Mohammadreza Banaei


2023

pdf bib
Revisiting Offline Compression: Going Beyond Factorization-based Methods for Transformer Language Models
Mohammadreza Banaei | Klaudia Bałazy | Artur Kasymov | Rémi Lebret | Jacek Tabor | Karl Aberer
Findings of the Association for Computational Linguistics: EACL 2023

Recent transformer language models achieve outstanding results in many natural language processing (NLP) tasks. However, their enormous size often makes them impractical on memory-constrained devices, requiring practitioners to compress them to smaller networks. In this paper, we explore offline compression methods, meaning computationally-cheap approaches that do not require further fine-tuning of the compressed model. We challenge the classical matrix factorization methods by proposing a novel, better-performing autoencoder-based framework. We perform a comprehensive ablation study of our approach, examining its different aspects over a diverse set of evaluation settings. Moreover, we show that enabling collaboration between modules across layers by compressing certain modules together positively impacts the final model performance. Experiments on various NLP tasks demonstrate that our approach significantly outperforms commonly used factorization-based offline compression methods.

pdf bib
Breaking the Language Barrier: Improving Cross-Lingual Reasoning with Structured Self-Attention
Negar Foroutan | Mohammadreza Banaei | Karl Aberer | Antoine Bosselut
Findings of the Association for Computational Linguistics: EMNLP 2023

In this work, we study whether multilingual language models (MultiLMs) can transfer logical reasoning abilities to other languages when they are fine-tuned for reasoning in a different language. We evaluate the cross-lingual reasoning abilities of MultiLMs in two schemes: (1) where the language of the context and the question remain the same in the new languages that are tested (i.e., the reasoning is still monolingual, but the model must transfer the learned reasoning ability across languages), and (2) where the language of the context and the question is different (which we term code-switched reasoning). On two logical reasoning datasets, RuleTaker and LeapOfThought, we demonstrate that although MultiLMs can transfer reasoning ability across languages in a monolingual setting, they struggle to transfer reasoning abilities in a code-switched setting. Following this observation, we propose a novel attention mechanism that uses a dedicated set of parameters to encourage cross-lingual attention in code-switched sequences, which improves the reasoning performance by up to 14% and 4% on the RuleTaker and LeapOfThought datasets, respectively.

2022

pdf bib
Discovering Language-neutral Sub-networks in Multilingual Language Models
Negar Foroutan | Mohammadreza Banaei | Rémi Lebret | Antoine Bosselut | Karl Aberer
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Multilingual pre-trained language models transfer remarkably well on cross-lingual downstream tasks. However, the extent to which they learn language-neutral representations (i.e., shared representations that encode similar phenomena across languages), and the effect of such representations on cross-lingual transfer performance, remain open questions. In this work, we conceptualize language neutrality of multilingual models as a function of the overlap between language-encoding sub-networks of these models. We employ the lottery ticket hypothesis to discover sub-networks that are individually optimized for various languages and tasks. Our evaluation across three distinct tasks and eleven typologically-diverse languages demonstrates that sub-networks for different languages are topologically similar (i.e., language-neutral), making them effective initializations for cross-lingual transfer with limited performance degradation.

2021

pdf bib
Direction is what you need: Improving Word Embedding Compression in Large Language Models
Klaudia Bałazy | Mohammadreza Banaei | Rémi Lebret | Jacek Tabor | Karl Aberer
Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)

The adoption of Transformer-based models in natural language processing (NLP) has led to great success using a massive number of parameters. However, due to deployment constraints in edge devices, there has been a rising interest in the compression of these models to improve their inference time and memory footprint. This paper presents a novel loss objective to compress token embeddings in the Transformer-based models by leveraging an AutoEncoder architecture. More specifically, we emphasize the importance of the direction of compressed embeddings with respect to original uncompressed embeddings. The proposed method is task-agnostic and does not require further language modeling pre-training. Our method significantly outperforms the commonly used SVD-based matrix-factorization approach in terms of initial language model Perplexity. Moreover, we evaluate our proposed approach over SQuAD v1.1 dataset and several downstream tasks from the GLUE benchmark, where we also outperform the baseline in most scenarios. Our code is public.