Papers by Arjun Mukherjee
COIN – an Inexpensive and Strong Baseline for Predicting Out of Vocabulary Word Embeddings (2022.coling-1)
Copied to clipboard
| Challenge: | Word embedding models only include terms that occur a sufficient number of times in training corpora. |
| Approach: | They propose a method for predicting word embeddings for out of vocabulary terms using word2vec. |
| Outcome: | The proposed method surpasses several methods on benchmark tasks and is inexpensive to compute. |
Experiments with Convolutional Neural Networks for Multi-Label Authorship Attribution (L18-1)
Copied to clipboard
| Challenge: | Existing methods for authorship attribution tasks are difficult, but they are effective. |
| Approach: | They propose a CNN that averaging author probability distributions at sentence level for longer documents and treating smaller documents as sentences adapts to single-label datasets and various document sizes. |
| Outcome: | The proposed method outperforms state-of-the-art models on a single-label AA benchmark dataset. |
Attending Sentences to detect Satirical Fake News (C18-1)
Copied to clipboard
| Challenge: | Existing approaches to capture news satire do not explore sentence and document difference . |
| Approach: | They propose a hierarchical deep neural network approach for satire detection . it is able to capture satirical news both at the sentence level and document level . |
| Outcome: | The proposed approach can capture satire at sentence and document levels. |
Predicting Personal Opinion on Future Events with Fingerprints (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods to predict users’ opinions on going events may not be able to acquire such content and thus cannot infer an unbiased opinion on emerging events. |
| Approach: | They propose to model opinion on unseen articles based on one’s fingerprinting: the prior reading and commenting history. |
| Outcome: | The proposed model can predict user’s opinion on unseen articles based on one’s fingerprinting: the prior reading and commenting history. |
SHADES: Towards a Multilingual Assessment of Stereotypes in Large Language Models (2025.naacl-long)
Copied to clipboard
Margaret Mitchell, Giuseppe Attanasio, Ioana Baldini, Miruna Clinciu, Jordan Clive, Pieter Delobelle, Manan Dey, Sil Hamilton, Timm Dill, Jad Doughman, Ritam Dutt, Avijit Ghosh, Jessica Zosa Forde, Carolin Holtermann, Lucie-Aimée Kaffee, Tanmay Laud, Anne Lauscher, Roberto L Lopez-Davila, Maraim Masoud, Nikita Nangia, Anaelia Ovalle, Giada Pistilli, Dragomir Radev, Beatrice Savoldi, Vipul Raheja, Jeremy Qin, Esther Ploeger, Arjun Subramonian, Kaustubh Dhole, Kaiser Sun, Amirbek Djanibekov, Jonibek Mansurov, Kayo Yin, Emilio Villa Cueva, Sagnik Mukherjee, Jerry Huang, Xudong Shen, Jay Gala, Hamdan Al-Ali, null Tair Djanibekov, Nurdaulet Mukhituly, Shangrui Nie, Shanya Sharma, Karolina Stanczak, Eliza Szczechla, Tiago Timponi Torrent, Deepak Tunuguntla, Marcelo Viridiano, Oskar Van Der Wal, Adina Yakefu, Aurélie Névéol, Mike Zhang, Sydney Zink, Zeerak Talat
| Challenge: | Large Language Models reproduce and exacerbate social biases present in training data, and resources to quantify this issue are limited. |
| Approach: | They propose a multilingual parallel dataset to examine culturally-specific stereotypes that may be learned by LLMs. |
| Outcome: | The proposed dataset includes stereotypes from 20 regions around the world and 16 languages, spanning multiple identity categories subject to discrimination worldwide. |