Diptesh Kanojia

Latest

• Findings of the WMT25 Shared Task on Automated Translation Evaluation Systems: Linguistic Diversity is Challenging and References Still Help
• The Tabby Autocrat
• ALOPE: Adaptive Layer Optimization for Translation Quality Estimation using Large Language Models
• Reference-Less Evaluation of Machine Translation: Navigating Through the Resource-Scarce Scenarios
• ALOPE: Adaptive Layer Optimization for Translation Quality Estimation using Large Language Models
• Cyberbullying Detection via Aggression-Enhanced Prompting
• The Mind's Eye: A Multi-Faceted Reward Framework for Guiding Visual Metaphor Generation
• BESSTIE: A Benchmark for Sentiment and Sarcasm Classification for Varieties of English
• NEAR²: A Nested Embedding Approach to Efficient Product Retrieval and Ranking
• Prompt-based Explainable Quality Estimation for English-Malayalam
• From Search Relevance to Content Safety
• Towards a Robust Framework for Multimodal Hate Detection: A Study on Video vs. Image-based Content
• Automatically Generating Chinese Homophone Words to Probe Machine Translation Estimation Systems
• Giving the Old a Fresh Spin: Quality Estimation-Assisted Constrained Decoding for Automatic Post-Editing
• CAMU: Context Augmentation for Meme Understanding
• Unsupervised Audio-Visual Segmentation with Modality Alignment
• DGFM: Full Body Dance Generation Driven by Music Foundation Models
• GCDance: Genre-Controlled 3D Full Body Dance Generation Driven By Music
• Natural Language Processing for Dialects of a Language: A Survey
• Connecting Ideas in Lower-Resource Scenarios: NLP for National Varieties, Creoles, and Other Low-resource Languages
• Refer to the Reference: Reference-focused Synthetic Automatic Post-Editing Data Generation
• When LLMs Struggle: Reference-less Translation Evaluation for Low-resource Languages
• PortraitTalk: Towards Customizable One-Shot Audio-to-Talking Face Generation
• AV-GS: Learning Material and Geometry aware Priors for Novel View Acoustic Synthesis
• StableTalk: Advancing Audio-to-Talking Face Generation with Stable Diffusion and Vision Transformer
• A Multi-task Learning Framework for Evaluating Machine Translation of Emotion-loaded User-generated Content
• Are Large Language Models State-of-the-art Quality Estimators for Machine Translation of User-generated Content?
• Findings of the Quality Estimation Shared Task at WMT 2024: Are LLMs Closing the Gap in QE?
• Centrality-aware Product Retrieval and Ranking
• Together We Can: Multilingual Automatic Post-Editing for Low-Resource Languages
• What do Large Language Models Need for Machine Translation Evaluation?
• Product Retrieval and Ranking for Alphanumeric Queries
• Experiences from Creating a Benchmark for Sentiment Classification for Varieties of English
• Sampling Strategies for Creation of a Benchmark for Dialectal Sentiment Classification
• Edit Distances and Their Applications to Downstream Tasks in Research and Commercial Contexts
• Connecting Ideas in 'Lower-Resource' Scenarios: NLP for National Varieties, Creoles and Other Low-resource Scenarios
• A Survey of Multimodal Sarcasm Detection
• Optimizing Quality Estimation for Low-Resource Language Translations: Exploring the Role of Language Relatedness
• Evaluating Machine Translation for Emotion-loaded User Generated Content (TransEval4Emo-UGC)
• Decoding Cyberbullying on Social Media: A Machine Learning Exploration
• Using character-level models for efficient abbreviation and long-form detection
• DiffSED: Sound Event Detection with Denoising Diffusion
• Google Translate Error Analysis for Mental Healthcare Information: Evaluating Accuracy, Comprehensibility, and Implications for Multilingual Healthcare Communication
• Generative AI and Natural Language Processing
• Airavata: Introducing Hindi Instruction-tuned LLM
• CreoleVal: Multilingual Multitask Benchmarks for Creoles
• APE-then-QE: Correcting then Filtering Pseudo Parallel Corpora for MT Training Data Creation
• Findings of the WMT 2023 Shared Task on Automatic Post-Editing
• Findings of the WMT 2023 Shared Task on Quality Estimation
• Predict and Use: Harnessing Predicted Gaze to Improve Multimodal Sarcasm Detection
• Quality Estimation-Assisted Automatic Post-Editing
• SurreyAI 2023 Submission for the Quality Estimation Shared Task
• Sarcasm in Sight and Sound: Benchmarking and Expansion to Improve Multimodal Sarcasm Detection
• Efficient and Explainable Information Retrieval
• Challenges of Human vs Machine Translation of Emotion-Loaded Chinese Microblog Texts
• Leveraging Foundation Models for Unsupervised Audio-Visual Segmentation
• Modelling Political Aggression on Social Media Platforms
• Towards Safer Communities: Detecting Aggression and Offensive Language in Code-Mixed Tweets to Combat Cyberbullying
• A Multi-task Learning Framework for Quality Estimation
• Evaluation of Chinese-English Machine Translation of Emotion-Loaded Microblog Texts: A Human Annotated Dataset for the Quality Assessment of Emotion Translation
