no code implementations • EMNLP 2020 • Amrith Krishna, Ashim Gupta, Deepak Garasangi, Pavankumar Satuluri, Pawan Goyal
We propose a graph-based model for joint morphological parsing and dependency parsing in Sanskrit.
no code implementations • ACL (ECNLP) 2021 • Kalyani Roy, Pawan Goyal, Manish Pandey
What makes this problem challenging is the diversity of product types and their attributes and values.
no code implementations • LREC 2022 • Ankan Mullick, Shubhraneel Pal, Tapas Nayak, Seung-Cheol Lee, Satadeep Bhattacharjee, Pawan Goyal
In the last few years, several attempts have been made on extracting information from material science research domain.
no code implementations • CL (ACL) 2020 • Amrith Krishna, Bishal Santra, Ashim Gupta, Pavankumar Satuluri, Pawan Goyal
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.
no code implementations • COLING 2022 • Aniruddha Roy, Rupak Kumar Thakur, Isha Sharma, Ashim Gupta, Amrith Krishna, Sudeshna Sarkar, Pawan Goyal
Further, we apply the model agnostic meta-learning approach to our base model.
no code implementations • ECNLP (ACL) 2022 • Kalyani Roy, Vineeth Balapanuru, Tapas Nayak, Pawan Goyal
In this paper, we investigate the suitability of the generative approach for PQA.
no code implementations • 29 Oct 2024 • Ankan Mullick, Sombit Bose, Abhilash Nandy, Gajula Sai Chaitanya, Pawan Goyal
Existing research primarily addresses simple queries with a single intent, lacking effective systems for handling complex queries with multiple intents and extracting different intent spans.
no code implementations • 9 Oct 2024 • Pretam Ray, Jivnesh Sandhan, Amrith Krishna, Pawan Goyal
Neural dependency parsing has achieved remarkable performance for low resource morphologically rich languages.
1 code implementation • 8 Oct 2024 • Sourjyadip Ray, Kushal Gupta, Soumi Kundu, Payal Arvind Kasat, Somak Aditya, Pawan Goyal
We introduce the Emergency Room Visual Question Answering (ERVQA) dataset, consisting of <image, question, answer> triplets covering diverse emergency room scenarios, a seminal benchmark for LVLMs.
1 code implementation • 20 Sep 2024 • Abhilash Nandy, Yash Agarwal, Ashish Patwa, Millon Madhur Das, Aman Bansal, Ankit Raj, Pawan Goyal, Niloy Ganguly
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.
no code implementations • 16 Sep 2024 • Süleyman Yıldız, Pawan Goyal, Peter Benner
However, symplectic projection requires the existence of fully discrete operators, and in many cases, such as black-box PDE solvers, these operators are inaccessible.
no code implementations • 5 Sep 2024 • Celine Reddig, Pawan Goyal, Igor Pontes Duff, Peter Benner
To circumvent this issue, in this work, we propose an active sampling strategy to sample only a few points from the given training set, which can allow us to estimate those subspaces accurately.
no code implementations • 27 Aug 2024 • Mohammad S. Khorrami, Pawan Goyal, Jaber R. Mianroodi, Bob Svendsen, Peter Benner, Dierk Raabe
The purpose of the current work is the development of a so-called physics-encoded Fourier neural operator (PeFNO) for surrogate modeling of the quasi-static equilibrium stress field in solids.
no code implementations • 16 Jul 2024 • Yaswanth Narsupalli, Abhranil Chandra, Sreevatsa Muppirala, Manish Gupta, Pawan Goyal
Interestingly, the framework is also applicable to reasoning tasks.
no code implementations • 9 Jul 2024 • Aniruddha Roy, Pretam Ray, Ayush Maheshwari, Sudeshna Sarkar, Pawan Goyal
Considering these expanding challenges, this paper explores a framework that leverages the benefits of a pre-trained language model along with knowledge distillation in a seq2seq architecture to facilitate translation for low-resource languages, including those not covered by mBART-50.
no code implementations • 7 Jul 2024 • Abhinav Joshi, Shounak Paul, Akshat Sharma, Pawan Goyal, Saptarshi Ghosh, Ashutosh Modi
Legal systems worldwide are inundated with exponential growth in cases and documents.
