Search Results for author:
Found 121 papers, 51 papers with code
Attribute Value Generation from Product Title using Language Models
What makes this problem challenging is the diversity of product types and their attributes and values.
Does Meta-learning Help mBERT for Few-shot Question Generation in a Cross-lingual Transfer Setting for Indic Languages?
Further, we apply the model agnostic meta-learning approach to our base model.
Investigating the Generative Approach for Question Answering in E-Commerce
In this paper, we investigate the suitability of the generative approach for PQA.
Keep it Surprisingly Simple: A Simple First Order Graph Based Parsing Model for Joint Morphosyntactic Parsing in Sanskrit
We propose a graph-based model for joint morphological parsing and dependency parsing in Sanskrit.
Using Sentence-level Classification Helps Entity Extraction from Material Science Literature
In the last few years, several attempts have been made on extracting information from material science research domain.
A Graph-Based Framework for Structured Prediction Tasks in Sanskrit
Ours is a search-based structured prediction framework, which expects a graph as input, where relevant linguistic information is encoded in the nodes, and the edges are then used to indicate the association between these nodes.
Modeling interdisciplinary interactions among Physics, Mathematics & Computer Science
Interdisciplinarity has over the recent years have gained tremendous importance and has become one of the key ways of doing cutting edge research.
A Robust SINDy Approach by Combining Neural Networks and an Integral Form
To do this, we make use of neural networks to learn an implicit representation based on measurement data so that not only it produces the output in the vicinity of the measurements but also the time-evolution of output can be described by a dynamical system.
Deep Learning for Structure-Preserving Universal Stable Koopman-Inspired Embeddings for Nonlinear Canonical Hamiltonian Dynamics
We demonstrate the capabilities of deep learning in acquiring compact symplectic coordinate transformation and the corresponding simple dynamical models, fostering data-driven learning of nonlinear canonical Hamiltonian systems, even those with continuous spectra.
Guaranteed Stable Quadratic Models and their applications in SINDy and Operator Inference
In this work, we propose inference formulations to learn quadratic models, which are stable by design.
Aesthetics of Sanskrit Poetry from the Perspective of Computational Linguistics: A Case Study Analysis on Siksastaka
We provide a deep analysis of Siksastaka, a Sanskrit poem, from the perspective of 6 prominent kavyashastra schools, to illustrate the proposed framework.
Data-Driven Identification of Quadratic Symplectic Representations of Nonlinear Hamiltonian Systems
By leveraging this, we obtain quadratic dynamics that are Hamiltonian in a transformed coordinate system.
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.
$FPDM$: Domain-Specific Fast Pre-training Technique using Document-Level Metadata
In this paper, we propose $FPDM$ (Fast Pre-training Technique using Document Level Metadata), a novel, compute-efficient framework that utilizes Document metadata and Domain-Specific Taxonomy as supervision signals to pre-train transformer encoder on a domain-specific corpus.
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.
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.
Frugal Prompting for Dialog Models
The research contributes to a better understanding of how LLMs can be effectively used for building interactive systems.
SanskritShala: A Neural Sanskrit NLP Toolkit with Web-Based Interface for Pedagogical and Annotation Purposes
We present a neural Sanskrit Natural Language Processing (NLP) toolkit named SanskritShala (a school of Sanskrit) to facilitate computational linguistic analyses for several tasks such as word segmentation, morphological tagging, dependency parsing, and compound type identification.
Intent Identification and Entity Extraction for Healthcare Queries in Indic Languages
Scarcity of data and technological limitations for resource-poor languages in developing countries like India poses a threat to the development of sophisticated NLU systems for healthcare.
Rank-Minimizing and Structured Model Inference
While extracting information from data with machine learning plays an increasingly important role, physical laws and other first principles continue to provide critical insights about systems and processes of interest in science and engineering.
Inference of Continuous Linear Systems from Data with Guaranteed Stability
Machine-learning technologies for learning dynamical systems from data play an important role in engineering design.
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.
Generalized Quadratic-Embeddings for Nonlinear Dynamics using Deep Learning
For complex dynamics behavior, modeling procedures, as well as models, can be intricated, which can make the design process cumbersome.
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.
TransLIST: A Transformer-Based Linguistically Informed Sanskrit Tokenizer
Existing lexicon driven approaches for SWS make use of Sanskrit Heritage Reader, a lexicon-driven shallow parser, to generate the complete candidate solution space, over which various methods are applied to produce the most valid solution.
