Findings of the WMT25 Shared Task on Automated Translation Evaluation Systems: Linguistic Diversity is Challenging and References Still Help
The WMT25 Shared Task on Automated Translation Evaluation Systems evaluates metrics and quality estimation systems that assess the …
Reference-Less Evaluation of Machine Translation: Navigating Through the Resource-Scarce Scenarios
Reference-less evaluation of machine translation, or Quality Estimation (QE), is vital for low-resource language pairs where …
Cyberbullying Detection via Aggression-Enhanced Prompting
Detecting cyberbullying on social media remains a critical challenge due to its subtle and varied expressions. This study investigates …
The Mind's Eye: A Multi-Faceted Reward Framework for Guiding Visual Metaphor Generation
Visual metaphor generation is a challenging task that aims to generate an image given an input text metaphor. Inherently, it needs …
BESSTIE: A Benchmark for Sentiment and Sarcasm Classification for Varieties of English
Despite large language models (LLMs) being known to exhibit bias against non-mainstream varieties, there are no known labeled datasets …
NEAR²: A Nested Embedding Approach to Efficient Product Retrieval and Ranking
E-commerce information retrieval (IR) systems struggle to simultaneously achieve high accuracy in interpreting complex user queries and …
Prompt-based Explainable Quality Estimation for English-Malayalam
The aim of this project was to curate data for the English-Malayalam language pair for the tasks of Quality Estimation (QE) and …
Towards a Robust Framework for Multimodal Hate Detection: A Study on Video vs. Image-based Content
Social media platforms enable the propagation of hateful content across different modalities such as textual, auditory, and visual, …
Automatically Generating Chinese Homophone Words to Probe Machine Translation Estimation Systems
Evaluating machine translation (MT) of user-generated content (UGC) involves unique challenges such as checking whether the nuance of …
Giving the Old a Fresh Spin: Quality Estimation-Assisted Constrained Decoding for Automatic Post-Editing
Automatic Post-Editing (APE) systems often struggle with over-correction, where unnecessary modifications are made to a translation, …
Unsupervised Audio-Visual Segmentation with Modality Alignment
Audio-Visual Segmentation (AVS) aims to identify, at the pixel level, the object in a visual scene that produces a given sound. Current …
DGFM: Full Body Dance Generation Driven by Music Foundation Models
In music-driven dance motion generation, most existing methods use hand-crafted features and neglect that music foundation models have …
Natural Language Processing for Dialects of a Language: A Survey
State-of-the-art natural language processing (NLP) models are trained on massive training corpora, and report a superlative performance …
When LLMs Struggle: Reference-less Translation Evaluation for Low-resource Languages
This paper investigates the reference-less evaluation of machine translation for low-resource language pairs, known as quality …
PortraitTalk: Towards Customizable One-Shot Audio-to-Talking Face Generation
Audio-driven talking face generation is a challenging task in digital communication. Despite significant progress in the area, most …
AV-GS: Learning Material and Geometry aware Priors for Novel View Acoustic Synthesis
Novel view acoustic synthesis (NVAS) aims to render binaural audio at any target viewpoint, given a mono audio emitted by a sound …
StableTalk: Advancing Audio-to-Talking Face Generation with Stable Diffusion and Vision Transformer
Audio-to-talking face generation stands at the forefront of advancements in generative AI. It bridges the gap between audio and visual …
Findings of the Quality Estimation Shared Task at WMT 2024: Are LLMs Closing the Gap in QE?
We report the results of the WMT 2024 shared task on Quality Estimation, in which the challenge is to predict the quality of the output …
Are Large Language Models State-of-the-art Quality Estimators for Machine Translation of User-generated Content?
This paper investigates whether large language models (LLMs) are state-of-the-art quality estimators for machine translation of …
A Multi-task Learning Framework for Evaluating Machine Translation of Emotion-loaded User-generated Content
Machine translation (MT) of user-generated content (UGC) poses unique challenges, including handling slang, emotion, and literary …
What do Large Language Models Need for Machine Translation Evaluation?
