281 citations · 902 across the 36 of their papers we have counts for
41 papers
NeuroX Library for Neuron Analysis of Deep NLP Models
Fahim Dalvi, Hassan Sajjad, Nadir Durrani
Neuron analysis provides insights into how knowledge is structured in representations and discovers the role of neurons in the network. In addition to developing an understanding o…
NxPlain: Web-based Tool for Discovery of Latent Concepts
Fahim Dalvi, Nadir Durrani, Hassan Sajjad +3
The proliferation of deep neural networks in various domains has seen an increased need for the interpretability of these models, especially in scenarios where fairness and trust a…
Evaluating Neuron Interpretation Methods of NLP Models
Yimin Fan, Fahim Dalvi, Nadir Durrani +1
Neuron Interpretation has gained traction in the field of interpretability, and have provided fine-grained insights into what a model learns and how language knowledge is distribut…
ConceptX: A Framework for Latent Concept Analysis
Firoj Alam, Fahim Dalvi, Nadir Durrani +3
The opacity of deep neural networks remains a challenge in deploying solutions where explanation is as important as precision. We present ConceptX, a human-in-the-loop framework fo…
Impact of Adversarial Training on Robustness and Generalizability of Language Models
Enes Altinisik, Hassan Sajjad, Husrev Taha Sencar +2
Adversarial training is widely acknowledged as the most effective defense against adversarial attacks. However, it is also well established that achieving both robustness and gener…
On the Transformation of Latent Space in Fine-Tuned NLP Models
Nadir Durrani, Hassan Sajjad, Fahim Dalvi +1
We study the evolution of latent space in fine-tuned NLP models. Different from the commonly used probing-framework, we opt for an unsupervised method to analyze representations. M…
Post-hoc analysis of Arabic transformer models
Ahmed Abdelali, Nadir Durrani, Fahim Dalvi +1
Arabic is a Semitic language which is widely spoken with many dialects. Given the success of pre-trained language models, many transformer models trained on Arabic and its dialects…
Analyzing Encoded Concepts in Transformer Language Models
Hassan Sajjad, Nadir Durrani, Fahim Dalvi +3
We propose a novel framework ConceptX, to analyze how latent concepts are encoded in representations learned within pre-trained language models. It uses clustering to discover the…
Discovering Salient Neurons in Deep NLP Models
Nadir Durrani, Fahim Dalvi, Hassan Sajjad
While a lot of work has been done in understanding representations learned within deep NLP models and what knowledge they capture, little attention has been paid towards individual…
Discovering Latent Concepts Learned in BERT
Fahim Dalvi, Abdul Rafae Khan, Firoj Alam +3
A large number of studies that analyze deep neural network models and their ability to encode various linguistic and non-linguistic concepts provide an interpretation of the inner…
Probing for Constituency Structure in Neural Language Models
David Arps, Younes Samih, Laura Kallmeyer +1
In this paper, we investigate to which extent contextual neural language models (LMs) implicitly learn syntactic structure. More concretely, we focus on constituent structure as re…
Interpreting Arabic Transformer Models
Ahmed Abdelali, Nadir Durrani, Fahim Dalvi +1
Arabic is a Semitic language which is widely spoken with many dialects. Given the success of pre-trained language models, many transformer models trained on Arabic and its dialects…
Neuron-level Interpretation of Deep NLP Models: A Survey
Hassan Sajjad, Nadir Durrani, Fahim Dalvi
The proliferation of deep neural networks in various domains has seen an increased need for interpretability of these models. Preliminary work done along this line and papers that…
How transfer learning impacts linguistic knowledge in deep NLP models?
Nadir Durrani, Hassan Sajjad, Fahim Dalvi
Transfer learning from pre-trained neural language models towards downstream tasks has been a predominant theme in NLP recently. Several researchers have shown that deep NLP models…
Fine-grained Interpretation and Causation Analysis in Deep NLP Models
Hassan Sajjad, Narine Kokhlikyan, Fahim Dalvi +1
This paper is a write-up for the tutorial on "Fine-grained Interpretation and Causation Analysis in Deep NLP Models" that we are presenting at NAACL 2021. We present and discuss th…
Effect of Post-processing on Contextualized Word Representations
Hassan Sajjad, Firoj Alam, Fahim Dalvi +1
Post-processing of static embedding has beenshown to improve their performance on both lexical and sequence-level tasks. However, post-processing for contextualized embeddings is a…
Analyzing Individual Neurons in Pre-trained Language Models
Nadir Durrani, Hassan Sajjad, Fahim Dalvi +1
While a lot of analysis has been carried to demonstrate linguistic knowledge captured by the representations learned within deep NLP models, very little attention has been paid tow…
Fighting the COVID-19 Infodemic in Social Media: A Holistic Perspective and a Call to Arms
Firoj Alam, Fahim Dalvi, Shaden Shaar +8
With the outbreak of the COVID-19 pandemic, people turned to social media to read and to share timely information including statistics, warnings, advice, and inspirational stories.…
Similarity Analysis of Contextual Word Representation Models
John M. Wu, Yonatan Belinkov, Hassan Sajjad +3
This paper investigates contextual word representation models from the lens of similarity analysis. Given a collection of trained models, we measure the similarity of their interna…
Fighting the COVID-19 Infodemic: Modeling the Perspective of Journalists, Fact-Checkers, Social Media Platforms, Policy Makers, and the Society
Firoj Alam, Shaden Shaar, Fahim Dalvi +14
With the emergence of the COVID-19 pandemic, the political and the medical aspects of disinformation merged as the problem got elevated to a whole new level to become the first glo…
CrisisBench: Benchmarking Crisis-related Social Media Datasets for Humanitarian Information Processing
Firoj Alam, Hassan Sajjad, Muhammad Imran +1
Time-critical analysis of social media streams is important for humanitarian organizations for planing rapid response during disasters. The \textit{crisis informatics} research com…
Analyzing Redundancy in Pretrained Transformer Models
Fahim Dalvi, Hassan Sajjad, Nadir Durrani +1
Transformer-based deep NLP models are trained using hundreds of millions of parameters, limiting their applicability in computationally constrained environments. In this paper, we…
On the Effect of Dropping Layers of Pre-trained Transformer Models
Hassan Sajjad, Fahim Dalvi, Nadir Durrani +1
Transformer-based NLP models are trained using hundreds of millions or even billions of parameters, limiting their applicability in computationally constrained environments. While…
A Clustering Framework for Lexical Normalization of Roman Urdu
Abdul Rafae Khan, Asim Karim, Hassan Sajjad +2
Roman Urdu is an informal form of the Urdu language written in Roman script, which is widely used in South Asia for online textual content. It lacks standard spelling and hence pos…