1 code implementation • 6 Jun 2024 • Ankan Mullick, Sombit Bose, Rounak Saha, Ayan Kumar Bhowmick, Pawan Goyal, Niloy Ganguly, Prasenjit Dey, Ravi Kokku
However, every persona of a domain has different requirements of information and hence their summarization.
1 code implementation • 3 May 2024 • Subhendu Khatuya, Rajdeep Mukherjee, Akash Ghosh, Manjunath Hegde, Koustuv Dasgupta, Niloy Ganguly, Saptarshi Ghosh, Pawan Goyal
We study the problem of automatically annotating relevant numerals (GAAP metrics) occurring in the financial documents with their corresponding XBRL tags.
1 code implementation • 3 May 2024 • Subhendu Khatuya, Koushiki Sinha, Niloy Ganguly, Saptarshi Ghosh, Pawan Goyal
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.
no code implementations • 27 Apr 2024 • Manav Nitin Kapadnis, Sohan Patnaik, Abhilash Nandy, Sourjyadip Ray, Pawan Goyal, Debdoot Sheet
Radiology Report Generation (R2Gen) demonstrates how Multi-modal Large Language Models (MLLMs) can automate the creation of accurate and coherent radiological reports.
1 code implementation • 6 Apr 2024 • Abhilash Nandy, Yash Kulkarni, Pawan Goyal, Niloy Ganguly
In this paper, we propose sequence-based pretraining methods to enhance procedural understanding in natural language processing.
1 code implementation • 4 Apr 2024 • Ankan Mullick, Mukur Gupta, Pawan Goyal
Biomedical queries have become increasingly prevalent in web searches, reflecting the growing interest in accessing biomedical literature.
1 code implementation • 30 Mar 2024 • Akash Ghosh, B Venkata Sahith, Niloy Ganguly, Pawan Goyal, Mayank Singh
Question-answering (QA) on hybrid scientific tabular and textual data deals with scientific information, and relies on complex numerical reasoning.
no code implementations • 1 Mar 2024 • Igor Pontes Duff, Pawan Goyal, Peter Benner
To this aim, we investigate the stability characteristics of control systems with energy-preserving nonlinearities, thereby identifying conditions under which such systems are bounded-input bounded-state stable.
no code implementations • 27 Feb 2024 • Ion Victor Gosea, Luisa Peterson, Pawan Goyal, Jens Bremer, Kai Sundmacher, Peter Benner
In this work, we address the challenge of efficiently modeling dynamical systems in process engineering.
no code implementations • 26 Feb 2024 • Ankan Mullick, Ayan Kumar Bhowmick, Raghav R, Ravi Kokku, Prasenjit Dey, Pawan Goyal, Niloy Ganguly
Dialog summarization has become increasingly important in managing and comprehending large-scale conversations across various domains.
no code implementations • 18 Jan 2024 • Ankan Mullick, Akash Ghosh, G Sai Chaitanya, Samir Ghui, Tapas Nayak, Seung-Cheol Lee, Satadeep Bhattacharjee, Pawan Goyal
Material science literature is a rich source of factual information about various categories of entities (like materials and compositions) and various relations between these entities, such as conductivity, voltage, etc.
1 code implementation • Conference on Information and Knowledge Management (CIKM) 2017 • Jatin Arora, Sumit Agrawal, Pawan Goyal, Sayan Pathak
This paper presents a deep learning based approach to extract product comparison information out of user reviews on various e-commerce websites.
Ranked #1 on
Predicate Detection
on Product Reviews 2017
(using extra training data)
1 code implementation • 24 Oct 2023 • Rajdeep Mukherjee, Nithish Kannen, Saurabh Kumar Pandey, Pawan Goyal
We then (pre)train an encoder-decoder model by applying contrastive learning on the decoder-generated aspect-aware sentiment representations of the masked terms.