Leveraging large language models (LLMs) for various natural language processing tasks has led to superlative claims about their …
Together We Can: Multilingual Automatic Post-Editing for Low-Resource Languages
This exploratory study investigates the potential of multilingual Automatic Post-Editing (APE) systems to enhance the quality of …
Centrality-aware Product Retrieval and Ranking
This paper addresses the challenge of improving user experience on e-commerce platforms by enhancing product ranking relevant to …
Product Retrieval and Ranking for Alphanumeric Queries
This talk addresses the challenge of improving user experience on e-commerce platforms by enhancing product ranking relevant to …
Sampling Strategies for Creation of a Benchmark for Dialectal Sentiment Classification
This paper investigates data sampling strategies to create a benchmark for dialectal sentiment classification of Google Places reviews …
Experiences from Creating a Benchmark for Sentiment Classification for Varieties of English
Existing benchmarks often fail to account for linguistic diversity, like language variants of English. In this paper, we share our …
Edit Distances and Their Applications to Downstream Tasks in Research and Commercial Contexts
The tutorial describes the concept of edit distances applied to research and commercial contexts. We use Translation Edit Rate (TER), …
Connecting Ideas in 'Lower-Resource' Scenarios: NLP for National Varieties, Creoles and Other Low-resource Scenarios
Despite excellent results on benchmarks over a small subset of languages, large language models struggle to process text from languages …
A Survey of Multimodal Sarcasm Detection
Sarcasm is a rhetorical device that is used to convey the opposite of the literal meaning of an utterance. Sarcasm is widely used on …
Optimizing Quality Estimation for Low-Resource Language Translations: Exploring the Role of Language Relatedness
Quality Estimation (QE) is vital to determine the effectiveness of MT systems. This paper investigates QE for machine translation (MT) …
Evaluating Machine Translation for Emotion-loaded User Generated Content (TransEval4Emo-UGC)
This paper presents a dataset for evaluating the machine translation of emotion-loaded user generated content. It contains …
Decoding Cyberbullying on Social Media: A Machine Learning Exploration
Social media, a vast platform for communication and entertainment, unfortunately, is an ideal breeding ground for cyberbullying. While …
Using character-level models for efficient abbreviation and long-form detection
Abbreviations and their associated long forms are important textual elements that are present in almost every scientific communication, …
DiffSED: Sound Event Detection with Denoising Diffusion
Sound Event Detection (SED) aims to predict the temporal boundaries of all the events of interest and their class labels, given an …
Google Translate Error Analysis for Mental Healthcare Information: Evaluating Accuracy, Comprehensibility, and Implications for Multilingual Healthcare Communication
This study explores the use of Google Translate (GT) for translating mental healthcare (MHealth) information and evaluates its …
CreoleVal: Multilingual Multitask Benchmarks for Creoles
Creoles represent an under-explored and marginalized group of languages, with few available resources for NLP research. While the …
APE-then-QE: Correcting then Filtering Pseudo Parallel Corpora for MT Training Data Creation
Automatic Post-Editing (APE) is the task of automatically identifying and correcting errors in the Machine Translation (MT) outputs. We …
SurreyAI 2023 Submission for the Quality Estimation Shared Task
Quality Estimation (QE) systems are important in situations where it is necessary to assess the quality of translations, but there is …
Quality Estimation-Assisted Automatic Post-Editing
Automatic Post-Editing (APE) systems are prone to over-correction of the Machine Translation (MT) outputs. While Word-level Quality …
Predict and Use: Harnessing Predicted Gaze to Improve Multimodal Sarcasm Detection
Sarcasm is a complex linguistic construct with incongruity at its very core. Detecting sarcasm depends on the actual content spoken and …
Findings of the WMT 2023 Shared Task on Quality Estimation
We report the results of the WMT 2023 shared task on Quality Estimation, in which the challenge is to predict the quality of the output …
Findings of the WMT 2023 Shared Task on Automatic Post-Editing
We present the results from the 9th round of the WMT shared task on MT Automatic Post-Editing, which consists of automatically …
Sarcasm in Sight and Sound: Benchmarking and Expansion to Improve Multimodal Sarcasm Detection
The introduction of the MUStARD dataset, and its emotion recognition extension MUStARD++, have identified sarcasm to be a multi-modal …
Challenges of Human vs Machine Translation of Emotion-Loaded Chinese Microblog Texts
This paper attempts to identify challenges professional translators face when translating emotion-loaded texts as well as errors …
Leveraging Foundation Models for Unsupervised Audio-Visual Segmentation
Audio-Visual Segmentation (AVS) aims to precisely outline audible objects in a visual scene at the pixel level. Existing AVS methods …
