Papers by Navid Rekabsaz
MultiHumES: Multilingual Humanitarian Dataset for Extractive Summarization (2021.eacl-main)
Copied to clipboard
| Challenge: | a new multilingual summarization model is being developed to help humanitarian experts process large amounts of secondary data to derive situational awareness and guide decision-making. |
| Approach: | They propose to use multilingual documents and annotated snippets to improve extraction of secondary data for humanitarian response experts. |
| Outcome: | The proposed model provides multilingual documents with informative snippets that have been annotated by humanitarian analysts over the past four years. |
Parameter-efficient Modularised Bias Mitigation via AdapterFusion (2023.eacl-main)
Copied to clipboard
Deepak Kumar, Oleg Lesota, George Zerveas, Daniel Cohen, Carsten Eickhoff, Markus Schedl, Navid Rekabsaz
| Challenge: | Large pre-trained language models contain societal biases and carry along these biase . Current approaches to mitigate these bias impose debiasing by updating model parameters, effectively transferring model to irreversible debiased state. |
| Approach: | They propose to develop stand-alone debiasing functionalities separate from the model, which can be integrated into the model on-demand while keeping the core model untouched. |
| Outcome: | The proposed approach improves or maintains effectiveness of bias mitigation, avoids catastrophic forgetting in a multi-attribute scenario, and maintains on-par task performance while granting parameter-efficiency and easy switching between the original and debiased models. |
CODER: An efficient framework for improving retrieval through COntextual Document Embedding Reranking (2022.emnlp-main)
Copied to clipboard
| Challenge: | Contextual document embedding reranking is an efficient and efficient retrieval framework. |
| Approach: | They propose a highly efficient retrieval framework that uses contextual document embedding reranking to incorporate ranking context into training. |
| Outcome: | The proposed framework reduces the computational overhead of a first-stage method and can be used as stand-alone retrieval models. |
Effective Controllable Bias Mitigation for Classification and Retrieval using Gate Adapters (2024.eacl-long)
Copied to clipboard
| Challenge: | a recent study focused on learning separate modules for on-demand debiasing. |
| Approach: | They propose a modular debiasing module with a controllable gate adapter . they demonstrate that the module can reduce the bias of search results . |
| Outcome: | The proposed module can reduce biases on three classification tasks with four protected attributes while maintaining higher task performance. |
Unlabeled Debiasing in Downstream Tasks via Class-wise Low Variance Regularization (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for debiasing depend on attribute labels and target attributes. |
| Approach: | They propose a method that uses class-wise variance of embeddings to reduce the effects of debiasing on a downstream task. |
| Outcome: | The proposed method outperforms baselines that rely on attribute labels while maintaining performance on the target task. |
HumSet: Dataset of Multilingual Information Extraction and Classification for Humanitarian Crises Response (2022.findings-emnlp)
Copied to clipboard
Selim Fekih, Nicolo’ Tamagnone, Benjamin Minixhofer, Ranjan Shrestha, Ximena Contla, Ewan Oglethorpe, Navid Rekabsaz
| Challenge: | During humanitarian crises, a quick and accurate analysis of relevant data is critical to a timely and effective response. |
| Approach: | They introduce and release a multilingual dataset of humanitarian response documents annotated by experts in the humanitarian response domain. |
| Outcome: | The proposed dataset provides documents in three languages and covers a variety of humanitarian crises from 2018 to 2021 across the globe. |
ScaLearn: Simple and Highly Parameter-Efficient Task Transfer by Learning to Scale (2024.findings-acl)
Copied to clipboard
| Challenge: | Multi-task learning (MTL) has shown significant practical benefits when using language models . current two stage MTL introduces a substantial number of additional parameters . |
| Approach: | They propose a multi-task learning method that leverages existing knowledge for a target task. |
| Outcome: | The proposed method outperforms baselines on three benchmarks and two encoder LMs with a small number of transfer parameters. |
WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing methods to train large pretrained language models require more computational resources and are expensive to train in other languages. |
| Approach: | They propose a method to transfer pretrained language models to new languages using subword-based tokenization and embeddings. |
| Outcome: | The proposed method outperforms existing methods on low-resource languages and makes training large models more accessible and less damaging to the environment. |
Batched Self-Consistency Improves LLM Relevance Assessment and Ranking (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing work has focused on a one-by-one pointwise (PW) scoring strategy where each LLM call judges one passage at a time against the query. |
| Approach: | They propose to use batched PW methods to evaluate multiple passages per LLM call to improve efficiency and judgment quality by enabling content from multiple passage to be seen jointly. |
| Outcome: | The proposed methods improve efficiency and judgment quality by enabling content from multiple passages to be seen jointly. |
Modular and On-demand Bias Mitigation with Attribute-Removal Subnetworks (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing studies show that pre-trained language models can be used to mitigate societal biases and stereotypes. |
| Approach: | They propose a modular bias mitigation approach that integrates debiasing modules into the core model on-demand at inference time. |
| Outcome: | The proposed approach improves on-par with baseline finetuning on gender, race, and age protected attributes on three classification tasks with gender, age, and race as protected attributes. |
Enhancing the Ranking Context of Dense Retrieval through Reciprocal Nearest Neighbors (2023.emnlp-main)
Copied to clipboard
| Challenge: | Sparse annotation poses persistent challenges to training dense retrieval models . despite potential future endeavors to extend annotation, issue of false negatives persists . |
| Approach: | They propose a method that smooths out the annotation of unlabeled relevant documents . they use reciprocal nearest neighbors to estimate relevance and rerank candidates . |
| Outcome: | The proposed method reduces the issue of false negatives in contrastive learning by reducing sparsity. |
What the Weight?! A Unified Framework for Zero-Shot Knowledge Composition (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing and new approaches to zero-shot knowledge composition are lacking in NLP. |
| Approach: | They propose a framework for zero-shot module composition that unifies existing and some novel variations for selecting, weighting, and combining parameter modules under a single unified notion. |
| Outcome: | The proposed framework enables a systematic unification of concepts and enables the first comprehensive benchmarking study of various zero-shot knowledge composition strategies. |