Notes and Working Papers

A Short Tutorial on Variational Auto-Encoders
Ehsan Shareghi

On Reality and the Limits of Language Data
Nigel Collier, Fangyu Liu, Ehsan Shareghi
arxiv, 2022

Selected Papers

On the Effect of Isotropy on VAE Representations of Text
Lan Zhang, Wray Buntine, Ehsan Shareghi
Association for Computational Linguistics (ACL), 2022

Learning Sparse Sentence Encoding without Supervision
Victor Prokhorov, Yingzhen Li, Ehsan Shareghi, Nigel Collier
Workshop on Representation Learning for NLP (RepL4NLP), 2021

Compressed Nonparametric Language Modelling
Ehsan Shareghi, Reza Haffari, Trevor Cohn
International Joint Conference on Artificial Intelligence (IJCAI), 2017

Mixture-of-Partitions: Infusing Large Biomedical Knowledge Graphs into BERT
Zaiqiao Meng, Fangyu Liu, Thomas Hikaru Clark, Ehsan Shareghi, Nigel Collier
Empirical Methods in Natural Language Processing (EMNLP), 2021

Self-alignment Pre-training for Biomedical Entity Representations
Fangyu Liu, Ehsan Shareghi, Zaiqiao Meng, Marco Basaldella, Nigel Collier
North American Chapter of the Association for Computational Linguistics (NAACL), 2021

RedApt: An Adaptor for wav2vec 2 Encoding - Faster and Smaller Speech Translation without Quality Compromise
Jinming Zhao, Hao Yang, Reza Haffari, Ehsan Shareghi
Empirical Methods in Natural Language Processing (Findings of EMNLP), 2022

Self-supervised Rewiring of Pre-trained Speech Encoders: Towards Faster Fine-tuning with Less Labels in Speech Processing
Hao Yang, Jinming Zhao, Reza Haffari, Ehsan Shareghi
Empirical Methods in Natural Language Processing (Findings of EMNLP), 2022

All Papers

Generating Synthetic Speech from SpokenVocab for Speech Translation
Jinming Zhao, Reza Haffari, Ehsan Shareghi
European Chapter of the Association for Computational Linguistics (Findings of EACL), 2023

Self-supervised Graph Masking Pre-training for Graph-to-Text Generation
Jiuzhou Han, Ehsan Shareghi
Empirical Methods in Natural Language Processing (EMNLP), 2022

RedApt: An Adaptor for wav2vec 2 Encoding - Faster and Smaller Speech Translation without Quality Compromise
Jinming Zhao, Hao Yang, Reza Haffari, Ehsan Shareghi
Empirical Methods in Natural Language Processing (Findings of EMNLP), 2022

Self-supervised Rewiring of Pre-trained Speech Encoders: Towards Faster Fine-tuning with Less Labels in Speech Processing
Hao Yang, Jinming Zhao, Reza Haffari, Ehsan Shareghi
Empirical Methods in Natural Language Processing (Findings of EMNLP), 2022

M-Adapter: Modality Adaptation for End-to-End Speech-to-Text Translation
Jinming Zhao, Hao Yang, Reza Haffari, Ehsan Shareghi
International Speech Communication Association (Interspeech), 2022

TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning
Yixuan Su, Fangyu Liu, Zaiqiao Meng, Tian Lan, Lei Shu, Ehsan Shareghi, Nigel Collier
North American Chapter of the Association for Computational Linguistics (Findings of NAACL), 2022

On the Effect of Isotropy on VAE Representations of Text
Lan Zhang, Wray Buntine, Ehsan Shareghi
Association for Computational Linguistics (ACL), 2022

Fire Burns, Sword Cuts: Commonsense Inductive Bias for Exploration in Text-based Games
Dongwon Kelvin Ryu, Ehsan Shareghi, Meng Fang, Yunqiu Xu, Shirui Pan, Reza Haffari
Association for Computational Linguistics (ACL), 2022

Rewire-then-Probe: A Contrastive Recipe for Probing Biomedical Knowledge of Pre-trained Language Models
Zaiqiao Meng, Fangyu Liu, Ehsan Shareghi, Yixuan Su, Charlotte Collins, Nigel Collier
Association for Computational Linguistics (ACL), 2022