Towards Safer Communities: Detecting Aggression and Offensive Language in Code-Mixed Tweets to Combat Cyberbullying
Cyberbullying is a serious societal issue widespread on various channels and platforms, particularly social networking sites. Such …
Modelling Political Aggression on Social Media Platforms
Recent years have seen a proliferation of aggressive social media posts, often wreaking even real-world consequences for victims. …
A Multi-task Learning Framework for Quality Estimation
Quality Estimation (QE) is the task of evaluating machine translation output in the absence of reference translation. Conventional …
Evaluation of Chinese-English Machine Translation of Emotion-Loaded Microblog Texts: A Human Annotated Dataset for the Quality Assessment of Emotion Translation
In this paper, we focus on how current Machine Translation (MT) engines perform on the translation of emotion-loaded texts by …
Applications and Challenges of Sentiment Analysis in Real-life Scenarios
Sentiment analysis has benefited from the availability of lexicons and benchmark datasets created over decades of research. However, …
Utilizing Weak Supervision to Create S3D: A Sarcasm Annotated Dataset
Sarcasm is prevalent in all corners of social media, posing many challenges within Natural Language Processing (NLP), particularly for …
Findings of the WMT 2022 Shared Task on Quality Estimation
We report the results of the WMT 2022 shared task on Quality Estimation, in which the challenge is to predict the quality of the output …
Findings of the WMT 2022 Shared Task on Automatic Post-Editing
We present the results from the 8th round of the WMT shared task on MT Automatic Post-Editing, which consists in automatically …
SURREY-CTS-NLP at WASSA2022: An Experiment of Discourse and Sentiment Analysis for the Prediction of Empathy, Distress and Emotion
This paper summarises the submissions our team, SURREY-CTS-NLP has made for the WASSA 2022 Shared Task for the prediction of empathy, …
An Ensemble Approach to Acronym Extraction using Transformers
Acronyms are abbreviated units of a phrase constructed by using initial components of the phrase in a text. Automatic extraction of …
FrameNet-assisted Noun Compound Interpretation
Given a noun compound (NC), we address the problem of predicting the appropriate semantic label linking the constituents of the NC. …
Happy Are Those Who Grade without Seeing: A Multi-Task Learning Approach to Grade Essays Using Gaze Behaviour
The gaze behaviour of a reader is helpful in solving several NLP tasks such as automatic essay grading. However, collecting gaze …
Cognitively Aided Zero-Shot Automatic Essay Grading
Automatic essay grading (AEG) is a process in which machines assign a grade to an essay written in response to a topic, called the …
Recommendation Chart of Domains for Cross-Domain Sentiment Analysis: Findings of A 20 Domain Study
Cross-domain sentiment analysis (CDSA) helps to address the problem of data scarcity in scenarios where labelled data for a domain …
Challenge Datasets of Cognate and False Friend Pairs for Indian Languages
Cognates are present in multiple variants of the same text across different languages (e.g., hund in German and hound in English …
"A Passage to India": Pre-trained Word Embeddings for Indian Languages
Dense word vectors or ‘word embeddings’ which encode semantic properties of words, have now become integral to NLP tasks …
Strategies of Effective Digitization of Commentaries and Sub-commentaries: Towards the Construction of Textual History
This paper describes additional aspects of a digital tool called the ‘Textual History Tool’. We describe its various salient features …
Harnessing Deep Cross-lingual Word Embeddings to Infer Accurate Phylogenetic Trees
Establishing language relatedness by inferring phylogenetic trees has been a topic of interest in the area of diachronic linguistics. …
"Keep Your Dimensions on a Leash": True Cognate Detection using Siamese Deep Neural Networks
Automatic Cognate Detection helps NLP tasks of Machine Translation, Information Retrieval, and Phylogenetics. Cognate words are defined …
Utilizing Word Embeddings based Features for Phylogenetic Tree Generation of Sanskrit Texts
Tracing the root of a text i.e., the original version of the text, by inferring phylogenetic trees has been a topic of interest in …
Utilizing Wordnets for Cognate Detection among Indian Languages
Automatic Cognate Detection (ACD) is a challenging task which has been utilized to help NLP applications like Machine Translation, …
An Introduction to the Textual History Tool
This paper describes a digital tool called the Textual History Tool in detail. This tool captures the historical evolution of a text …
Some Strategies to Capture Karaka-Yogyata with Special Reference to apadana
In today’s digital world language technology has gained importance. Several software, have been developed and are available in the …
Cognate Identification to improve Phylogenetic trees for Indian Languages
Cognates are present in multiple variants of the same text across different languages. Computational Phylogenetics uses algorithms and …
Synthesizing Audio for Hindi Wordnet
