Search Results for author:
Found 65 papers, 40 papers with code
A Data Bootstrapping Recipe for Low-Resource Multilingual Relation Classification
Data collection is challenging for Indian languages, because they are syntactically and morphologically diverse, as well as different from resource-rich languages like English.
Efficient Continual Pre-training of LLMs for Low-resource Languages
On the other hand, continual pre-training (CPT) with large amounts of language-specific data is a costly proposition in terms of data acquisition and computational resources.
Adaptive BPE Tokenization for Enhanced Vocabulary Adaptation in Finetuning Pretrained Language Models
Current approaches trivially append the target domain-specific vocabulary at the end of the PLM vocabulary.
YesBut: A High-Quality Annotated Multimodal Dataset for evaluating Satire Comprehension capability of Vision-Language Models
In this paper, we propose the challenging tasks of Satirical Image Detection (detecting whether an image is satirical), Understanding (generating the reason behind the image being satirical), and Completion (given one half of the image, selecting the other half from 2 given options, such that the complete image is satirical) and release a high-quality dataset YesBut, consisting of 2547 images, 1084 satirical and 1463 non-satirical, containing different artistic styles, to evaluate those tasks.
Unlocking Efficiency: Adaptive Masking for Gene Transformer Models
Our findings reveal that CM-GEMS outperforms state-of-the-art models (DNABert-2, Nucleotide transformer, DNABert) trained at 120K steps, achieving similar results in just 10K and 1K steps.
On The Persona-based Summarization of Domain-Specific Documents
However, every persona of a domain has different requirements of information and hence their summarization.
MEDVOC: Vocabulary Adaptation for Fine-tuning Pre-trained Language Models on Medical Text Summarization
In contrast to existing domain adaptation approaches in summarization, MEDVOC treats vocabulary as an optimizable parameter and optimizes the PLM vocabulary based on fragment score conditioned only on the downstream task's reference summaries.
Instruction-Guided Bullet Point Summarization of Long Financial Earnings Call Transcripts
While automatic summarization techniques have made significant advancements, their primary focus has been on summarizing short news articles or documents that have clear structural patterns like scientific articles or government reports.
Parameter-Efficient Instruction Tuning of Large Language Models For Extreme Financial Numeral Labelling
We study the problem of automatically annotating relevant numerals (GAAP metrics) occurring in the financial documents with their corresponding XBRL tags.
TIGQA:An Expert Annotated Question Answering Dataset in Tigrinya
The absence of explicitly tailored, accessible annotated datasets for educational purposes presents a notable obstacle for NLP tasks in languages with limited resources. This study initially explores the feasibility of using machine translation (MT) to convert an existing dataset into a Tigrinya dataset in SQuAD format.
Beyond Accuracy: Investigating Error Types in GPT-4 Responses to USMLE Questions
In our annotated dataset, a substantial portion of GPT-4's incorrect responses is categorized as a "Reasonable response by GPT-4," by annotators.
Order-Based Pre-training Strategies for Procedural Text Understanding
In this paper, we propose sequence-based pretraining methods to enhance procedural understanding in natural language processing.
How COVID-19 has Impacted the Anti-Vaccine Discourse: A Large-Scale Twitter Study Spanning Pre-COVID and Post-COVID Era
The debate around vaccines has been going on for decades, but the COVID-19 pandemic showed how crucial it is to understand and mitigate anti-vaccine sentiments.
How Robust are the Tabular QA Models for Scientific Tables? A Study using Customized Dataset
Question-answering (QA) on hybrid scientific tabular and textual data deals with scientific information, and relies on complex numerical reasoning.
Cost-Performance Optimization for Processing Low-Resource Language Tasks Using Commercial LLMs
As means to reduce the number of tokens processed by the LLM, we consider code-mixing, translation, and transliteration of LRLs to HRLs.
Long Dialog Summarization: An Analysis
Dialog summarization has become increasingly important in managing and comprehending large-scale conversations across various domains.
BOXREC: Recommending a Box of Preferred Outfits in Online Shopping
In this paper, we propose a box recommendation framework - BOXREC - which at first, collects user preferences across different item types (namely, top-wear, bottom-wear and foot-wear) including price-range of each type and a maximum shopping budget for a particular shopping session.
CLMSM: A Multi-Task Learning Framework for Pre-training on Procedural Text
In this paper, we propose CLMSM, a domain-specific, continual pre-training framework, that learns from a large set of procedural recipes.
GeneMask: Fast Pretraining of Gene Sequences to Enable Few-Shot Learning
Large-scale language models such as DNABert and LOGO aim to learn optimal gene representations and are trained on the entire Human Reference Genome.