• Advances in Natural Language Processing @ Surrey
• Workshop: Teaching Neural Machine Translation to Translators
• Quality Estimation for Machine Translation
• Applications and Challenges of Sentiment Analysis in Real-life Scenarios
• Findings of the WMT 2022 Shared Task on Automatic Post-Editing
• Findings of the WMT 2022 Shared Task on Quality Estimation
• Utilizing Weak Supervision to Create S3D: A Sarcasm Annotated Dataset
• Cognitive Natural Language Processing
• Quality Estimation
• Dialouge Processing: The role of NLP and building blocks of a chatbot
• Harnessing Abstractive Summarization for Fact-Checked Claim Detection
• Transformers: Perspectives from NLP
• HiNER: A Large Hindi Named Entity Recognition Dataset
• PLOD: An Abbreviation Detection Dataset for Scientific Documents
• SURREY-CTS-NLP at WASSA2022: An Experiment of Discourse and Sentiment Analysis for the Prediction of Empathy, Distress and Emotion
• Introducing Neural Machine Translation (NMT) to Translators
• An Ensemble Approach to Acronym Extraction using Transformers
• Quality Estimation for Machine Translation
• Automated Evidence Collection for Fake News Detection
• Pushing the Right Buttons: Adversarial Evaluation of Quality Estimation
• 'So You Think You’re Funny?': Rating the Humour Quotient in Standup Comedy
• FrameNet-assisted Noun Compound Interpretation
• Cognition-aware Cognate Detection
• Unsupervised Neural Machine Translation
• Harnessing Cross-lingual Features to Improve Cognate Detection for Low-resource Languages
• A Survey on Using Gaze Behaviour for Natural Language Processing
• Cognitively Aided Zero-Shot Automatic Essay Grading
• Happy Are Those Who Grade without Seeing: A Multi-Task Learning Approach to Grade Essays Using Gaze Behaviour
• Investigations into the use of Distributed Semantics for Cognate Detection and Computational Phylogenetics
• "A Passage to India": Pre-trained Word Embeddings for Indian Languages
• Challenge Datasets of Cognate and False Friend Pairs for Indian Languages
• Recommendation Chart of Domains for Cross-Domain Sentiment Analysis: Findings of A 20 Domain Study
• Strategies of Effective Digitization of Commentaries and Sub-commentaries: Towards the Construction of Textual History
• "Keep Your Dimensions on a Leash": True Cognate Detection using Siamese Deep Neural Networks
• Harnessing Deep Cross-lingual Word Embeddings to Infer Accurate Phylogenetic Trees
• Utilizing Word Embeddings based Features for Phylogenetic Tree Generation of Sanskrit Texts
• An Introduction to the Textual History Tool
• Utilizing Wordnets for Cognate Detection among Indian Languages
• Cognate Identification to improve Phylogenetic trees for Indian Languages
• Some Strategies to Capture Karaka-Yogyata with Special Reference to apadana
• Natural Language Processing and its intersection with Data Science
• Eyes are the Windows to the Soul: Predicting the Rating of Text Quality Using Gaze Behaviour
• Hindi Wordnet for Language Teaching: Experiences and Lessons Learnt
• Indian Language Wordnets and their Linkages with Princeton WordNet
• New Vistas to study Bhartṛhari: Cognitive NLP
• pyiwn: A Python-based API to access Indian Language WordNets
• Semi-automatic WordNet Linking using Word Embeddings
• Synthesizing Audio for Hindi Wordnet
• Is your Statement Purposeless? Predicting Computer Science Graduation Admission Acceptance based on Statement Of Purpose
• Sarcasm Suite: A browser-based engine for sarcasm detection and generation
• Scanpath Complexity: Modeling Reading Effort using Gaze Information
• NLP Fundamentals at VIVA IET
• A picture is worth a thousand words: Using OpenClipArt library for enriching IndoWordNet
• Civique: Using Social Media to detect Urban Emergencies
• Harnessing Cognitive Features for Sarcasm Detection
• Leveraging Cognitive Features for Sentiment Analysis
• Mapping it differently: A solution to the linking challenges
• Predicting Readers' Sarcasm Understandability by Modeling Gaze Behavior
• SlangNet: A WordNet like resource for English Slang
• Sophisticated Lexical Databases - Simplified Usage: Mobile Applications and Browser Plugins For Wordnets
• That’ll do fine!: A coarse lexical resource for English-Hindi MT, using polylingual topic models
• TransChat: Cross-Lingual Instant Messaging for Indian Languages
• Using Multilingual Topic Models for Improved Alignment in English-Hindi MT
• World WordNet database structure: an efficient schema for storing information of WordNets of the world
• Do not do processing, when you can look up: Towards a Discrimination Net for WSD
• PaCMan: Parallel Corpus Management Workbench
• PanchBhoota: Hierarchical phrase based machine translation systems for five Indian languages
• More than meets the eye: Study of Human Cognition in Sense Annotation
• A Study of the Sense Annotation Process: Man v/s Machine.
• Discrimination-net for Hindi