Ranked #3 on
Aspect Sentiment Triplet Extraction
on ASTE-Data-V2
Aspect Sentiment Triplet Extraction
Aspect Term Extraction and Sentiment Classification
+4
1 code implementation • 22 Oct 2023 • Abhilash Nandy, Manav Nitin Kapadnis, Pawan Goyal, Niloy Ganguly
In this paper, we propose CLMSM, a domain-specific, continual pre-training framework, that learns from a large set of procedural recipes.
1 code implementation • 14 Oct 2023 • Jivnesh Sandhan, Yaswanth Narsupalli, Sreevatsa Muppirala, Sriram Krishnan, Pavankumar Satuluri, Amba Kulkarni, Pawan Goyal
This work introduces the novel task of nested compound type identification (NeCTI), which aims to identify nested spans of a multi-component compound and decode the implicit semantic relations between them.
no code implementations • 19 Sep 2023 • Rima Hazra, Mayank Singh, Pawan Goyal, Bibhas Adhikari, Animesh Mukherjee
Interdisciplinarity has over the recent years have gained tremendous importance and has become one of the key ways of doing cutting edge research.
no code implementations • 13 Sep 2023 • Ali Forootani, Pawan Goyal, Peter Benner
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.
1 code implementation • 26 Aug 2023 • Pawan Goyal, Süleyman Yıldız, Peter Benner
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.
1 code implementation • 26 Aug 2023 • Pawan Goyal, Igor Pontes Duff, Peter Benner
In this work, we propose inference formulations to learn quadratic models, which are stable by design.
1 code implementation • 14 Aug 2023 • Jivnesh Sandhan, Amruta Barbadikar, Malay Maity, Pavankumar Satuluri, Tushar Sandhan, Ravi M. Gupta, Pawan Goyal, Laxmidhar Behera
We provide a deep analysis of Siksastaka, a Sanskrit poem, from the perspective of 6 prominent kavyashastra schools, to illustrate the proposed framework.
no code implementations • 2 Aug 2023 • Süleyman Yıldız, Pawan Goyal, Thomas Bendokat, Peter Benner
By leveraging this, we obtain quadratic dynamics that are Hamiltonian in a transformed coordinate system.
1 code implementation • 9 Jun 2023 • Abhilash Nandy, Manav Nitin Kapadnis, Sohan Patnaik, Yash Parag Butala, Pawan Goyal, Niloy Ganguly
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.
1 code implementation • 9 Jun 2023 • Kishalay Das, Pawan Goyal, Seung-Cheol Lee, Satadeep Bhattacharjee, Niloy Ganguly
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.
no code implementations • 6 Jun 2023 • Soumya Sharma, Subhendu Khatuya, Manjunath Hegde, Afreen Shaikh. Koustuv Dasgupta, Pawan Goyal, Niloy Ganguly
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.
1 code implementation • 6 Jun 2023 • Soumya Sharma, Tapas Nayak, Arusarka Bose, Ajay Kumar Meena, Koustuv Dasgupta, Niloy Ganguly, Pawan Goyal
Relation extraction models trained on a source domain cannot be applied on a different target domain due to the mismatch between relation sets.
1 code implementation • 24 May 2023 • Bishal Santra, Sakya Basak, Abhinandan De, Manish Gupta, Pawan Goyal
The research contributes to a better understanding of how LLMs can be effectively used for building interactive systems.
1 code implementation • 19 Feb 2023 • Jivnesh Sandhan, Anshul Agarwal, Laxmidhar Behera, Tushar Sandhan, Pawan Goyal
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.
no code implementations • 19 Feb 2023 • Pawan Goyal, Benjamin Peherstorfer, Peter Benner
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.
1 code implementation • 19 Feb 2023 • Ankan Mullick, Ishani Mondal, Sourjyadip Ray, R Raghav, G Sai Chaitanya, Pawan Goyal
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.
no code implementations • 24 Jan 2023 • Pawan Goyal, Igor Pontes Duff, Peter Benner
Machine-learning technologies for learning dynamical systems from data play an important role in engineering design.
1 code implementation • 14 Jan 2023 • Kishalay Das, Bidisha Samanta, Pawan Goyal, Seung-Cheol Lee, Satadeep Bhattacharjee, Niloy Ganguly
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.
no code implementations • 1 Nov 2022 • Pawan Goyal, Peter Benner
To simplify this task, we aim to identify a coordinate transformation that allows us to represent the dynamics of nonlinear systems using a common, simple model structure.
