We meet on a weely basis to discuss recent research papers. Here is the schedule and the papers presented.


Date Speaker Title  
09/02/24 Junjie    
02/02/24 Huda    
26/01/24 Salem    
19/01/24 Mike    
12/01/24 Tulika    
05/01/24 Procheta    
15/12/23 Danushka, Meng, Jodie EMNLP-23 overview  
08/12/23 No meeting due to EMNLP    
01/12/23 Liangfang    
24/11/23 Danushka An Information-theoretic Approach to Prompt Engineering Without Ground Truth Labels  
17/11/23 Tianhui IJCNLP-AACL 2023 Overview  
10/11/23 Jodie Assessing Multilingual Fairness in Pre-trained Multimodal Representations  
03/11/23 No meeting due to IJCNLP-AACL    
27/10/23 Danushka Discovering Universal Geometry in Embeddings with ICA  
20/10/23 Huda Direct Fact Retrieval from Knowledge Graphs without Entity Linking  
13/10/23 Tianhui    
10/06/23 Tulika    
29/09/23 Procheta Self-Refine: Iterative Refinement with Self-Feedback  
22/09/23 Mike Should You Mask 15% in Masked Language Modeling?  
14/09/23 Jodie Having Beer after Prayer? Measuring Cultural Bias in Large Language Models  
07/09/23 Danushka XL-LEXEME: WiC Pretrained Model for Cross-Lingual LEXical sEMantic changE  
20/07/23 Danushka (ACL update)    
13/07/23 No meeting (ACL@Toronto)    
06/07/23 Huda Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling. poster and presentation  
29/06/23 Tianhui LoRA: Low-Rank Adaptation of Large Language Models(https://arxiv.org/abs/2106.09685)  
22/06/23 No meeting (EMNLP preparations)    
15/06/23 Procheta Tutorial rehersal  
08/06/23 Skipped due to NLP Symposium    
01/06/23 Danushka Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph Experts  
25/05/23 Mike Chain-of-Thought Prompting Elicits Reasoning in Large Language Models  
18/05/23 Jodie We’re Afraid Language Models Aren’t Modeling Ambiguity  
11/05/23 Huda Decoupling Mixture-of-Graphs: Unseen Relational Learning for Knowledge Graph Completion by Fusing Ontology and Textual Experts  
04/05/23 Tianhui Multimodal Chain-of-Thought Reasoning in Language Models  
27/04/23 Danushka Generated Knowledge Prompting for Commonsense Reasoning  
20/04/23 Procheta “Why Should I Trust You?”: Explaining the Predictions of Any Classifier  
13/04/23 Tulika ECIR conference update  
06/04/23 Mike Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusion  
30/03/23 Jodie XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models  
23/03/23 Huda Do Pre-trained Models Benefit Knowledge Graph Completion? A Reliable Evaluation and a Reasonable Approach  
16/03/23 Xiaohang Time-Aware Language Models as Temporal Knowledge Bases  
09/03/23 Gaifan Compressing Sentence Representation for Semantic Retrieval via Homomorphic Projective Distillation  
02/03/23 Tianhui Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoning  
16/02/23 Tulika Aspect-Controllable Opinion Summarization  
09/02/23 Procheta Dialog Inpainting: Turning Documents into Dialogs  
02/02/23 Danushka Accelerating Large-Scale Inference with Anisotropic Vector Quantization  
26/01/23 Jodie Retrieval Augmentation for Commonsense Reasoning: A Unified Approach  
19/01/23 Huda FPC: Fine-tuning with Prompt Curriculum for Relation Extraction  
05/01/23 Mike Generative Knowledge Graph Construction: A Review  
22/12/22 Tulika Many Hands Make Light Work: Using Essay Traits to Automatically Score Essays  
15/12/22 Jodie and Danushka EMNLP 2022 Summary  
01/12/22 Jodie ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding  
24/11/22 Aida MelBERT: Metaphor Detection via Contextualized Late Interaction using Metaphorical Identification Theories  
17/11/22 Huda Deep Bidirectional Language-Knowledge Graph Pretraining  
10/11/22 Danushka Learning To Retrieve Prompts for In-Context Learning  
03/11/22 Tulika Dr. Can See: Towards a Multi-modal Disease Diagnosis Virtual Assistant  
27/10/22 Mike An End-to-end Model for Entity-level Relation Extraction using Multi-instance Learning  
