MemBERT: Injecting Unstructured Knowledge into BERT

Proceedings of the 11th International Conference on Advanced Intelligent Systems and Informatics, 2025

Transformer-based pre-trained language models are advanced machine learning models that understand and produce human language. These models are mainly based on the "Transformer" design. They have undergone substantial pre-training on large volumes of text data to understand language patterns. Notable examples include BERT, GPT, and RoBERTa. These tools have transformed NLP tasks by demonstrating exceptional performance and adaptability, facilitating knowledge transfer to specialized tasks, and addressing issues associated with training a model from the start. This systematic review examines transformer-based pre-trained language models, including architecture, pretraining techniques, and adaption approaches. This study examines the core concepts, training methods, and applications of these models to answer significant research concerns. This study examines transformer-based pre-trained models in NLP and their fine-tuning methodologies. This review sheds light on the current state of transformer-based language models and outlines potential future advances in this dynamic subject.

Findings of the Association for Computational Linguistics: EMNLP 2021, 2021

Large pre-trained language models such as BERT have been the driving force behind recent improvements across many NLP tasks. However, BERT is only trained to predict missing words-either through masking or next sentence prediction-and has no knowledge of lexical, syntactic or semantic information beyond what it picks up through unsupervised pre-training. We propose a novel method to explicitly inject linguistic information in the form of word embeddings into any layer of a pre-trained BERT. When injecting counter-fitted and dependency-based embeddings, the performance improvements on multiple semantic similarity datasets indicate that such information is beneficial and currently missing from the original model. Our qualitative analysis shows that counter-fitted embedding injection is particularly beneficial, with notable improvements on examples that require synonym resolution.

ArXiv, 2019

We introduce HUBERT which combines the structured-representational power of Tensor-Product Representations (TPRs) and BERT, a pre-trained bidirectional Transformer language model. We show that there is shared structure between different NLP datasets that HUBERT, but not BERT, is able to learn and leverage. We validate the effectiveness of our model on the GLUE benchmark and HANS dataset. Our experiment results show that untangling data-specific semantics from general language structure is key for better transfer among NLP tasks.

arXiv (Cornell University), 2020

Transformers have greatly advanced the state-ofthe-art in Natural Language Processing (NLP) in recent years, but present very large computation and storage requirements. We observe that the design process of Transformers (pre-train a foundation model on a large dataset in a self-supervised manner, and subsequently fine-tune it for different downstream tasks) leads to task-specific models that are highly over-parameterized, adversely impacting both accuracy and inference efficiency. We propose AxFormer, a systematic framework that applies accuracydriven approximations to create optimized transformer models for a given downstream task. AxFormer combines two key optimizations-accuracy-driven pruning and selective hard attention. Accuracy-driven pruning identifies and removes parts of the fine-tuned transformer that hinder performance on the given downstream task. Sparse hard-attention optimizes attention blocks in selected layers by eliminating irrelevant word aggregations, thereby helping the model focus only on the relevant parts of the input. In effect, AxFormer leads to models that are more accurate, while also being faster and smaller. Our experiments on GLUE and SQUAD tasks show that AxFormer models are up to 4.5% more accurate, while also being up to 2.5× faster and up to 3.2× smaller than conventional finetuned models. In addition, we demonstrate that AxFormer can be combined with previous efforts such as distillation or quantization to achieve further efficiency gains.

In the natural language processing literature, neural networks are becoming increasingly deeper and complex. The recent poster child of this trend is the deep language representation model, which includes BERT, ELMo, and GPT. These developments have led to the conviction that previous-generation, shallower neural networks for language understanding are obsolete. In this paper, however, we demonstrate that rudimentary, lightweight neural networks can still be made competitive without architecture changes, external training data, or additional input features. We propose to distill knowledge from BERT, a state-of-the-art language representation model, into a single-layer BiLSTM, as well as its siamese counterpart for sentence-pair tasks. Across multiple datasets in paraphrasing, natural language inference, and sentiment classification, we achieve comparable results with ELMo, while using roughly 100 times fewer parameters and 15 times less inference time.

2022

In this paper, we proposed a novel adjustable fine-tuning method that improves the training and inference time of the BERT model on downstream tasks. In the proposed method, we first detect more important word vectors in each layer by our proposed redundancy metric and then eliminate the less important word vectors with our proposed strategy. In our method, the word vector elimination rate in each layer is controlled by the Tilt-Rate hyper-parameter, and the model learns to work with a considerably lower number of Floating Point Operations (FLOPs) than the original BERT\textsubscript{base} model. Our proposed method does not need any extra training steps, and also it can be generalized to other transformer-based models. We perform extensive experiments that show the word vectors in higher layers have an impressive amount of redundancy that can be eliminated and decrease the training and inference time. Experimental results on extensive sentiment analysis, classification and regressi...