Legal Case Document Summarization: Extractive and Abstractive Methods and their Evaluation
Summarization of legal case judgement documents is a challenging problem in Legal NLP.
Fast Few shot Self-attentive Semi-supervised Political Inclination Prediction
With the rising participation of the common mass in social media, it is increasingly common now for policymakers/journalists to create online polls on social media to understand the political leanings of people in specific locations.
Pre-trained Language Models for the Legal Domain: A Case Study on Indian Law
With the rapidly increasing volume of Legal NLP applications in various countries, it has become necessary to pre-train such LMs over legal text of other countries as well.
A Novel Multi-Task Learning Approach for Context-Sensitive Compound Type Identification in Sanskrit
The phenomenon of compounding is ubiquitous in Sanskrit.
Exploring Generative Models for Joint Attribute Value Extraction from Product Titles
Attribute values of the products are an essential component in any e-commerce platform.
CORAL: Contextual Response Retrievability Loss Function for Training Dialog Generation Models
Furthermore, CE loss computation for the dialog generation task does not take the input context into consideration and, hence, it grades the response irrespective of the context.
Neural ODEs with Irregular and Noisy Data
In our methodology, the main innovation can be seen in the integration of deep neural networks with the neural ordinary differential equations (ODEs) approach.
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.
A Study on Prompt-based Few-Shot Learning Methods for Belief State Tracking in Task-oriented Dialog Systems
Driven by the recent success of pre-trained language models and prompt-based learning, we explore prompt-based few-shot learning for Dialogue Belief State Tracking.
A Generative Approach for Financial Causality Extraction
Causality represents the foremost relation between events in financial documents such as financial news articles, financial reports.
Systematic Investigation of Strategies Tailored for Low-Resource Settings for Low-Resource Dependency Parsing
While these are well-known to the community, it is not trivial to select the best-performing combination of these strategies for a low-resource language that we are interested in, and not much attention has been given to measuring the efficacy of these strategies.
Prabhupadavani: A Code-mixed Speech Translation Data for 25 Languages
This data also can be used for a code-mixed machine translation task.
Cultural Vocal Bursts Intensity Prediction
Machine Translation
+1
LeSICiN: A Heterogeneous Graph-based Approach for Automatic Legal Statute Identification from Indian Legal Documents
The task of Legal Statute Identification (LSI) aims to identify the legal statutes that are relevant to a given description of Facts or evidence of a legal case.
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.
Representation Learning for Conversational Data using Discourse Mutual Information Maximization
Although many pretrained models exist for text or images, there have been relatively fewer attempts to train representations specifically for dialog understanding.
Learning Low-Dimensional Quadratic-Embeddings of High-Fidelity Nonlinear Dynamics using Deep Learning
It is, however, observed that the dynamics of high-fidelity models often evolve in low-dimensional manifolds.
PASTE: A Tagging-Free Decoding Framework Using Pointer Networks for Aspect Sentiment Triplet Extraction
Aspect Sentiment Triplet Extraction (ASTE) deals with extracting opinion triplets, consisting of an opinion target or aspect, its associated sentiment, and the corresponding opinion term/span explaining the rationale behind the sentiment.
Learning Dynamics from Noisy Measurements using Deep Learning with a Runge-Kutta Constraint
We demonstrate the effectiveness of the proposed method to learning models using data obtained from various differential equations.
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.
COMPARE: A Taxonomy and Dataset of Comparison Discussions in Peer Reviews
We present COMPARE, a taxonomy and a dataset of comparison discussions in peer reviews of research papers in the domain of experimental deep learning.
You too Brutus! Trapping Hateful Users in Social Media: Challenges, Solutions & Insights
Hate speech is regarded as one of the crucial issues plaguing the online social media.
A Greedy Data Collection Scheme For Linear Dynamical Systems
Mathematical models are essential to analyze and understand the dynamics of complex systems.
ArgFuse: A Weakly-Supervised Framework for Document-Level Event Argument Aggregation
Most of the existing information extraction frameworks (Wadden et al., 2019; Veysehet al., 2020) focus on sentence-level tasks and are hardly able to capture the consolidated information from a given document.
