Search Results for author: Soumen Chakrabarti

Found 41 papers, 20 papers with code

A Data Bootstrapping Recipe for Low-Resource Multilingual Relation Classification

no code implementations CoNLL (EMNLP) 2021 Arijit Nag, Bidisha Samanta, Animesh Mukherjee, Niloy Ganguly, Soumen Chakrabarti

Data collection is challenging for Indian languages, because they are syntactically and morphologically diverse, as well as different from resource-rich languages like English.

Classification Relation Classification

Structured Case-based Reasoning for Inference-time Adaptation of Text-to-SQL parsers

no code implementations10 Jan 2023 Abhijeet Awasthi, Soumen Chakrabarti, Sunita Sarawagi

To the best of our knowledge, we are the first to attempt inference-time adaptation of Text-to-SQL models, and harness trainable structured similarity between subqueries.

Semantic Parsing Text-To-SQL

mOKB6: A Multilingual Open Knowledge Base Completion Benchmark

no code implementations13 Nov 2022 Shubham Mittal, Keshav Kolluru, Soumen Chakrabarti, Mausam

Automated completion of open knowledge bases (KBs), which are constructed from triples of the form (subject phrase, relation phrase, object phrase) obtained via open information extraction (IE) from text, is useful for discovering novel facts that may not directly be present in the text.

coreference-resolution Coreference Resolution +2

Maximum Common Subgraph Guided Graph Retrieval: Late and Early Interaction Networks

no code implementations20 Oct 2022 Indradyumna Roy, Soumen Chakrabarti, Abir De

A common consideration for scoring similarity is the maximum common subgraph (MCS) between the query and corpus graphs, usually counting the number of common edges (i. e., MCES).


Neural Estimation of Submodular Functions with Applications to Differentiable Subset Selection

no code implementations20 Oct 2022 Abir De, Soumen Chakrabarti

We do not draw the concave function from a restricted family, but rather learn from data using a highly expressive neural network that implements a differentiable quadrature procedure.

TwiRGCN: Temporally Weighted Graph Convolution for Question Answering over Temporal Knowledge Graphs

no code implementations12 Oct 2022 Aditya Sharma, Apoorv Saxena, Chitrank Gupta, Seyed Mehran Kazemi, Partha Talukdar, Soumen Chakrabarti

Recent years have witnessed much interest in temporal reasoning over knowledge graphs (KG) for complex question answering (QA), but there remains a substantial gap in human capabilities.

Knowledge Graphs Question Answering

Semi-supervised Stance Detection of Tweets Via Distant Network Supervision

2 code implementations3 Jan 2022 Subhabrata Dutta, Samiya Caur, Soumen Chakrabarti, Tanmoy Chakraborty

Detecting and labeling stance in social media text is strongly motivated by hate speech detection, poll prediction, engagement forecasting, and concerted propaganda detection.

Hate Speech Detection Propaganda detection +1

A Data Bootstrapping Recipe for Low Resource Multilingual Relation Classification

no code implementations18 Oct 2021 Arijit Nag, Bidisha Samanta, Animesh Mukherjee, Niloy Ganguly, Soumen Chakrabarti

Relation classification (sometimes called 'extraction') requires trustworthy datasets for fine-tuning large language models, as well as for evaluation.

Classification Relation Classification

Topic Transferable Table Question Answering

1 code implementation EMNLP 2021 Saneem Ahmed Chemmengath, Vishwajeet Kumar, Samarth Bharadwaj, Jaydeep Sen, Mustafa Canim, Soumen Chakrabarti, Alfio Gliozzo, Karthik Sankaranarayanan

Weakly-supervised table question-answering(TableQA) models have achieved state-of-art performance by using pre-trained BERT transformer to jointly encoding a question and a table to produce structured query for the question.

Question Answering Question Generation +1

Incomplete Gamma Integrals for Deep Cascade Prediction using Content, Network, and Exogenous Signals

1 code implementation13 Jun 2021 Subhabrata Dutta, Shravika Mittal, Dipankar Das, Soumen Chakrabarti, Tanmoy Chakraborty

Second, there is a measurable positive correlation between the novelty of the root content (with respect to a streaming external corpus) and the relative size of the resulting cascade.

