no code implementations • 6 Apr 2024 • Poulami Ghosh, Shikhar Vashishth, Raj Dabre, Pushpak Bhattacharyya
How does the importance of positional encoding in pre-trained language models (PLMs) vary across languages with different morphological complexity?
1 code implementation • 4 Jan 2024 • Rachit Bansal, Bidisha Samanta, Siddharth Dalmia, Nitish Gupta, Shikhar Vashishth, Sriram Ganapathy, Abhishek Bapna, Prateek Jain, Partha Talukdar
Foundational models with billions of parameters which have been trained on large corpora of data have demonstrated non-trivial skills in a variety of domains.
no code implementations • 2 Nov 2023 • Megh Thakkar, Tolga Bolukbasi, Sriram Ganapathy, Shikhar Vashishth, Sarath Chandar, Partha Talukdar
Once the pre-training corpus has been assembled, all data samples in the corpus are treated with equal importance during LM pre-training.
no code implementations • 19 Sep 2023 • Shikhar Bharadwaj, Min Ma, Shikhar Vashishth, Ankur Bapna, Sriram Ganapathy, Vera Axelrod, Siddharth Dalmia, Wei Han, Yu Zhang, Daan van Esch, Sandy Ritchie, Partha Talukdar, Jason Riesa
Spoken language identification refers to the task of automatically predicting the spoken language in a given utterance.
no code implementations • 20 Jul 2023 • Anjali Raj, Shikhar Bharadwaj, Sriram Ganapathy, Min Ma, Shikhar Vashishth
In the recent years, speech representation learning is constructed primarily as a self-supervised learning (SSL) task, using the raw audio signal alone, while ignoring the side-information that is often available for a given speech recording.
no code implementations • 7 Jun 2023 • Shikhar Vashishth, Shikhar Bharadwaj, Sriram Ganapathy, Ankur Bapna, Min Ma, Wei Han, Vera Axelrod, Partha Talukdar
In this paper, we propose a novel framework of combining self-supervised representation learning with the language label information for the pre-training task.
no code implementations • 15 Dec 2021 • Sheng Zhang, Hao Cheng, Shikhar Vashishth, Cliff Wong, Jinfeng Xiao, Xiaodong Liu, Tristan Naumann, Jianfeng Gao, Hoifung Poon
Zero-shot entity linking has emerged as a promising direction for generalizing to new entities, but it still requires example gold entity mentions during training and canonical descriptions for all entities, both of which are rarely available outside of Wikipedia.
1 code implementation • ACL 2021 • Justin Lovelace, Denis Newman-Griffis, Shikhar Vashishth, Jill Fain Lehman, Carolyn Penstein Rosé
We develop a deep convolutional network that utilizes textual entity representations and demonstrate that our model outperforms recent KG completion methods in this challenging setting.
2 code implementations • ICLR 2021 • Rishabh Joshi, Vidhisha Balachandran, Shikhar Vashishth, Alan Black, Yulia Tsvetkov
To successfully negotiate a deal, it is not enough to communicate fluently: pragmatic planning of persuasive negotiation strategies is essential.
1 code implementation • EMNLP 2020 • Sopan Khosla, Shikhar Vashishth, Jill Fain Lehman, Carolyn Rose
In this paper, we propose the novel modeling approach MedFilter, which addresses these insights in order to increase performance at identifying and categorizing task-relevant utterances, and in so doing, positively impacts performance at a downstream information extraction task.
1 code implementation • 1 May 2020 • Shikhar Vashishth, Denis Newman-Griffis, Rishabh Joshi, Ritam Dutt, Carolyn Rose
To address the dearth of annotated training data for medical entity linking, we present WikiMed and PubMedDS, two large-scale medical entity linking datasets, and demonstrate that pre-training MedType on these datasets further improves entity linking performance.
2 code implementations • ACL 2020 • Zhiqing Sun, Shikhar Vashishth, Soumya Sanyal, Partha Talukdar, Yiming Yang
Knowledge Graph Completion (KGC) aims at automatically predicting missing links for large-scale knowledge graphs.
Ranked #25 on Link Prediction on FB15k-237 (MR metric)
2 code implementations • 8 Nov 2019 • Shikhar Vashishth
Knowledge graphs are structured representations of facts in a graph, where nodes represent entities and edges represent relationships between them.
4 code implementations • ICLR 2020 • Shikhar Vashishth, Soumya Sanyal, Vikram Nitin, Partha Talukdar
Multi-relational graphs are a more general and prevalent form of graphs where each edge has a label and direction associated with it.
Ranked #22 on Link Prediction on FB15k-237
1 code implementation • 1 Nov 2019 • Shikhar Vashishth, Soumya Sanyal, Vikram Nitin, Nilesh Agrawal, Partha Talukdar
In this paper, we analyze how increasing the number of these interactions affects link prediction performance, and utilize our observations to propose InteractE.
Ranked #11 on Link Prediction on YAGO3-10
2 code implementations • 24 Sep 2019 • Shikhar Vashishth, Shyam Upadhyay, Gaurav Singh Tomar, Manaal Faruqui
The attention layer in a neural network model provides insights into the model's reasoning behind its prediction, which are usually criticized for being opaque.
1 code implementation • 1 Feb 2019 • Shikhar Vashishth, Prince Jain, Partha Talukdar
Open Information Extraction (OpenIE) methods extract (noun phrase, relation phrase, noun phrase) triples from text, resulting in the construction of large Open Knowledge Bases (Open KBs).
Ranked #1 on Noun Phrase Canonicalization on Ambiguous Dataset
1 code implementation • ACL 2018 • Shikhar Vashishth, Shib Sankar Dasgupta, Swayambhu Nath Ray, Partha Talukdar
While existing approaches for these tasks assume accurate knowledge of the document date, this is not always available, especially for arbitrary documents from the Web.
Ranked #1 on Document Dating on APW
1 code implementation • 24 Jan 2019 • Shikhar Vashishth, Prateek Yadav, Manik Bhandari, Partha Talukdar
Graph-based Semi-Supervised Learning (SSL) methods aim to address this problem by labeling a small subset of the nodes as seeds and then utilizing the graph structure to predict label scores for the rest of the nodes in the graph.
1 code implementation • EMNLP 2018 • Shikhar Vashishth, Rishabh Joshi, Sai Suman Prayaga, Chiranjib Bhattacharyya, Partha Talukdar
In this paper, we propose RESIDE, a distantly-supervised neural relation extraction method which utilizes additional side information from KBs for improved relation extraction.
Ranked #5 on Relation Extraction on NYT Corpus
1 code implementation • ACL 2019 • Shikhar Vashishth, Manik Bhandari, Prateek Yadav, Piyush Rai, Chiranjib Bhattacharyya, Partha Talukdar
Word embeddings have been widely adopted across several NLP applications.
1 code implementation • 29 May 2018 • Prateek Yadav, Madhav Nimishakavi, Naganand Yadati, Shikhar Vashishth, Arun Rajkumar, Partha Talukdar
We analyse local and global properties of graphs and demonstrate settings where LCNs tend to work better than GCNs.