages.
IndT5: A Text-to-Text Transformer for 10 Indigenous Languages
Transformer language models have become fundamental components of natural language processing based pipelines.
Translating the Unseen? Yoruba-English MT in Low-Resource, Morphologically-Unmarked Settings
In this work, we perform fine-grained analysis on how an SMT system compares with two NMT systems (BiLSTM and Transformer) when translating bare nouns in Yor\`ub\'a into English.
NADI 2021: The Second Nuanced Arabic Dialect Identification Shared Task
This Shared Task includes four subtasks: country-level Modern Standard Arabic (MSA) identification (Subtask 1. 1), country-level dialect identification (Subtask 1. 2), province-level MSA identification (Subtask 2. 1), and province-level sub-dialect identification (Subtask 2. 2).
Self-Training Pre-Trained Language Models for Zero- and Few-Shot Multi-Dialectal Arabic Sequence Labeling
We propose to self-train pre-trained language models in zero- and few-shot scenarios to improve performance on data-scarce varieties using only resources from data-rich ones.
ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic
To evaluate our models, we also introduce ARLUE, a new benchmark for multi-dialectal Arabic language understanding evaluation.
DiaLex: A Benchmark for Evaluating Multidialectal Arabic Word Embeddings
We describe DiaLex, a benchmark for intrinsic evaluation of dialectal Arabic word embedding.
Machine Generation and Detection of Arabic Manipulated and Fake News
Finally, we develop the first models for detecting manipulated Arabic news and achieve state-of-the-art results on Arabic fake news detection (macro F1=70. 06).
Automatic Detection of Machine Generated Text: A Critical Survey
Detectors that can distinguish text generated by TGM from human written text play a vital role in mitigating such misuse of TGMs.
NADI 2020: The First Nuanced Arabic Dialect Identification Shared Task
The data for the shared task covers a total of 100 provinces from 21 Arab countries and are collected from the Twitter domain.
Toward Micro-Dialect Identification in Diaglossic and Code-Switched Environments
Although the prediction of dialects is an important language processing task, with a wide range of applications, existing work is largely limited to coarse-grained varieties.
One Model to Pronounce Them All: Multilingual Grapheme-to-Phoneme Conversion With a Transformer Ensemble
The task of grapheme-to-phoneme (G2P) conversion is important for both speech recognition and synthesis.
Growing Together: Modeling Human Language Learning With n-Best Multi-Checkpoint Machine Translation
We describe our submission to the 2020 Duolingo Shared Task on Simultaneous Translation And Paraphrase for Language Education (STAPLE) (Mayhew et al., 2020).
Leveraging Affective Bidirectional Transformers for Offensive Language Detection
Social media are pervasive in our life, making it necessary to ensure safe online experiences by detecting and removing offensive and hate speech.
Understanding and Detecting Dangerous Speech in Social Media
Social media communication has become a significant part of daily activity in modern societies.
Mega-COV: A Billion-Scale Dataset of 100+ Languages for COVID-19
We describe Mega-COV, a billion-scale dataset from Twitter for studying COVID-19.
AraNet: A Deep Learning Toolkit for Arabic Social Media
We describe AraNet, a collection of deep learning Arabic social media processing tools.
Sentence-Level BERT and Multi-Task Learning of Age and Gender in Social Media
In this work we exploit a newly-created Arabic dataset with ground truth age and gender labels to learn these attributes both individually and in a multi-task setting at the sentence level.
DiaNet: BERT and Hierarchical Attention Multi-Task Learning of Fine-Grained Dialect
Prediction of language varieties and dialects is an important language processing task, with a wide range of applications.
BERT-Based Arabic Social Media Author Profiling
We report our models for detecting age, language variety, and gender from social media data in the context of the Arabic author profiling and deception detection shared task (APDA).
Multi-Task Bidirectional Transformer Representations for Irony Detection
Supervised deep learning requires large amounts of training data.
No Army, No Navy: BERT Semi-Supervised Learning of Arabic Dialects
We present our deep leaning system submitted to MADAR shared task 2 focused on twitter user dialect identification.
Neural Machine Translation of Low-Resource and Similar Languages with Backtranslation
We investigate the utility of neural machine translation on three low-resource, similar language pairs: Spanish {--} Portuguese, Czech {--} Polish, and Hindi {--} Nepali.
UBC-NLP at SemEval-2019 Task 6:Ensemble Learning of Offensive Content With Enhanced Training Data
We examine learning offensive content on Twitter with limited, imbalanced data.
Happy Together: Learning and Understanding Appraisal From Natural Language
In this paper, we explore various approaches for learning two types of appraisal components from happy language.
UBC-NLP at SemEval-2019 Task 6: Ensemble Learning of Offensive Content With Enhanced Training Data
We examine learning offensive content on Twitter with limited, imbalanced data.
UBC-NLP at SemEval-2019 Task 4: Hyperpartisan News Detection With Attention-Based Bi-LSTMs
We present our deep learning models submitted to the SemEval-2019 Task 4 competition focused at Hyperpartisan News Detection.
Deep Learning the EEG Manifold for Phonological Categorization from Active Thoughts
Speech-related Brain Computer Interfaces (BCI) aim primarily at finding an alternative vocal communication pathway for people with speaking disabilities.
SPEAK YOUR MIND! Towards Imagined Speech Recognition With Hierarchical Deep Learning
Speech-related Brain Computer Interface (BCI) technologies provide effective vocal communication strategies for controlling devices through speech commands interpreted from brain signals.
UBC-NLP at IEST 2018: Learning Implicit Emotion With an Ensemble of Language Models
We also offer an analysis of system performance and the impact of training data size on the task.
Deep Models for Arabic Dialect Identification on Benchmarked Data
We treat these two limitations:We (1) benchmark the data, and (2) empirically test6different deep learning methods on thetask, comparing peformance to several classical machine learning models under different condi-tions (i. e., both binary and multi-way classification).
Enabling Deep Learning of Emotion With First-Person Seed Expressions
The computational treatment of emotion in natural language text remains relatively limited, and Arabic is no exception.
EmoNet: Fine-Grained Emotion Detection with Gated Recurrent Neural Networks
Accurate detection of emotion from natural language has applications ranging from building emotional chatbots to better understanding individuals and their lives.
Not All Segments are Created Equal: Syntactically Motivated Sentiment Analysis in Lexical Space
Although there is by now a considerable amount of research on subjectivity and sentiment analysis on morphologically-rich languages, it is still unclear how lexical information can best be modeled in these languages.
SANA: A Large Scale Multi-Genre, Multi-Dialect Lexicon for Arabic Subjectivity and Sentiment Analysis
The computational treatment of subjectivity and sentiment in natural language is usually significantly improved by applying features exploiting lexical resources where entries are tagged with semantic orientation (e. g., positive, negative values).
AWATIF: A Multi-Genre Corpus for Modern Standard Arabic Subjectivity and Sentiment Analysis
We present AWATIF, a multi-genre corpus of Modern Standard Arabic (MSA) labeled for subjectivity and sentiment analysis (SSA) at the sentence level.