Mixture-of-Partitions: Infusing Large Biomedical Knowledge Graphs into BERT
Zaiqiao Meng, Fangyu Liu, Thomas Hikaru Clark, Ehsan Shareghi, Nigel Collier
Empirical Methods in Natural Language Processing (EMNLP), 2021

It Is Not As Good As You Think! Evaluating Simultaneous Machine Translation on Interpretation Data
Jinming Zhao, Philip Arthur, Reza Haffari, Trevor Cohn, Ehsan Shareghi
Empirical Methods in Natural Language Processing (EMNLP), 2021

Unsupervised Representation Disentanglement of Text
Lan Zhang, Victor Prokhorov, Ehsan Shareghi
Workshop on Representation Learning for NLP (RepL4NLP), 2021

Learning Sparse Sentence Encoding without Supervision
Victor Prokhorov, Yingzhen Li, Ehsan Shareghi, Nigel Collier
Workshop on Representation Learning for NLP (RepL4NLP), 2021

Integrating Transformers and Knowledge Graphs for Twitter Stance Detection
Thomas Hikaru Clark, Costanza Conforti, Fangyu Liu, Zaiqiao Meng, Ehsan Shareghi, Nigel Collier
Workshop on Noisy User-generated Text (W-NUT), 2021

A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters
Mengjie Zhao, Yi Zhu, Ehsan Shareghi, Ivan Vulić, Roi Reichart, Anna Korhonen, Hinrich Schütze
Association for Computational Linguistics (ACL), 2021

Self-alignment Pre-training for Biomedical Entity Representations
Fangyu Liu, Ehsan Shareghi, Zaiqiao Meng, Marco Basaldella, Nigel Collier
North American Chapter of the Association for Computational Linguistics (NAACL), 2021

Combining Deep Generative Models and Multi-lingual Pretraining for Semi-supervised Document Classification
Yi Zhu, Ehsan Shareghi, Yingzhen Li, Roi Reichart, Anna Korhonen
European Chapter of the Association for Computational Linguistics (EACL), 2021

COMETA: A Corpus for Medical Entity Linking in the Social Media
Marco Basaldella, Fangyu Liu, Ehsan Shareghi, Nigel Collier
Empirical Methods in Natural Language Processing (EMNLP), 2020

Bayesian Learning for Neural Dependency Parsing
Ehsan Shareghi, Yingzhen Li, Yi Zhu, Roi Reichart, Anna Korhonen
North American Chapter of the Association for Computational Linguistics (NAACL), 2019

A Bit of Progress and Stronger n-gram Language Modeling Baselines
Ehsan Shareghi, Daniela Gerz, Ivan Vulić, Anna Korhonen
North American Chapter of the Association for Computational Linguistics (NAACL), 2019

On the Importance of the Kullback-Leibler Divergence Term in Variational Autoencoders for Text Generation
Victor Prokhorov, Ehsan Shareghi, Yingzhen Li, ‪Mohammad Taher Pilehvar, Nigel Collier
Workshop on Neural Generation and Translation (WNGT), 2019

Compressed Nonparametric Language Modelling
Ehsan Shareghi, Reza Haffari, Trevor Cohn
International Joint Conference on Artificial Intelligence (IJCAI), 2017

Richer Interpolative Smoothing Based on Modified Kneser-Ney Language Modeling
Ehsan Shareghi, Reza Haffari, Trevor Cohn
Empirical Methods in Natural Language Processing (EMNLP), 2016

Fast, Small and Exact: Infinite-order Language Modelling with Compressed Suffix Trees
Ehsan Shareghi, Matthias Petri, Reza Haffari, Trevor Cohn
Transactions of the Association for Computational Linguistics (TACL), 2016

Compact, Efficient and Unlimited Capacity: Language Modeling with Compressed Suffix Trees
Ehsan Shareghi, Matthias Petri, Reza Haffari, Trevor Cohn
Empirical Methods in Natural Language Processing (EMNLP), 2015

Structured Prediction of Sequences and Trees using Infinite Contexts
Ehsan Shareghi, Reza Haffari, Trevor Cohn, Ann Nicholson
European Conference on Machine Learning (ECML), 2015