$FastDoc$: Domain-Specific Fast Continual Pre-training Technique using Document-Level Metadata and Taxonomy
In this paper, we propose $FastDoc$ (Fast Continual Pre-training Technique using Document Level Metadata and Taxonomy), a novel, compute-efficient framework that utilizes Document metadata and Domain-Specific Taxonomy as supervision signals to continually pre-train transformer encoder on a domain-specific corpus.
CrysMMNet: Multimodal Representation for Crystal Property Prediction
In this work, we leverage textual descriptions of materials to model global structural information into graph structure and learn a more robust and enriched representation of crystalline materials.
Financial Numeric Extreme Labelling: A Dataset and Benchmarking for XBRL Tagging
The U. S. Securities and Exchange Commission (SEC) mandates all public companies to file periodic financial statements that should contain numerals annotated with a particular label from a taxonomy.
FinRED: A Dataset for Relation Extraction in Financial Domain
Relation extraction models trained on a source domain cannot be applied on a different target domain due to the mismatch between relation sets.
IVP-VAE: Modeling EHR Time Series with Initial Value Problem Solvers
Continuous-time models such as Neural ODEs and Neural Flows have shown promising results in analyzing irregularly sampled time series frequently encountered in electronic health records.
A Review of the Role of Causality in Developing Trustworthy AI Systems
This review aims to provide the reader with an overview of causal methods that have been developed to improve the trustworthiness of AI models.
CrysGNN : Distilling pre-trained knowledge to enhance property prediction for crystalline materials
To leverage these untapped data, this paper presents CrysGNN, a new pre-trained GNN framework for crystalline materials, which captures both node and graph level structural information of crystal graphs using a huge amount of unlabelled material data.
What You Like: Generating Explainable Topical Recommendations for Twitter Using Social Annotations
With over 500 million tweets posted per day, in Twitter, it is difficult for Twitter users to discover interesting content from the deluge of uninteresting posts.
ECTSum: A New Benchmark Dataset For Bullet Point Summarization of Long Earnings Call Transcripts
Despite tremendous progress in automatic summarization, state-of-the-art methods are predominantly trained to excel in summarizing short newswire articles, or documents with strong layout biases such as scientific articles or government reports.
A Framework to Generate High-Quality Datapoints for Multiple Novel Intent Detection
However, the newer intents may not be explicitly announced and need to be inferred dynamically.
An Application to Generate Style Guided Compatible Outfit
Fashion recommendation has witnessed a phenomenal growth of research, particularly in the domains of shop-the-look, contextaware outfit creation, personalizing outfit creation etc.
CAVES: A Dataset to facilitate Explainable Classification and Summarization of Concerns towards COVID Vaccines
This is also the first multi-label classification dataset that provides explanations for each of the labels.
Scheduling Virtual Conferences Fairly: Achieving Equitable Participant and Speaker Satisfaction
As the efficiency and fairness objectives can be in conflict with each other, we propose a joint optimization framework that allows conference organizers to design schedules that balance (i. e., allow trade-offs) among efficiency, participant fairness and speaker fairness objectives.
A Generative Approach for Financial Causality Extraction
Causality represents the foremost relation between events in financial documents such as financial news articles, financial reports.
Recommendation of Compatible Outfits Conditioned on Style
Recommendation in the fashion domain has seen a recent surge in research in various areas, for example, shop-the-look, context-aware outfit creation, personalizing outfit creation, etc.
Offsetting Unequal Competition through RL-assisted Incentive Schemes
On inspecting, we realize that an overall incentive scheme for the weak team does not incentivize the weaker agents within that team to learn and improve.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Towards Fair Recommendation in Two-Sided Platforms
Many online platforms today (such as Amazon, Netflix, Spotify, LinkedIn, and AirBnB) can be thought of as two-sided markets with producers and customers of goods and services.
MTLTS: A Multi-Task Framework To Obtain Trustworthy Summaries From Crisis-Related Microblogs
Occurrences of catastrophes such as natural or man-made disasters trigger the spread of rumours over social media at a rapid pace.
A Data Bootstrapping Recipe for Low Resource Multilingual Relation Classification
Relation classification (sometimes called 'extraction') requires trustworthy datasets for fine-tuning large language models, as well as for evaluation.
Knowledge-Aware Neural Networks for Medical Forum Question Classification
Online medical forums have become a predominant platform for answering health-related information needs of consumers.
Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework
Answering questions asked from instructional corpora such as E-manuals, recipe books, etc., has been far less studied than open-domain factoid context-based question answering.