13/10/22 Tianhui Enhancing Topic-to-Essay Generation with External Commonsense Knowledge  
06/10/22 Huda Document-Level Relation Extraction with Sentences Importance Estimation and Focusing  
29/09/22 Procheta Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation  
22/09/22 Danushka IR like a SIR: Sense-enhanced Information Retrieval for Multiple Languages  
08/09/22 Danushka Word2Box: Capturing Set-Theoretic Semantics of Words using Box Embeddings  
23/08/22 Jodie MetaICL: Learning to Learn In Context  
02/08/22 Huda On Transferability of Prompt Tuning for Natural Language Processing and Learning to Transfer Prompts for Text Generation  
26/07/22 Michael Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks  
12/07/22 Danushka Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity  
05/07/22 Angrosh IsoBN: Fine-Tuning BERT with Isotropic Batch Normalization  
28/06/22 Jodie Nibbling at the Hard Core of Word Sense Disambiguation  
14/06/22 Huda Learning to Borrow – Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph Completion  
07/06/22 Michael Meta-learning via Language Model In-context Tuning  
17/05/22 Danushka ACL summary  
10/05/22 Angrosh Label Verbalization and Entailment for Effective Zero- and Few-Shot Relation Extraction  
26/05/22 Huda Learning to Borrow – Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph Completion  
19/04/22 Jodie Sense Embeddings are also Biased–Evaluating Social Biases in Static and Contextualised Sense Embeddings  
12/04/22 Michael Position-based Prompting for Health Outcome Generation  
05/04/22 Danushka Generating Datasets with Pretrained Language Models  
29/03/22 Huda Exploring Task Difficulty for Few-Shot Relation Extraction  
22/03/22 Jodie Word sense disambiguation: Towards interactive context exploitation from both word and sense perspectives  
15/03/22 Michael CROSSFIT : A Few-shot Learning Challenge for Cosstask generalisation in NLP  
08/03/22 Danushka PairRE: Knowledge Graph Embeddings via Paired Relation Vectors  
01/03/22 Angrosh Relation Classification with Entity Type Restriction  
22/02/22 Huda Entity Concept-enhanced Few-shot Relation Extraction  
15/02/22 Danushka Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning  
08/02/22 Michael Making Pre-trained Language Models Better Few-shot Learners  
02/02/22 Jodie ESC: Redesigning WSD with Extractive Sense Comprehension  
26/01/22 Huda CoLAKE: Contextualized Language and Knowledge Embedding  
19/01/22 Danushka Knowlege base completion meets transfer learning  
24/11/21 Jodie ConSeC: Word Sense Disambiguation as Continuous Sense Comprehension  
17/11/21 Micheal When does Further Pre-training MLM Help? An Empirical Study on Task-Oriented Dialog Pre-training  
3/11/21 Angrosh Graph Transformer Networks  
27/10/21 Huda Distilling Relation Embeddings from Pre-trained Language Models  
20/10/21 Danushka Dynamic contextualised word embeddings  
13/10/21 Jodie MirrorWiC: On Eliciting Word-in-Context Representations from Pretrained Language Models  
06/10/21 Micheal AUTOPROMPT: Eliciting Knowledge from Language Models with Automatically Generated Prompts  
29/09/21 James Does knowledge distillation really work?  
22/09/21 Huda ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation Learning  
13/09/21 Angrosh Dependency-driven RE with Attentive Graph Convolutional Networks  
08/09/21 Danushka Is sparse attention interpretable  
01/09/21 Jodie Sparsity Makes Sense: Word Sense Disambiguation Using Sparse Contextualized Word Representations  
25/08/21 Micheal Prefix-Tuning: Optimizing Continuous Prompts for Generation  
18/08/21 James Lookahead: A far-sighted alternative of magnitude-based pruning  
11/08/21 Huda ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning  
04/08/21 Angrosh VGCN-BERT: Augmenting BERT with Graph Embedding for Text Classification  

Go to the Home Page