24 citations · 83 across the 67 of their papers we have counts for
75 papers
Quality-Aware Self-Correcting Speech Translation on an Edge Device
Zubair Ajmal Farooq, Diptesh Kanojia
We present a fully offline speech-to-speech translation pipeline that runs on a Jetson Nano (4 GB) and corrects its own weak translations without retraining. A Whisper-tiny ASR fee…
Beyond Relevance: Structured Semantic Supervision for Product Search with LLM-Augmented Annotations
Girish A. Koushik, Swapnil Bhosale, Samarth Agrawal +4
E-commerce search requires distinguishing products that are merely related to a query from those that directly satisfy the user's shopping intent. We augment query-product pairs wi…
In the Blind: Building Pseudo-References for MT Evaluation
Diptesh Kanojia, Chi-kiu Lo, Archchana Sindhujan +3
The WMT26 General MT task evaluates systems on 10 language pairs that have no human references (neither translated from scratch nor post-edited from MT output by humans). We descri…
IndicQE-APE: A Consolidated Benchmark for Quality Estimation and Automatic Post-Editing for Indic Languages
Diptesh Kanojia, Archchana Sindhujan, Sourabh Deoghare +14
Indic quality estimation (QE) and automatic post-editing (APE) data is spread across separate releases, so no single resource supports training and evaluation across tasks and lang…
DiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation
Jordan Painter, Dipankar Srirag, Adarsh Kappiyath +3
Large language models increasingly understand dialectal English, yet still produce only standard, US-leaning English, leaving dialectal generation, the harder half of the problem,…
TeMuDance: Contrastive Alignment-Based Textual Control for Music-Driven Dance Generation
Xinran Liu, Diptesh Kanojia, Wenwu Wang +1
Existing music-driven dance generation approaches have achieved strong realism and effective audio-motion alignment. However, they generally lack semantic controllability, making i…
Improving Search Suggestions for Alphanumeric Queries
Samarth Agrawal, Jayanth Yetukuri, Diptesh Kanojia +2
Alphanumeric identifiers such as manufacturer part numbers (MPNs), SKUs, and model codes are ubiquitous in e-commerce catalogs and search. These identifiers are sparse, non linguis…
Parameter-Efficient Quality Estimation via Frozen Recursive Models
Umar Abubacar, Roman Bauer, Diptesh Kanojia
Tiny Recursive Models (TRM) achieve strong results on reasoning tasks through iterative refinement of a shared network. We investigate whether these recursive mechanisms transfer t…
MUNIChus: Multilingual News Image Captioning Benchmark
Yuji Chen, Alistair Plum, Hansi Hettiarachchi +4
The goal of news image captioning is to generate captions by integrating news article content with corresponding images, highlighting the relationship between textual context and v…
Domain-Specific Quality Estimation for Machine Translation in Low-Resource Scenarios
Namrata Patil Gurav, Akashdeep Ranu, Archchana Sindhujan +1
Quality Estimation (QE) is essential for assessing machine translation quality in reference-less settings, particularly for domain-specific and low-resource language scenarios. In…
Beyond Scalar Scores: Reinforcement Learning for Error-Aware Quality Estimation of Machine Translation
Archchana Sindhujan, Girish A. Koushik, Shenbin Qian +2
Quality Estimation (QE) aims to assess the quality of machine translation (MT) outputs without relying on reference translations, making it essential for real-world, large-scale MT…
TANDEM: Temporal-Aware Neural Detection for Multimodal Hate Speech
Girish A. Koushik, Helen Treharne, Diptesh Kanojia
Social media platforms are increasingly dominated by long-form multimodal content, where harmful narratives are constructed through a complex interplay of audio, visual, and textua…
MAGIC-Talk: Motion-aware Audio-Driven Talking Face Generation with Customizable Identity Control
Fatemeh Nazarieh, Zhenhua Feng, Diptesh Kanojia +2
Audio-driven talking face generation has gained significant attention for applications in digital media and virtual avatars. While recent methods improve audio-lip synchronization,…
Evaluating Open-Source Vision-Language Models for Multimodal Sarcasm Detection
Saroj Basnet, Shafkat Farabi, Tharindu Ranasinghe +2
Recent advances in open-source vision-language models (VLMs) offer new opportunities for understanding complex and subjective multimodal phenomena such as sarcasm. In this work, we…
The Mind's Eye: A Multi-Faceted Reward Framework for Guiding Visual Metaphor Generation
Girish A. Koushik, Fatemeh Nazarieh, Katherine Birch +2
Visual metaphor generation is a challenging task that aims to generate an image given an input text metaphor. Inherently, it needs language understanding to bind a source concept w…
Cyberbullying Detection via Aggression-Enhanced Prompting
Aisha Saeid, Anu Sabu, Girish A. Koushik +2
Detecting cyberbullying on social media remains a critical challenge due to its subtle and varied expressions. This study investigates whether integrating aggression detection as a…
ALOPE: Adaptive Layer Optimization for Translation Quality Estimation using Large Language Models
Archchana Sindhujan, Shenbin Qian, Chan Chi Chun Matthew +2
Large Language Models (LLMs) have shown remarkable performance across a wide range of natural language processing tasks. Quality Estimation (QE) for Machine Translation (MT), which…
NEAR: A Nested Embedding Approach to Efficient Product Retrieval and Ranking
Shenbin Qian, Diptesh Kanojia, Samarth Agrawal +4
E-commerce information retrieval (IR) systems struggle to simultaneously achieve high accuracy in interpreting complex user queries and maintain efficient processing of vast produc…
TRACE: Textual Relevance Augmentation and Contextual Encoding for Multimodal Hate Detection
Girish A. Koushik, Helen Treharne, Aditya Joshi +1
Social media memes are a challenging domain for hate detection because they intertwine visual and textual cues into culturally nuanced messages. To tackle these challenges, we intr…
Automatically Generating Chinese Homophone Words to Probe Machine Translation Estimation Systems
Shenbin Qian, Constantin Orăsan, Diptesh Kanojia +1
Evaluating machine translation (MT) of user-generated content (UGC) involves unique challenges such as checking whether the nuance of emotions from the source are preserved in the…
DGFM: Full Body Dance Generation Driven by Music Foundation Models
Xinran Liu, Zhenhua Feng, Diptesh Kanojia +1
In music-driven dance motion generation, most existing methods use hand-crafted features and neglect that music foundation models have profoundly impacted cross-modal content gener…
Towards a Robust Framework for Multimodal Hate Detection: A Study on Video vs. Image-based Content
Girish A. Koushik, Diptesh Kanojia, Helen Treharne
Social media platforms enable the propagation of hateful content across different modalities such as textual, auditory, and visual, necessitating effective detection methods. While…
GCDance: Genre-Controlled Music-Driven 3D Full Body Dance Generation
Xinran Liu, Xu Dong, Shenbin Qian +3
Music-driven dance generation is a challenging task as it requires strict adherence to genre-specific choreography while ensuring physically realistic and precisely synchronized da…
Giving the Old a Fresh Spin: Quality Estimation-Assisted Constrained Decoding for Automatic Post-Editing
Sourabh Deoghare, Diptesh Kanojia, Pushpak Bhattacharyya
Automatic Post-Editing (APE) systems often struggle with over-correction, where unnecessary modifications are made to a translation, diverging from the principle of minimal editing…