Multi-VFL: A Vertical Federated Learning System for Multiple Data and Label Owners
Vertical Federated Learning (VFL) refers to the collaborative training of a model on a dataset where the features of the dataset are split among multiple data owners, while label information is owned by a single data owner.
Automatic Speech Recognition in Sanskrit: A New Speech Corpus and Modelling Insights
In this work, we propose the first large scale study of automatic speech recognition (ASR) in Sanskrit, with an emphasis on the impact of unit selection in Sanskrit ASR.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Discovery of Nonlinear Dynamical Systems using a Runge-Kutta Inspired Dictionary-based Sparse Regression Approach
Discovering dynamical models to describe underlying dynamical behavior is essential to draw decisive conclusions and engineering studies, e. g., optimizing a process.
Event Argument Extraction using Causal Knowledge Structures
We develop a causal network for our event-annotated dataset by extracting relevant event causal structures from ConceptNet and phrases from Wikipedia.
Evaluating Neural Word Embeddings for Sanskrit
To effectively use such readily available resources, it is very much essential to perform a systematic study on word embedding approaches for the Sanskrit language.
Deep Neural Approaches to Relation Triplets Extraction: A Comprehensive Survey
Recently, with the advances made in continuous representation of words (word embeddings) and deep neural architectures, many research works are published in the area of relation extraction and it is very difficult to keep track of so many papers.
LQResNet: A Deep Neural Network Architecture for Learning Dynamic Processes
In this work, we suggest combining the operator inference with certain deep neural network approaches to infer the unknown nonlinear dynamics of the system.
A Little Pretraining Goes a Long Way: A Case Study on Dependency Parsing Task for Low-resource Morphologically Rich Languages
In this work, we focus on dependency parsing for morphological rich languages (MRLs) in a low-resource setting.
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.
Reproducibility, Replicability and Beyond: Assessing Production Readiness of Aspect Based Sentiment Analysis in the Wild
With the exponential growth of online marketplaces and user-generated content therein, aspect-based sentiment analysis has become more important than ever.
Joint Autoregressive and Graph Models for Software and Developer Social Networks
This "social network of code" is rarely studied by social network researchers.
Medical Entity Linking using Triplet Network
Entity linking (or Normalization) is an essential task in text mining that maps the entity mentions in the medical text to standard entities in a given Knowledge Base (KB).
HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection
We also observe that models, which utilize the human rationales for training, perform better in reducing unintended bias towards target communities.
Ranked #3 on
Hate Speech Detection
on HateXplain
Automatic Charge Identification from Facts: A Few Sentence-Level Charge Annotations is All You Need
Additionally, we propose a novel model that utilizes sentence-level charge labels as an auxiliary task, coupled with the main task of document-level charge identification in a multi-task learning framework.
Finding Prerequisite Relations between Concepts using Textbook
In the current work, we present a method of finding prerequisite relations between concepts using related textbooks.
Hierarchical Transformer for Task Oriented Dialog Systems
Generative models for dialog systems have gained much interest because of the recent success of RNN and Transformer based models in tasks like question answering and summarization.
Operator Inference and Physics-Informed Learning of Low-Dimensional Models for Incompressible Flows
To that end, we utilize the intrinsic structure of the Navier-Stokes equations for incompressible flows and show that learning dynamics of the velocity and pressure can be decoupled, thus leading to an efficient operator inference approach for learning the underlying dynamics of incompressible flows.
MatScIE: An automated tool for the generation of databases of methods and parameters used in the computational materials science literature
The number of published articles in the field of materials science is growing rapidly every year.
Data-Driven Learning of Reduced-order Dynamics for a Parametrized Shallow Water Equation
This paper discusses a non-intrusive data-driven model order reduction method that learns low-dimensional dynamical models for a parametrized shallow water equation.
Numerical Analysis Numerical Analysis
Fast Neural Models for Symbolic Regression at Scale
Deep learning owes much of its success to the astonishing expressiveness of neural networks.
Logic Constrained Pointer Networks for Interpretable Textual Similarity
We study the problem of aligning components of sentences leading to an interpretable model for semantic textual similarity.
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.
Aspect-based Sentiment Analysis of Scientific Reviews
We also investigate the extent of disagreement between the reviewers and the chair and find that the inter-reviewer disagreement may have a link to the disagreement with the chair.