1 code implementation • 22 Oct 2022 • Rajdeep Mukherjee, Abhinav Bohra, Akash Banerjee, Soumya Sharma, Manjunath Hegde, Afreen Shaikh, Shivani Shrivastava, Koustuv Dasgupta, Niloy Ganguly, Saptarshi Ghosh, Pawan Goyal
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.
1 code implementation • 21 Oct 2022 • Jivnesh Sandhan, Rathin Singha, Narein Rao, Suvendu Samanta, Laxmidhar Behera, Pawan Goyal
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.
1 code implementation • 14 Oct 2022 • Abhay Shukla, Paheli Bhattacharya, Soham Poddar, Rajdeep Mukherjee, Kripabandhu Ghosh, Pawan Goyal, Saptarshi Ghosh
Summarization of legal case judgement documents is a challenging problem in Legal NLP.
no code implementations • 21 Sep 2022 • Souvic Chakraborty, Pawan Goyal, Animesh Mukherjee
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.
1 code implementation • 13 Sep 2022 • Shounak Paul, Arpan Mandal, Pawan Goyal, Saptarshi Ghosh
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.
1 code implementation • COLING 2022 • Jivnesh Sandhan, Ashish Gupta, Hrishikesh Terdalkar, Tushar Sandhan, Suvendu Samanta, Laxmidhar Behera, Pawan Goyal
The phenomenon of compounding is ubiquitous in Sanskrit.
no code implementations • 15 Aug 2022 • Kalyani Roy, Tapas Nayak, Pawan Goyal
Attribute values of the products are an essential component in any e-commerce platform.
no code implementations • 21 May 2022 • Bishal Santra, Ravi Ghadia, Manish Gupta, Pawan Goyal
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.
no code implementations • 19 May 2022 • Pawan Goyal, Peter Benner
In our methodology, the main innovation can be seen in the integration of deep neural networks with the neural ordinary differential equations (ODEs) approach.
1 code implementation • Findings (NAACL) 2022 • Ankan Mullick, Sukannya Purkayastha, Pawan Goyal, Niloy Ganguly
However, the newer intents may not be explicitly announced and need to be inferred dynamically.
no code implementations • 18 Apr 2022 • Debjoy Saha, Bishal Santra, Pawan Goyal
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.
1 code implementation • 12 Apr 2022 • Tapas Nayak, Soumya Sharma, Yash Butala, Koustuv Dasgupta, Pawan Goyal, Niloy Ganguly
Causality represents the foremost relation between events in financial documents such as financial news articles, financial reports.
1 code implementation • LaTeCHCLfL (COLING) 2022 • Jivnesh Sandhan, Ayush Daksh, Om Adideva Paranjay, Laxmidhar Behera, Pawan Goyal
This data also can be used for a code-mixed machine translation task.
Cultural Vocal Bursts Intensity Prediction
Machine Translation
+1
1 code implementation • 27 Jan 2022 • Jivnesh Sandhan, Laxmidhar Behera, Pawan Goyal
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.
1 code implementation • 29 Dec 2021 • Shounak Paul, Pawan Goyal, Saptarshi Ghosh
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.
1 code implementation • 10 Dec 2021 • Rajdeep Mukherjee, Uppada Vishnu, Hari Chandana Peruri, Sourangshu Bhattacharya, Koustav Rudra, Pawan Goyal, Niloy Ganguly
Occurrences of catastrophes such as natural or man-made disasters trigger the spread of rumours over social media at a rapid pace.
no code implementations • NAACL 2022 • Bishal Santra, Sumegh Roychowdhury, Aishik Mandal, Vasu Gurram, Atharva Naik, Manish Gupta, Pawan Goyal
Although many pretrained models exist for text or images, there have been relatively fewer attempts to train representations specifically for dialog understanding.
no code implementations • 25 Nov 2021 • Pawan Goyal, Peter Benner
It is, however, observed that the dynamics of high-fidelity models often evolve in low-dimensional manifolds.