A Hierarchical VAE for Calibrating Attributes while Generating Text using Normalizing Flow
In this digital age, online users expect personalized content.
tWT--WT: A Dataset to Assert the Role of Target Entities for Detecting Stance of Tweets
The stance detection task aims at detecting the stance of a tweet or a text for a target.
Understanding the Role of Affect Dimensions in Detecting Emotions from Tweets: A Multi-task Approach
For the regression task, VADEC, when trained with SenWave, achieves 7. 6% and 16. 5% gains in Pearson Correlation scores over the current state-of-the-art on the EMOBANK dataset for the Valence (V) and Dominance (D) affect dimensions respectively.
Convex Online Video Frame Subset Selection using Multiple Criteria for Data Efficient Autonomous Driving
We design a novel convex optimization-based multi-criteria online subset selection algorithm that uses a thresholded concave function of selection variables.
Demarcating Endogenous and Exogenous Opinion Dynamics: An Experimental Design Approach
The networked opinion diffusion in online social networks (OSN) is often governed by the two genres of opinions - endogenous opinions that are driven by the influence of social contacts among users, and exogenous opinions which are formed by external effects like news, feeds etc.
A Novel Two-stage Framework for Extracting Opinionated Sentences from News Articles
This paper presents a novel two-stage framework to extract opinionated sentences from a given news article.
TMCOSS: Thresholded Multi-Criteria Online Subset Selection for Data-Efficient Autonomous Driving
Training vision-based Autonomous driving models is a challenging problem with enormous practical implications.
An Integrated Approach for Improving Brand Consistency of Web Content: Modeling, Analysis and Recommendation
A consumer-dependent (business-to-consumer) organization tends to present itself as possessing a set of human qualities, which is termed as the brand personality of the company.
On Fair Virtual Conference Scheduling: Achieving Equitable Participant and Speaker Satisfaction
We show that the welfare and fairness objectives can be in conflict with each other, and there is a need to maintain a balance between these objective while caring for them simultaneously.
Fine-grained Sentiment Controlled Text Generation
DE-VAE achieves better control of sentiment as an attribute while preserving the content by learning a suitable lossless transformation network from the disentangled sentiment space to the desired entangled representation.
Read what you need: Controllable Aspect-based Opinion Summarization of Tourist Reviews
Manually extracting relevant aspects and opinions from large volumes of user-generated text is a time-consuming process.
FairRec: Two-Sided Fairness for Personalized Recommendations in Two-Sided Platforms
We investigate the problem of fair recommendation in the context of two-sided online platforms, comprising customers on one side and producers on the other.
Map Enhanced Route Travel Time Prediction using Deep Neural Networks
Travel time estimation is a fundamental problem in transportation science with extensive literature.
Regression Under Human Assistance
In this paper, we take a first step towards the development of machine learning models that are optimized to operate under different automation levels.
Incorporating Domain Knowledge into Medical NLI using Knowledge Graphs
Specifically, we experiment with fusing embeddings obtained from knowledge graph with the state-of-the-art approaches for NLI task (ESIM model).
A Deep Generative Model for Code-Switched Text
Code-switching, the interleaving of two or more languages within a sentence or discourse is pervasive in multilingual societies.
Improved Sentiment Detection via Label Transfer from Monolingual to Synthetic Code-Switched Text
Consequently, the best monolingual methods perform relatively poorly on code-switched text.
AttentiveChecker: A Bi-Directional Attention Flow Mechanism for Fact Verification
The recently released FEVER dataset provided benchmark results on a fact-checking task in which given a factual claim, the system must extract textual evidence (sets of sentences from Wikipedia pages) that support or refute the claim.
NeVAE: A Deep Generative Model for Molecular Graphs
Moreover, in contrast with the state of the art, our decoder is able to provide the spatial coordinates of the atoms of the molecules it generates.
A graphical framework to detect and categorize diverse opinions from online news
This paper proposes a graphical framework to extract opinionated sentences which highlight different contexts within a given news article by introducing the concept of diversity in a graphical model for opinion detection. We conduct extensive evaluations and find that the proposed modification leads to impressive improvement in performance and makes the final results of the model much more usable.
Summarizing Situational and Topical Information During Crises
The use of microblogging platforms such as Twitter during crises has become widespread.
Functions of Code-Switching in Tweets: An Annotation Framework and Some Initial Experiments
Code-Switching (CS) between two languages is extremely common in communities with societal multilingualism where speakers switch between two or more languages when interacting with each other.
Discriminative Link Prediction using Local Links, Node Features and Community Structure
Apart from the new predictor, another contribution is a rigorous protocol for benchmarking and reporting LP algorithms, which reveals the regions of strengths and weaknesses of all the predictors studied here, and establishes the new proposal as the most robust.