In this paper, we describe our work on the creation of a voice model using a speech synthesis system for the Hindi Language. We use …
pyiwn: A Python-based API to access Indian Language WordNets
Indian language WordNets have their individual web-based browsing interfaces along with a common interface for IndoWordNet. These …
New Vistas to study Bhartṛhari: Cognitive NLP
A sentence is an important notion in the Indian grammatical tradition. The collection of the definitions of a sentence can be found in …
Hindi Wordnet for Language Teaching: Experiences and Lessons Learnt
This paper reports the work related to making Hindi Wordnet1 available as a digital resource for language learning and teaching, and …
Eyes are the Windows to the Soul: Predicting the Rating of Text Quality Using Gaze Behaviour
Predicting a reader’s rating of text quality is a challenging task that involves estimating different subjective aspects of the …
Scanpath Complexity: Modeling Reading Effort using Gaze Information
Measuring reading effort is useful for practical purposes such as designing learning material and personalizing text comprehension …
Sarcasm Suite: A browser-based engine for sarcasm detection and generation
Sarcasm Suite is a browser-based engine that deploys five of our past papers in sarcasm detection and generation. The sarcasm detection …
Is your Statement Purposeless? Predicting Computer Science Graduation Admission Acceptance based on Statement Of Purpose
We present a quantitative, data-driven machine learning approach to mitigate the problem of unpredictability of Computer Science …
That’ll do fine!: A coarse lexical resource for English-Hindi MT, using polylingual topic models
Parallel corpora are often injected with bilingual lexical resources for improved Indian language machine translation (MT). In absence …
Sophisticated Lexical Databases - Simplified Usage: Mobile Applications and Browser Plugins For Wordnets
India is a country with 22 officially recognized languages and 17 of these have WordNets, a crucial resource. Web browser based …
SlangNet: A WordNet like resource for English Slang
We present a WordNet like structured resource for slang words and neologisms on the internet. The dynamism of language is often an …
Predicting Readers' Sarcasm Understandability by Modeling Gaze Behavior
Sarcasm understandability or the ability to understand textual sarcasm depends upon readers’ language proficiency, social knowledge, …
Mapping it differently: A solution to the linking challenges
This paper reports the work of creating bilingual mappings in English for certain synsets of Hindi wordnet, the need for doing this, …
Leveraging Cognitive Features for Sentiment Analysis
Sentiments expressed in user-generated short text and sentences are nuanced by subtleties at lexical, syntactic, semantic and pragmatic …
Harnessing Cognitive Features for Sarcasm Detection
In this paper, we propose a novel mechanism for enriching the feature vector, for the task of sarcasm detection, with cognitive …
Civique: Using Social Media to detect Urban Emergencies
We present the Civique system for emergency detection in urban areas by monitoring micro blogs like Tweets. The system detects …
A picture is worth a thousand words: Using OpenClipArt library for enriching IndoWordNet
WordNet has proved to be immensely useful for Word Sense Disambiguation, and thence Machine translation, Information Retrieval and …
World WordNet database structure: an efficient schema for storing information of WordNets of the world
WordNet is an online lexical resource which expresses unique concepts in a language. English WordNet is the first WordNet which was …
Using Multilingual Topic Models for Improved Alignment in English-Hindi MT
Parallel corpora are often injected with bilingual dictionaries for improved Indian language machine translation (MT). In absence of …
TransChat: Cross-Lingual Instant Messaging for Indian Languages
We present TransChat, an open-source, cross platform, Indian language Instant Messaging (IM) application that facilitates cross lingual …
PanchBhoota: Hierarchical phrase based machine translation systems for five Indian languages
We present our work on developing fifteen Hierarchical Phrase Based Statistical Machine Translation (HPBSMT) systems for five Indian …
PaCMan: Parallel Corpus Management Workbench
We present a Parallel Corpora Management tool that aides parallel corpora generation for the task of Machine Translation (MT). It takes …
Do not do processing, when you can look up: Towards a Discrimination Net for WSD
The task of Word Sense Disambiguation (WSD) incorporates in its definition the role of ‘context’. We present our work on the …
More than meets the eye: Study of Human Cognition in Sense Annotation
Word Sense Disambiguation (WSD) approaches have reported good accuracies in recent years. However, these approaches can be classified …
Discrimination-net for Hindi
Current state-of-the-art Word Sense Disambiguation (WSD) algorithms are mostly supervised and use the P (Sense|Word) statistic for …
A Study of the Sense Annotation Process: Man v/s Machine.
Does context help determine sense? This question might seem frivolous, even preposterous to anybody sensible. However, our long time …