1 code implementation • EMNLP 2021 • Rajdeep Mukherjee, Tapas Nayak, Yash Butala, Sourangshu Bhattacharya, Pawan Goyal
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.
no code implementations • NeurIPS Workshop DLDE 2021 • Pawan Goyal, Peter Benner
We demonstrate the effectiveness of the proposed method to learning models using data obtained from various differential equations.
1 code implementation • Findings (EMNLP) 2021 • Abhilash Nandy, Soumya Sharma, Shubham Maddhashiya, Kapil Sachdeva, Pawan Goyal, Niloy Ganguly
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.
2 code implementations • 9 Aug 2021 • Shruti Singh, Mayank Singh, Pawan Goyal
We present COMPARE, a taxonomy and a dataset of comparison discussions in peer reviews of research papers in the domain of experimental deep learning.
1 code implementation • 1 Aug 2021 • Mithun Das, Punyajoy Saha, Ritam Dutt, Pawan Goyal, Animesh Mukherjee, Binny Mathew
Hate speech is regarded as one of the crucial issues plaguing the online social media.
no code implementations • 27 Jul 2021 • Karim Cherifi, Pawan Goyal, Peter Benner
Mathematical models are essential to analyze and understand the dynamics of complex systems.
1 code implementation • ACL (CASE) 2021 • Debanjana Kar, Sudeshna Sarkar, Pawan Goyal
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.
no code implementations • 10 Jun 2021 • Vaikkunth Mugunthan, Pawan Goyal, Lalana Kagal
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.
1 code implementation • Findings (ACL) 2021 • Devaraja Adiga, Rishabh Kumar, Amrith Krishna, Preethi Jyothi, Ganesh Ramakrishnan, Pawan Goyal
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
2 code implementations • 11 May 2021 • Pawan Goyal, Peter Benner
Discovering dynamical models to describe underlying dynamical behavior is essential to draw decisive conclusions and engineering studies, e. g., optimizing a process.
no code implementations • ICON 2020 • Debanjana Kar, Sudeshna Sarkar, Pawan Goyal
We develop a causal network for our event-annotated dataset by extracting relevant event causal structures from ConceptNet and phrases from Wikipedia.
1 code implementation • 1 Apr 2021 • Jivnesh Sandhan, Om Adideva, Digumarthi Komal, Laxmidhar Behera, Pawan Goyal
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.
no code implementations • 31 Mar 2021 • Tapas Nayak, Navonil Majumder, Pawan Goyal, Soujanya Poria
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.
1 code implementation • 3 Mar 2021 • Pawan Goyal, Peter Benner
In this work, we suggest combining the operator inference with certain deep neural network approaches to infer the unknown nonlinear dynamics of the system.
1 code implementation • EACL 2021 • Jivnesh Sandhan, Amrith Krishna, Ashim Gupta, Laxmidhar Behera, Pawan Goyal
In this work, we focus on dependency parsing for morphological rich languages (MRLs) in a low-resource setting.
no code implementations • WS 2014 • Rajkumar Pujari, Swara Desai, Niloy Ganguly, Pawan Goyal
This paper presents a novel two-stage framework to extract opinionated sentences from a given news article.
1 code implementation • 23 Jan 2021 • Rajdeep Mukherjee, Shreyas Shetty, Subrata Chattopadhyay, Subhadeep Maji, Samik Datta, Pawan Goyal
With the exponential growth of online marketplaces and user-generated content therein, aspect-based sentiment analysis has become more important than ever.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
no code implementations • 21 Jan 2021 • Rima Hazra, Hardik Aggarwal, Pawan Goyal, Animesh Mukherjee, Soumen Chakrabarti
This "social network of code" is rarely studied by social network researchers.
no code implementations • WS 2019 • Ishani Mondal, Sukannya Purkayastha, Sudeshna Sarkar, Pawan Goyal, Jitesh Pillai, Amitava Bhattacharyya, Mahanandeeshwar Gattu
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).