Question Answering Over Temporal Knowledge Graphs

2 code implementations ACL 2021 Apoorv Saxena, Soumen Chakrabarti, Partha Talukdar

Temporal Knowledge Graphs (Temporal KGs) extend regular Knowledge Graphs by providing temporal scopes (start and end times) on each edge in the KG.

Knowledge Graphs Question Answering

OpenIE6: Iterative Grid Labeling and Coordination Analysis for Open Information Extraction

1 code implementation EMNLP 2020 Keshav Kolluru, Vaibhav Adlakha, Samarth Aggarwal, Mausam, Soumen Chakrabarti

This IGL based coordination analyzer helps our OpenIE system handle complicated coordination structures, while also establishing a new state of the art on the task of coordination analysis, with a 12. 3 pts improvement in F1 over previous analyzers.

Open Information Extraction

IMoJIE: Iterative Memory-Based Joint Open Information Extraction

1 code implementation ACL 2020 Keshav Kolluru, Samarth Aggarwal, Vipul Rathore, Mausam, Soumen Chakrabarti

While traditional systems for Open Information Extraction were statistical and rule-based, recently neural models have been introduced for the task.

Open Information Extraction

Knowledge Base Completion: Baseline strikes back (Again)

1 code implementation2 May 2020 Prachi Jain, Sushant Rathi, Mausam, Soumen Chakrabarti

Most existing methods train with a small number of negative samples for each positive instance in these datasets to save computational costs.

Knowledge Base Completion Knowledge Base Population +2

Scene Graph based Image Retrieval -- A case study on the CLEVR Dataset

no code implementations3 Nov 2019 Sahana Ramnath, Amrita Saha, Soumen Chakrabarti, Mitesh M. Khapra

With the prolification of multimodal interaction in various domains, recently there has been much interest in text based image retrieval in the computer vision community.

Graph Matching Image Retrieval +2

Differentially Private Link Prediction With Protected Connections

no code implementations20 Jul 2019 Abir De, Soumen Chakrabarti

Link prediction (LP) algorithms propose to each node a ranked list of nodes that are currently non-neighbors, as the most likely candidates for future linkage.

Learning-To-Rank Link Prediction

A Deep Generative Model for Code-Switched Text

1 code implementation21 Jun 2019 Bidisha Samanta, Sharmila Reddy, Hussain Jagirdar, Niloy Ganguly, Soumen Chakrabarti

Code-switching, the interleaving of two or more languages within a sentence or discourse is pervasive in multilingual societies.

Topic Sensitive Attention on Generic Corpora Corrects Sense Bias in Pretrained Embeddings

1 code implementation ACL 2019 Vihari Piratla, Sunita Sarawagi, Soumen Chakrabarti

Given a small corpus $\mathcal D_T$ pertaining to a limited set of focused topics, our goal is to train embeddings that accurately capture the sense of words in the topic in spite of the limited size of $\mathcal D_T$.

GIRNet: Interleaved Multi-Task Recurrent State Sequence Models

1 code implementation28 Nov 2018 Divam Gupta, Tanmoy Chakraborty, Soumen Chakrabarti

A primary instance is also submitted to each auxiliary RNN, but their state sequences are gated and merged into a novel composite state sequence tailored to the primary inference task.

Part-Of-Speech Tagging Sentiment Analysis +1

Type-Sensitive Knowledge Base Inference Without Explicit Type Supervision

1 code implementation ACL 2018 Prachi Jain, Pankaj Kumar, {Mausam}, Soumen Chakrabarti

State-of-the-art knowledge base completion (KBC) models predict a score for every known or unknown fact via a latent factorization over entity and relation embeddings.

Entity Typing Knowledge Base Completion +4

Discriminative Link Prediction using Local Links, Node Features and Community Structure

no code implementations17 Oct 2013 Abir De, Niloy Ganguly, Soumen Chakrabarti

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.

Benchmarking Link Prediction

Cannot find the paper you are looking for? You can Submit a new open access paper.