Search Results for author: Pranav Goel

Found 18 papers, 9 papers with code

Event Centric Entity Linking for Hindi News Articles: A Knowledge Graph Based Approach

no code implementations ICON 2019 Pranav Goel, Suhan Prabhu, Alok Debnath, Manish Shrivastava

We describe the development of a knowledge graph from an event annotated corpus by presenting a pipeline that identifies and extracts the relations between entities and events from Hindi news articles.

Entity Linking

Improving the TENOR of Labeling: Re-evaluating Topic Models for Content Analysis

1 code implementation29 Jan 2024 Zongxia Li, Andrew Mao, Daniel Stephens, Pranav Goel, Emily Walpole, Alden Dima, Juan Fung, Jordan Boyd-Graber

Topic models are a popular tool for understanding text collections, but their evaluation has been a point of contention.

Topic Models

Are Neural Topic Models Broken?

1 code implementation28 Oct 2022 Alexander Hoyle, Pranav Goel, Rupak Sarkar, Philip Resnik

Recently, the relationship between automated and human evaluation of topic models has been called into question.

Topic Models

Studying word order through iterative shuffling

1 code implementation EMNLP 2021 Nikolay Malkin, Sameera Lanka, Pranav Goel, Nebojsa Jojic

As neural language models approach human performance on NLP benchmark tasks, their advances are widely seen as evidence of an increasingly complex understanding of syntax.

Language Modelling Sentence

Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherence

2 code implementations NeurIPS 2021 Alexander Hoyle, Pranav Goel, Denis Peskov, Andrew Hian-Cheong, Jordan Boyd-Graber, Philip Resnik

To address the standardization gap, we systematically evaluate a dominant classical model and two state-of-the-art neural models on two commonly used datasets.

Topic Models

GPT Perdetry Test: Generating new meanings for new words

no code implementations NAACL 2021 Nikolay Malkin, Sameera Lanka, Pranav Goel, Sudha Rao, Nebojsa Jojic

Human innovation in language, such as inventing new words, is a challenge for pretrained language models.

Test

Is Automated Topic Model Evaluation Broken? The Incoherence of Coherence

1 code implementation NeurIPS 2021 Alexander Hoyle, Pranav Goel, Andrew Hian-Cheong, Denis Peskov, Jordan Lee Boyd-Graber, Philip Resnik

To address the standardization gap, we systematically evaluate a dominant classical model and two state-of-the-art neural models on two commonly used datasets.

Topic Models

Improving Neural Topic Models using Knowledge Distillation

1 code implementation EMNLP 2020 Alexander Hoyle, Pranav Goel, Philip Resnik

Topic models are often used to identify human-interpretable topics to help make sense of large document collections.

Knowledge Distillation Topic Models

Hindi TimeBank: An ISO-TimeML Annotated Reference Corpus

no code implementations LREC 2020 Pranav Goel, Suhan Prabhu, Alok Debnath, Priyank Modi, Manish Shrivastava

In this paper, we present the Hindi TimeBank, an ISO-TimeML annotated reference corpus for the detection and classification of events, states and time expressions, and the links between them.

How Pre-trained Word Representations Capture Commonsense Physical Comparisons

no code implementations WS 2019 Pranav Goel, Shi Feng, Jordan Boyd-Graber

One type of common sense is how two objects compare on physical properties such as size and weight: e. g., {`}is a house bigger than a person?{'}.

Common Sense Reasoning

How emotional are you? Neural Architectures for Emotion Intensity Prediction in Microblogs

1 code implementation COLING 2018 Devang Kulshreshtha, Pranav Goel, Anil Kumar Singh

Social media based micro-blogging sites like Twitter have become a common source of real-time information (impacting organizations and their strategies, and are used for expressing emotions and opinions.

Multi-Task Learning

IIT (BHU): System Description for LSDSem'17 Shared Task

no code implementations WS 2017 Pranav Goel, Anil Kumar Singh

This paper describes an ensemble system submitted as part of the LSDSem Shared Task 2017 - the Story Cloze Test.

Cloze Test Common Sense Reasoning +4

Automatic Identification of Sarcasm Target: An Introductory Approach

no code implementations22 Oct 2016 Aditya Joshi, Pranav Goel, Pushpak Bhattacharyya, Mark Carman

To compare our approach, we use two baselines: a na\"ive baseline and another baseline based on work in sentiment target identification.

Sarcasm Detection Sentence

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