6 code implementations • 18 Dec 2020 • Binny Mathew, Punyajoy Saha, Seid Muhie Yimam, Chris Biemann, Pawan Goyal, Animesh Mukherjee
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
1 code implementation • COLING 2020 • Shounak Paul, Pawan Goyal, Saptarshi Ghosh
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.
no code implementations • 20 Nov 2020 • Shivam Pal, Vipul Arora, Pawan Goyal
In the current work, we present a method of finding prerequisite relations between concepts using related textbooks.
2 code implementations • NAACL 2021 • Bishal Santra, Potnuru Anusha, Pawan Goyal
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.
1 code implementation • 13 Oct 2020 • Peter Benner, Pawan Goyal, Jan Heiland, Igor Pontes Duff
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.
no code implementations • 15 Sep 2020 • Souradip Guha, Ankan Mullick, Jatin Agrawal, Swetarekha Ram, Samir Ghui, Seung-Cheol Lee, Satadeep Bhattacharjee, Pawan Goyal
The number of published articles in the field of materials science is growing rapidly every year.
1 code implementation • 28 Jul 2020 • Süleyman Yıldız, Pawan Goyal, Peter Benner, Bülent Karasözen
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
4 code implementations • 16 Jul 2020 • Owen Dugan, Rumen Dangovski, Allan Costa, Samuel Kim, Pawan Goyal, Joseph Jacobson, Marin Soljačić
Neural networks' expressiveness comes at the cost of complex, black-box models that often extrapolate poorly beyond the domain of the training dataset, conflicting with the goal of finding compact analytic expressions to describe scientific data.
1 code implementation • 15 Jul 2020 • Subhadeep Maji, Rohan Kumar, Manish Bansal, Kalyani Roy, Pawan Goyal
We study the problem of aligning components of sentences leading to an interpretable model for semantic textual similarity.
1 code implementation • 8 Jun 2020 • Rajdeep Mukherjee, Hari Chandana Peruri, Uppada Vishnu, Pawan Goyal, Sourangshu Bhattacharya, Niloy Ganguly
Manually extracting relevant aspects and opinions from large volumes of user-generated text is a time-consuming process.
1 code implementation • 5 Jun 2020 • Souvic Chakraborty, Pawan Goyal, Animesh Mukherjee
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.
no code implementations • WS 2020 • Kalyani Roy, Smit Shah, Nithish Pai, Jaidam Ramtej, Prajit Prashant Nadkarn, Jyotirmoy Banerjee, Pawan Goyal, Surender Kumar
While certain questions can only be answered after using the product, there are many questions which can be answered from the product specification itself.
1 code implementation • WS 2020 • Ashim Gupta, Amrith Krishna, Pawan Goyal, Oliver Hellwig
Neural sequence labelling approaches have achieved state of the art results in morphological tagging.
1 code implementation • LREC 2020 • Amrith Krishna, Shiv Vidhyut, Dilpreet Chawla, Sruti Sambhavi, Pawan Goyal
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.
no code implementations • 17 Apr 2020 • Amrith Krishna, Ashim Gupta, Deepak Garasangi, Jivnesh Sandhan, Pavankumar Satuluri, Pawan Goyal
We compare the performance of each of the models in a low-resource setting, with 1, 500 sentences for training.
no code implementations • 12 Apr 2020 • Bishal Santra, Prakhar Sharma, Sumegh Roychowdhury, Pawan Goyal
In this paper, we have explored the effects of different minibatch sampling techniques in Knowledge Graph Completion.
no code implementations • 12 Mar 2020 • Pawan Goyal, Hussam Al Daas, Peter Benner
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.
no code implementations • LREC 2020 • Abhik Jana, Nikhil Reddy Varimalla, Pawan Goyal
Discriminating lexical relations among distributionally similar words has always been a challenge for natural language processing (NLP) community.
2 code implementations • 22 Feb 2020 • Peter Benner, Pawan Goyal, Boris Kramer, Benjamin Peherstorfer, Karen Willcox
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.
no code implementations • WS 2019 • Sinchani Chakraborty, Sudeshna Sarkar, Pawan Goyal, Mahan Gattu, eeshwar
Relation classification is crucial for inferring semantic relatedness between entities in a piece of text.