Using Large Pretrained Language Models for Answering User Queries from Product Specifications
While certain questions can only be answered after using the product, there are many questions which can be answered from the product specification itself.
Evaluating Neural Morphological Taggers for Sanskrit
Neural sequence labelling approaches have achieved state of the art results in morphological tagging.
SHR++: An Interface for Morpho-syntactic Annotation of Sanskrit Corpora
It incorporates analyses and predictions from various tools designed for processing texts in Sanskrit, and utilise them to ease the cognitive load of the human annotators.
Neural Approaches for Data Driven Dependency Parsing in Sanskrit
We compare the performance of each of the models in a low-resource setting, with 1, 500 sentences for training.
Exploring Effects of Random Walk Based Minibatch Selection Policy on Knowledge Graph Completion
In this paper, we have explored the effects of different minibatch sampling techniques in Knowledge Graph Completion.
Low-Rank and Total Variation Regularization and Its Application to Image Recovery
In this work, we propose a new problem formulation in such a way that we seek to recover an image that is of low-rank and has sparsity in a transformed domain.
Using Distributional Thesaurus Embedding for Co-hyponymy Detection
Discriminating lexical relations among distributionally similar words has always been a challenge for natural language processing (NLP) community.
Operator inference for non-intrusive model reduction of systems with non-polynomial nonlinear terms
The proposed method learns operators for the linear and polynomially nonlinear dynamics via a least-squares problem, where the given non-polynomial terms are incorporated in the right-hand side.
Biomedical Relation Classification by single and multiple source domain adaptation
Relation classification is crucial for inferring semantic relatedness between entities in a piece of text.
Identification of Port-Hamiltonian Systems from Frequency Response Data
In this paper, we study the identification problem of a passive system from tangential interpolation data.
Weakly-Supervised Deep Learning for Domain Invariant Sentiment Classification
The task of learning a sentiment classification model that adapts well to any target domain, different from the source domain, is a challenging problem.
HateMonitors: Language Agnostic Abuse Detection in Social Media
In this paper, we present our machine learning model, HateMonitor, developed for Hate Speech and Offensive Content Identification in Indo-European Languages (HASOC), a shared task at FIRE 2019.
Competing Topic Naming Conventions in Quora: Predicting Appropriate Topic Merges and Winning Topics from Millions of Topic Pairs
Our system is also able to predict ~ 25% of the correct case of merges within the first month of the merge and ~ 40% of the cases within a year.
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).
Poetry to Prose Conversion in Sanskrit as a Linearisation Task: A Case for Low-Resource Languages
Owing to the resource constraints, we formulate this task as a word ordering (linearisation) task.
On the Compositionality Prediction of Noun Phrases using Poincar\'e Embeddings
In particular, we use hypernymy information of the multiword and its constituents encoded in the form of the recently introduced Poincar{\'e} embeddings in addition to the distributional information to detect compositionality for noun phrases.
On the Compositionality Prediction of Noun Phrases using Poincaré Embeddings
In particular, we use hypernymy information of the multiword and its constituents encoded in the form of the recently introduced Poincar\'e embeddings in addition to the distributional information to detect compositionality for noun phrases.
DeepTagRec: A Content-cum-User based Tag Recommendation Framework for Stack Overflow
In this paper, we develop a content-cum-user based deep learning framework DeepTagRec to recommend appropriate question tags on Stack Overflow.
Misleading Metadata Detection on YouTube
YouTube is the leading social media platform for sharing videos.
Hateminers : Detecting Hate speech against Women
With the online proliferation of hate speech, there is an urgent need for systems that can detect such harmful content.
Detecting Reliable Novel Word Senses: A Network-Centric Approach
The outlined method can therefore be used as a new post-hoc step to improve the precision of novel word sense detection in a robust and reliable way where the underlying framework uses a graph structure.
Analyzing the hate and counter speech accounts on Twitter
We also build a supervised model for classifying the hateful and counterspeech accounts on Twitter and obtain an F-score of 0. 77.
Social and Information Networks
Spread of hate speech in online social media
The present online social media platform is afflicted with several issues, with hate speech being on the predominant forefront.
Social and Information Networks
Deep Dive into Anonymity: A Large Scale Analysis of Quora Questions
In particular, we observe that the choice to post the question as anonymous is dependent on the user's perception of anonymity and they often choose to speak about depression, anxiety, social ties and personal issues under the guise of anonymity.
