Search Results for author: Saadullah Amin

Found 8 papers, 6 papers with code

Few-Shot Cross-lingual Transfer for Coarse-grained De-identification of Code-Mixed Clinical Texts

1 code implementation BioNLP (ACL) 2022 Saadullah Amin, Noon Pokaratsiri Goldstein, Morgan Kelly Wixted, Alejandro García-Rudolph, Catalina Martínez-Costa, Günter Neumann

Despite the advances in digital healthcare systems offering curated structured knowledge, much of the critical information still lies in large volumes of unlabeled and unstructured clinical texts.

Cross-Lingual Transfer De-identification +2

MedDistant19: Towards an Accurate Benchmark for Broad-Coverage Biomedical Relation Extraction

1 code implementation COLING 2022 Saadullah Amin, Pasquale Minervini, David Chang, Pontus Stenetorp, Günter Neumann

Relation extraction in the biomedical domain is challenging due to the lack of labeled data and high annotation costs, needing domain experts.

Relation Extraction

Temporal Knowledge Graph Reasoning with Low-rank and Model-agnostic Representations

1 code implementation RepL4NLP (ACL) 2022 Ioannis Dikeoulias, Saadullah Amin, Günter Neumann

Temporal knowledge graph completion (TKGC) has become a popular approach for reasoning over the event and temporal knowledge graphs, targeting the completion of knowledge with accurate but missing information.

Knowledge Graph Embedding Temporal Knowledge Graph Completion +1

T2NER: Transformers based Transfer Learning Framework for Named Entity Recognition

1 code implementation EACL 2021 Saadullah Amin, G. Neumann

In this work, we present a Transformers based Transfer Learning framework for Named Entity Recognition (T2NER) created in PyTorch for the task of NER with deep transformer models.

Domain Adaptation Multi-Task Learning +2

LowFER: Low-rank Bilinear Pooling for Link Prediction

1 code implementation ICML 2020 Saadullah Amin, Stalin Varanasi, Katherine Ann Dunfield, Günter Neumann

Bilinear models, while expressive, are prone to overfitting and lead to quadratic growth of parameters in number of relations.

Link Prediction Relational Reasoning

CopyBERT: A Unified Approach to Question Generation with Self-Attention

no code implementations WS 2020 Stalin Varanasi, Saadullah Amin, Guenter Neumann

Contextualized word embeddings provide better initialization for neural networks that deal with various natural language understanding (NLU) tasks including Question Answering (QA) and more recently, Question Generation(QG).

Dependency Parsing Language Modelling +5

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