1 code implementation • 31 Oct 2019 • Peter Benner, Pawan Goyal, Paul Van Dooren
In this paper, we study the identification problem of a passive system from tangential interpolation data.
no code implementations • 29 Oct 2019 • Pratik Kayal, Mayank Singh, Pawan Goyal
The task of learning a sentiment classification model that adapts well to any target domain, different from the source domain, is a challenging problem.
1 code implementation • 27 Sep 2019 • Punyajoy Saha, Binny Mathew, Pawan Goyal, Animesh Mukherjee
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.
no code implementations • 10 Sep 2019 • Binny Mathew, Suman Kalyan Maity, Pawan Goyal, Animesh Mukherjee
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.
1 code implementation • IJCNLP 2019 • Soumya Sharma, Bishal Santra, Abhik Jana, T. Y. S. S. Santosh, Niloy Ganguly, Pawan Goyal
Specifically, we experiment with fusing embeddings obtained from knowledge graph with the state-of-the-art approaches for NLI task (ESIM model).
no code implementations • ACL 2019 • Amrith Krishna, Vishnu Sharma, Bishal Santra, Aishik Chakraborty, Pavankumar Satuluri, Pawan Goyal
Owing to the resource constraints, we formulate this task as a word ordering (linearisation) task.
no code implementations • ACL 2019 • Abhik Jana, Dima Puzyrev, Alex Panchenko, er, Pawan Goyal, Chris Biemann, Animesh Mukherjee
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.
no code implementations • 7 Jun 2019 • Abhik Jana, Dmitry Puzyrev, Alexander Panchenko, Pawan Goyal, Chris Biemann, Animesh Mukherjee
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.
1 code implementation • 10 Mar 2019 • Suman Kalyan Maity, Abhishek Panigrahi, Sayan Ghosh, Arundhati Banerjee, Pawan Goyal, Animesh Mukherjee
In this paper, we develop a content-cum-user based deep learning framework DeepTagRec to recommend appropriate question tags on Stack Overflow.
1 code implementation • 25 Jan 2019 • Priyank Palod, Ayush Patwari, Sudhanshu Bahety, Saurabh Bagchi, Pawan Goyal
YouTube is the leading social media platform for sharing videos.
2 code implementations • 17 Dec 2018 • Punyajoy Saha, Binny Mathew, Pawan Goyal, Animesh Mukherjee
With the online proliferation of hate speech, there is an urgent need for systems that can detect such harmful content.
no code implementations • 14 Dec 2018 • Abhik Jana, Animesh Mukherjee, Pawan Goyal
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.
no code implementations • 6 Dec 2018 • Binny Mathew, Navish Kumar, Ravina, Pawan Goyal, Animesh Mukherjee
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
no code implementations • 4 Dec 2018 • Binny Mathew, Ritam Dutt, Pawan Goyal, Animesh Mukherjee
The present online social media platform is afflicted with several issues, with hate speech being on the predominant forefront.
Social and Information Networks
no code implementations • 17 Nov 2018 • Binny Mathew, Ritam Dutt, Suman Kalyan Maity, Pawan Goyal, Animesh Mukherjee
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.
1 code implementation • CONLL 2018 • Amrith Krishna, Bodhisattwa Prasad Majumder, Rajesh Shreedhar Bhat, Pawan Goyal
We propose a post-OCR text correction approach for digitising texts in Romanised Sanskrit.
1 code implementation • EMNLP 2018 • Amrith Krishna, Bishal Santra, Sasi Prasanth Bandaru, Gaurav Sahu, Vishnu Dutt Sharma, Pavankumar Satuluri, Pawan Goyal
The configurational information in sentences of a free word order language such as Sanskrit is of limited use.
2 code implementations • Proceedings of the International AAAI Conference on Web and Social Media 2019 • Binny Mathew, Hardik Tharad, Subham Rajgaria, Prajwal Singhania, Suman Kalyan Maity, Pawan Goyal, Animesh Mukherje
In this paper, we create and release the first ever dataset for counterspeech using comments from YouTube.
Social and Information Networks
no code implementations • COLING 2018 • Abhik Jana, Pranjal Kanojiya, Pawan Goyal, Animesh Mukherjee
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.
