Papers by Shikhar Vashishth
Graph-based Deep Learning in Natural Language Processing (D19-2)
Copied to clipboard
| Challenge: | This tutorial aims to introduce graph-based deep learning techniques such as Graph Convolutional Networks (GCNs) for Natural Language Processing (NLP) |
| Approach: | It provides a brief introduction to graph-based deep learning techniques such as Graph Convolutional Networks (GCNs) for Natural Language Processing (NLP). |
| Outcome: | This tutorial provides a brief introduction to graph-based deep learning techniques such as Graph Convolutional Networks (GCNs) for natural language processing (NLP). |
Robust Knowledge Graph Completion with Stacked Convolutions and a Student Re-Ranking Network (2021.acl-long)
Copied to clipboard
| Challenge: | Knowledge graphs (KGs) are incomplete because of the large number of benchmark datasets that are not representative of real KGs. |
| Approach: | They develop a deep convolutional network that utilizes textual entity representations to distill the knowledge from the convolution into a student network that re-ranks promising candidate entities. |
| Outcome: | The proposed model outperforms recent methods in a realistic setting where dense connectivity is not guaranteed. |
A Morphology-Based Investigation of Positional Encodings (2024.emnlp-main)
Copied to clipboard
| Challenge: | Contemporary deep learning models handle languages with diverse morphology . morphological complexity of languages is closely linked with positional encodings . |
| Approach: | They propose to use positional encodings to integrate morphological complexity into deep learning models. |
| Outcome: | The proposed model improves on 22 languages and 5 downstream tasks. |
Self-Influence Guided Data Reweighting for Language Model Pre-training (2023.emnlp-main)
Copied to clipboard
| Challenge: | Language Models (LMs) pre-trained with selfsupervision on large text data are the default starting point for developing models for various downstream tasks. |
| Approach: | They propose a method for jointly reweighting samples by leveraging self-influence scores as an indicator of sample importance and pre-training. |
| Outcome: | The proposed method promotes novelty and stability for model pre-training. |
Dating Documents using Graph Convolution Networks (P18-1)
Copied to clipboard
| Challenge: | Existing approaches for document dating assume accurate knowledge of document date, but this is not always available for arbitrary documents from the Web. |
| Approach: | They propose a Graph Convolutional Network (GCN) based document dating approach which exploits syntactic and temporal graph structures of document in a principled way. |
| Outcome: | The proposed approach outperforms state-of-the-art models on real-world datasets by 19% absolute accuracy points. |
A Re-evaluation of Knowledge Graph Completion Methods (2020.acl-main)
Copied to clipboard
| Challenge: | Knowledge Graph Completion (KGC) aims at automatically predicting missing links for large-scale knowledge graphs. |
| Approach: | They propose a protocol to evaluate KGC methods that is robust to handle bias in the model, which can substantially affect the final results. |
| Outcome: | The proposed evaluation protocol is robust to handle bias in the model, which can substantially affect the final results. |
Knowledge-Rich Self-Supervision for Biomedical Entity Linking (2022.findings-emnlp)
Copied to clipboard
Sheng Zhang, Hao Cheng, Shikhar Vashishth, Cliff Wong, Jinfeng Xiao, Xiaodong Liu, Tristan Naumann, Jianfeng Gao, Hoifung Poon
| Challenge: | Entity linking is challenging in high-value domains with myriad entities . standard classification approaches suffer from the annotation bottleneck . |
| Approach: | They propose a self-supervised approach to learn domain knowledge for biomedical entity linking . it generates self-reported mention examples on unlabeled text and trains contextual encoder . |
| Outcome: | The proposed method outperforms existing methods by 20 points in accuracy on biomedical datasets. |
Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks (P19-1)
Copied to clipboard
Shikhar Vashishth, Manik Bhandari, Prateek Yadav, Piyush Rai, Chiranjib Bhattacharyya, Partha Talukdar
| Challenge: | Existing word embedding methods utilize sequential context of a word to learn its embeddment, but such methods result in an explosion of the vocabulary size. |
| Approach: | They propose a flexible Graph Convolution based method for learning word embeddings that utilizes the dependency context of a word without increasing the vocabulary size. |
| Outcome: | The proposed model outperforms existing methods on intrinsic and extrinsic tasks and provides an advantage when used with ELMo. |
MedFilter: Improving Extraction of Task-relevant Utterances through Integration of Discourse Structure and Ontological Knowledge (2020.emnlp-main)
Copied to clipboard
| Challenge: | Identifying task-relevant utterances improves performance at downstream medical processing. |
| Approach: | They propose a novel approach that uses task-oriented conversations to improve utterance classification over SOTA models. |
| Outcome: | The proposed model improves on a corpus of 7,000 doctor-patient conversations on 7,000 patient conversations. |
LinguaMeta: Unified Metadata for Thousands of Languages (2024.lrec-main)
Copied to clipboard
| Challenge: | LinguaMeta is a unified repository of language metadata for thousands of languages. |
| Approach: | They introduce LinguaMeta, a unified resource for language metadata for thousands of languages. |
| Outcome: | The proposed resource is intended for use by researchers and organizations who aim to extend technology to thousands of languages. |
RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information (D18-1)
Copied to clipboard
| Challenge: | Distantly-supervised Relation Extraction (RE) methods ignore readily available side information. |
| Approach: | They propose a distantly-supervised neural relation extraction method which uses additional side information from KBs to train an extractor. |
| Outcome: | The proposed method improves performance even when limited side information is available. |