Hassan Sajjad

Latest

• Evaluating Neuron Interpretation Methods of NLP Models
• Impact of Adversarial Training on Robustness and Generalizability of Language Models
• NeuroX Library for Neuron Analysis of Deep NLP Models
• Learning Uncertainty for Unknown Domains with Zero-Target-Assumption
• NxPlain: A Web-based Tool for Discovery of Latent Concepts
• Discovering Salient Neurons in deep NLP models
• On the Transformation of Latent Space in Fine-Tuned NLP Models
• Probing for Constituency Structure in Neural Language Models
• Post-hoc analysis of Arabic transformer models
• Effect of Post-processing on Contextualized Word Representations
• Analyzing Encoded Concepts in Transformer Language Models
• Discovering Latent Concepts Learned in BERT
• Neuron-level Interpretation of Deep NLP Models: A Survey
• On the Effect of Dropping Layers of Pre-trained Transformer Models
• When a Disaster Happens, We are Ready: Location Mention Recognition from Crisis Tweets
• How transfer learning impacts linguistic knowledge in deep NLP models?
• CrisisBench: Benchmarking Crisis-related Social Media Datasets for Humanitarian Information Processing
• Fighting the COVID-19 Infodemic in Social Media: A Holistic Perspective and a Call to Arms
• Fine-grained Interpretationand Causation Analysis in Deep NLP Models
• Implicit Representations of Event Properties within Contextual Language Models:Searching for ``Causativity Neurons"
• Compressing Large-Scale Transformer-Based Models: A Case Study on BERT
• AraBench: Benchmarking Dialectal Arabic-English Machine Translation
• Are We Ready for this Disaster? Towards Location Mention Recognition from Crisis Tweets
• Analyzing Individual Neurons in Pre-trained Language Models
• Analyzing Redundancy in Pretrained Transformer Models
• Similarity Analysis of Contextual Word Representation Models
• A Clustering Framework for Lexical Normalization of Roman Urdu
• On the Linguistic Representational Power of Neural Machine Translation Models
• A System for Diacritizing Four Varieties of Arabic
• Findings of the WMT 2019 Shared Task on Machine Translation Robustness.
• Highly Effective Arabic Diacritization using Sequence to Sequence Modeling
• One Size Does Not Fit All: Comparing NMT Representations of Different Granularities
• Identifying and Controlling Important Neurons in Neural Machine Translation
• What is one Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models
• NeuroX: A Toolkit for Analyzing Individual Neurons in Neural Networks
• Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translation
• H2@BUCC18: Parallel Sentence Extraction from Comparable Corpora Using Multilingual Sentence Embeddings
• Neural Machine Translation Training in a Multi-Domain Scenario
• Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks
• Understanding and Improving Morphological Learning in the Neural Machine Translation Decoder
• Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging
• What do Neural Machine Translation Models Learn about Morphology?
• Robust Classification of Crisis-Related Data on Social Networks using Convolutional Neural Networks
• QCRI Live Speech Translation System
• Domain Adaptation using Neural Network Joint Model
• Statistical models for unsupervised, semi-supervised and supervised transliteration mining
• A Deep Fusion Model for Domain Adaptation in Phrase-based MT
• QCRI @ DSL 2016: Spoken Arabic Dialect Identification Using Textual
• QCRI’s Machine Translation Systems for IWSLT’2016
• An Empirical Study: Post-editing Effort for English to Arabic Hybrid Machine Translation
• Applications of Online Deep Learning for Crisis Response Using Social Media Information
• Normalizing Mathematical Expressions to Improve the Translation of Educational Content
• Eyes Don't Lie: Predicting Machine Translation Quality Using Eye Movement.
• Using Joint Models for Domain Adaptation in Statistical Machine Translation
• An Unsupervised Method for Discovering Lexical Variations in Roman Urdu Informal Text.
• How do Humans Evaluate Machine Translation
• How to Avoid Unwanted Pregnancies: Domain Adaptation using Neural Network Models
• QCMUQ@QALB-2015 Shared Task: Combining Character level MT and Error-tolerant Finite-State Recognition for ArabicSpelling Correction
• QCN Egyptian Arabic to English MachineTranslation System for NIST OpenMT15
• Distant Supervision for Tweet Classification Using YouTube Labels
• Bridging social media via distant supervision
• Unsupervised word segmentation improves dialectal Arabic to English machine translation
• Verifiably Effective Arabic Dialect Identification.
• The AMARA Corpus: Building Parallel Language Resources for the Educational Domain
• Understanding Types of Users on Twitter
• Integrating an Unsupervised Transliteration Model into Statistical Machine Translation
• QCRI at IWSLT 2013: Experiments in Arabic-English and English-Arabic Spoken Language Translation
• The AMARA Corpus: Building Resources for Translating the Web's Educational Content
• Munich-Edinburgh-Stuttgart Submissions at WMT13: Morphological and Syntactic Processing for SMT
• Munich-Edinburgh-Stuttgart Submissions of OSM Systems at WMT13
• QCRI-MES Submission at WMT13: Using Transliteration Mining to Improve Statistical Machine Translation
• Translating Dialectal Arabic to English
• Underspecified Query Refinement via Natural Language Question Generation
• A Statistical Model for Unsupervised and Semi-supervised Transliteration Mining
• Comparing Two Techniques for Learning Transliteration Models Using a Parallel Corpus
• An Algorithm for Unsupervised Transliteration Mining with an Application to Word Alignment
• Hindi-to-Urdu Machine Translation through Transliteration
• Tagging Urdu Text with Parts of Speech: A Tagger Comparison