1 code implementation • LREC 2018 • Vikas Reddy, Amrith Krishna, Vishnu Dutt Sharma, Prateek Gupta, Vineeth M R, Pawan Goyal
There is an abundance of digitised texts available in Sanskrit.
no code implementations • NAACL 2018 • Abhik Jana, Pawan Goyal
), we turn a distributional thesaurus network into dense word vectors and investigate the usefulness of distributional thesaurus embedding in improving overall word representation.
no code implementations • LREC 2018 • Abhik Jana, Pawan Goyal
Distinguishing lexical relations has been a long term pursuit in natural language processing (NLP) domain.
no code implementations • 13 Feb 2018 • Mayank Singh, Rajdeep Sarkar, Atharva Vyas, Pawan Goyal, Animesh Mukherjee, Soumen Chakrabarti
We propose several approaches to rank papers from these noisy 'match' outcomes.
no code implementations • WS 2017 • Binny Mathew, Suman Kalyan Maity, Pratip Sarkar, Animesh Mukherjee, Pawan Goyal
Word senses are not static and may have temporal, spatial or corpus-specific scopes.
no code implementations • 10 Sep 2017 • Mayank Singh, Soham Dan, Sanyam Agarwal, Pawan Goyal, Animesh Mukherjee
We also categorize individual research articles based on their application areas and the techniques proposed/improved in the article.
no code implementations • WS 2017 • Amrith Krishna, Pavankumar Satuluri, Harshavardhan Ponnada, Muneeb Ahmed, Gulab Arora, Kaustubh Hiware, Pawan Goyal
Derivational nouns are widely used in Sanskrit corpora and represent an important cornerstone of productivity in the language.
no code implementations • WS 2017 • Amrith Krishna, Pavan Kumar Satuluri, Pawan Goyal
The last decade saw a surge in digitisation efforts for ancient manuscripts in Sanskrit.
no code implementations • WS 2016 • Arkanath Pathak, Pawan Goyal, Plaban Bhowmick
We also propose two baselines and observe that the proposed approach outperforms baseline systems for the final task of Structure Prediction.
no code implementations • COLING 2016 • Amrith Krishna, Bishal Santra, Pavankumar Satuluri, B, Sasi Prasanth aru, Bhumi Faldu, Yajuvendra Singh, Pawan Goyal
In Sanskrit, the phonemes at the word boundaries undergo changes to form new phonemes through a process called as sandhi.
no code implementations • WS 2016 • Ankan Mullick, Pawan Goyal, Niloy Ganguly
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.
no code implementations • WS 2016 • Amrith Krishna, Pavankumar Satuluri, Shubham Sharma, Apurv Kumar, Pawan Goyal
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.
no code implementations • WS 2016 • Paheli Bhattacharya, Pawan Goyal, Sudeshna Sarkar
In Cross-Language Information Retrieval, finding the appropriate translation of the source language query has always been a difficult problem to solve.
no code implementations • 5 Oct 2016 • Koustav Rudra, Siddhartha Banerjee, Niloy Ganguly, Pawan Goyal, Muhammad Imran, Prasenjit Mitra
The use of microblogging platforms such as Twitter during crises has become widespread.
no code implementations • 23 Aug 2016 • Soham Dan, Sanyam Agarwal, Mayank Singh, Pawan Goyal, Animesh Mukherjee
Every field of research consists of multiple application areas with various techniques routinely used to solve problems in these wide range of application areas.
no code implementations • 4 Aug 2016 • Paheli Bhattacharya, Pawan Goyal, Sudeshna Sarkar
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.
3 code implementations • 21 Jun 2016 • Tanmay Basu, Shraman Kumar, Abhishek Kalyan, Priyanka Jayaswal, Pawan Goyal, Stephen Pettifer, Siddhartha R. Jonnalagadda
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.
no code implementations • 17 Dec 2015 • Amrith Krishna, Pawan Goyal
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.
no code implementations • ACL 2014 • Sunny Mitra, Ritwik Mitra, Martin Riedl, Chris Biemann, Animesh Mukherjee, Pawan Goyal
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.