Upcycle Your OCR: Reusing OCRs for Post-OCR Text Correction in Romanised Sanskrit
We propose a post-OCR text correction approach for digitising texts in Romanised Sanskrit.
Free as in Free Word Order: An Energy Based Model for Word Segmentation and Morphological Tagging in Sanskrit
The configurational information in sentences of a free word order language such as Sanskrit is of limited use.
Thou shalt not hate: Countering Online Hate Speech
In this paper, we create and release the first ever dataset for counterspeech using comments from YouTube.
Social and Information Networks
WikiRef: Wikilinks as a route to recommending appropriate references for scientific Wikipedia pages
In this paper, we propose a novel two step approach -- WikiRef -- that (i) leverages the wikilinks present in a scientific Wikipedia target page and, thereby, (ii) recommends highly relevant references to be included in that target page appropriately and automatically borrowed from the reference section of the wikilinks.
Can Network Embedding of Distributional Thesaurus be Combined with Word Vectors for Better Representation?
), we turn a distributional thesaurus network into dense word vectors and investigate the usefulness of distributional thesaurus embedding in improving overall word representation.
Building a Word Segmenter for Sanskrit Overnight
There is an abundance of digitised texts available in Sanskrit.
Network Features Based Co-hyponymy Detection
Distinguishing lexical relations has been a long term pursuit in natural language processing (NLP) domain.
Automated Early Leaderboard Generation From Comparative Tables
We propose several approaches to rank papers from these noisy 'match' outcomes.
Adapting predominant and novel sense discovery algorithms for identifying corpus-specific sense differences
Word senses are not static and may have temporal, spatial or corpus-specific scopes.
AppTechMiner: Mining Applications and Techniques from Scientific Articles
We also categorize individual research articles based on their application areas and the techniques proposed/improved in the article.
A Graph Based Semi-Supervised Approach for Analysis of Derivational Nouns in Sanskrit
Derivational nouns are widely used in Sanskrit corpora and represent an important cornerstone of productivity in the language.
A Dataset for Sanskrit Word Segmentation
The last decade saw a surge in digitisation efforts for ancient manuscripts in Sanskrit.
A Two-Phase Approach Towards Identifying Argument Structure in Natural Language
We also propose two baselines and observe that the proposed approach outperforms baseline systems for the final task of Structure Prediction.
Word Segmentation in Sanskrit Using Path Constrained Random Walks
In Sanskrit, the phonemes at the word boundaries undergo changes to form new phonemes through a process called as sandhi.
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.
Compound Type Identification in Sanskrit: What Roles do the Corpus and Grammar Play?
We construct an elaborate features space for our system by combining conditional rules from the grammar \textit{Adṣṭ{\=a}dhy{\=a}y{\=\i}}, semantic relations between the compound components from a lexical database \textit{Amarakoṣa} and linguistic structures from the data using Adaptor Grammars.
Query Translation for Cross-Language Information Retrieval using Multilingual Word Clusters
In Cross-Language Information Retrieval, finding the appropriate translation of the source language query has always been a difficult problem to solve.
Summarizing Situational and Topical Information During Crises
The use of microblogging platforms such as Twitter during crises has become widespread.
Which techniques does your application use?: An information extraction framework for scientific articles
Every field of research consists of multiple application areas with various techniques routinely used to solve problems in these wide range of application areas.
UsingWord Embeddings for Query Translation for Hindi to English Cross Language Information Retrieval
In this paper, we propose an approach based on word embeddings, a method that captures contextual clues for a particular word in the source language and gives those words as translations that occur in a similar context in the target language.
A Novel Framework to Expedite Systematic Reviews by Automatically Building Information Extraction Training Corpora
Initially, it uses information contained in existing systematic reviews to identify the sentences from the PDF files of the included references that contain specific data elements of interest using a modified Jaccard similarity measure.
Towards automating the generation of derivative nouns in Sanskrit by simulating Panini
We also present cases where we have checked the applicability of the system with the rules which are not specifically applicable to derivation of derivative nouns, in order to see the effectiveness of the proposed schema as a generic system for modeling Astadhyayi.
That's sick dude!: Automatic identification of word sense change across different timescales
In this paper, we propose an unsupervised method to identify noun sense changes based on rigorous analysis of time-varying text data available in the form of millions of digitized books.