arXiv (Cornell University), 2023

Transformer-based pretrained models like BERT, GPT-2 and T5 have been finetuned for a large number of natural language processing (NLP) tasks, and have been shown to be very effective. However, while finetuning, what changes across layers in these models with respect to pretrained checkpoints is under-studied. Further, how robust are these models to perturbations in input text? Does the robustness vary depending on the NLP task for which the models have been finetuned? While there exists some work on studying the robustness of BERT finetuned for a few NLP tasks, there is no rigorous study that compares this robustness across encoder only, decoder only and encoderdecoder models. In this paper, we characterize changes between pretrained and finetuned language model representations across layers using two metrics: CKA and STIR. Further, we study the robustness of three language models (BERT, GPT-2 and T5) with eight different text perturbations on classification tasks from the General Language Understanding Evaluation (GLUE) benchmark, and generation tasks like summarization, free-form generation and question generation. GPT-2 representations are more robust than BERT and T5 across multiple types of input perturbation. Although models exhibit good robustness broadly, dropping nouns, verbs or changing characters are the most impactful. Overall, this study provides valuable insights into perturbation-specific weaknesses of popular Transformer-based models, which should be kept in mind when passing inputs. We make the code and models publicly available 1 .

arXiv (Cornell University), 2020

There has been significant progress in recent years in the field of Natural Language Processing thanks to the introduction of the Transformer architecture. Current state-of-the-art models, via a large number of parameters and pre-training on massive text corpus, have shown impressive results on several downstream tasks. Many researchers have studied previous (non-Transformer) models to understand their actual behavior under different scenarios, showing that these models are taking advantage of clues or failures of datasets and that slight perturbations on the input data can severely reduce their performance. In contrast, recent models have not been systematically tested with adversarial-examples in order to show their robustness under severe stress conditions. For that reason, this work evaluates three Transformer-based models (RoBERTa, XLNet, and BERT) in Natural Language Inference (NLI) and Question Answering (QA) tasks to know if they are more robust or if they have the same flaws as their predecessors. As a result, our experiments reveal that RoBERTa, XLNet and BERT are more robust than recurrent neural network models to stress tests for both NLI and QA tasks. Nevertheless, they are still very fragile and demonstrate various unexpected behaviors, thus revealing that there is still room for future improvement in this field.

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models (Peters et al., 2018a; Rad-ford et al., 2018), BERT is designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result , the pre-trained BERT model can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications. BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural language processing tasks, including pushing the GLUE score to 80.5% (7.7% point absolute improvement), MultiNLI accuracy to 86.7% (4.6% absolute improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point absolute improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point absolute improvement).

Cornell University - arXiv, 2022

This paper describes the models developed by the AILAB-Udine team for the SMM4H'22 Shared Task. We explored the limits of Transformer based models on text classification, entity extraction and entity normalization, tackling Tasks 1, 2, 5, 6 and 10. The main takeaways we got from participating in different tasks are: the overwhelming positive effects of combining different architectures when using ensemble learning, and the great potential of generative models for term normalization.

2020

One of the challenges in the NLP field is training large classification models, a task that is both difficult and tedious. It is even harder when GPU hardware is unavailable. The increased availability of pre-trained and off-the-shelf word embeddings, models, and modules aim at easing the process of training large models and achieving a competitive performance. We explore the use of off-the-shelf BERT models and share the results of our experiments and compare their results to those of LSTM networks and more simple baselines. We show that the complexity and computational cost of BERT is not a guarantee for enhanced predic-tive performance in the classification tasks at hand.

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020

Transformer models have advanced the state of the art in many Natural Language Processing (NLP) tasks. In this paper, we present a new Transformer architecture, Extended Transformer Construction (ETC), that addresses two key challenges of standard Transformer architectures, namely scaling input length and encoding structured inputs. To scale attention to longer inputs, we introduce a novel global-local attention mechanism between global tokens and regular input tokens. We also show that combining global-local attention with relative position encodings and a Contrastive Predictive Coding (CPC) pretraining objective allows ETC to encode structured inputs. We achieve state-of-the-art results on four natural language datasets requiring long and/or structured inputs.

Natural language processing (NLP) has witnessed many substantial advancements in the past three years. With the introduction of the Transformer and self-attention mechanism, language models are now able to learn better representations of the natural language. These attention-based models have achieved exceptional state-of-the-art results on various NLP benchmarks. One of the contributing factors is the growing use of transfer learning. Models are pre-trained on unsupervised objectives using rich datasets that develop fundamental natural language abilities that are fine-tuned further on supervised data for downstream tasks. Surprisingly, current researches have led to a novel era of powerful models that no longer require fine-tuning. The objective of this paper is to present a comparative analysis of some of the most influential language models. The benchmarks of the study are problem-solving methodologies, model architecture, compute power, standard NLP benchmark accuracies and shortcomings.

Transactions of the Association for Computational Linguistics, 2020

Transformer-based models have pushed state of the art in many areas of NLP, but our understanding of what is behind their success is still limited. This paper is the first survey of over 150 studies of the popular BERT model. We review the current state of knowledge about how BERT works, what kind of information it learns and how it is represented, common modifications to its training objectives and architecture, the overparameterization issue, and approaches to compression. We then outline directions for future research.

Cornell University - arXiv, 2021

The inception of modeling contextual information using models such as BERT, ELMo, and Flair has significantly improved representation learning for words. It has also given SOTA results in almost every NLP task-Machine Translation, Text Summarization and Named Entity Recognition, to name a few. In this work, in addition to using these dominant context-aware representations, we propose a Knowledge Aware Representation Learning (KARL) Network for Named Entity Recognition (NER). We discuss the challenges of using existing methods in incorporating world knowledge for NER and show how our proposed methods could be leveraged to overcome those challenges. KARL is based on a Transformer Encoder that utilizes large knowledge bases represented as fact triplets, converts them to a graph context, and extracts essential entity information residing inside to generate contextualized triplet representation for feature augmentation. Experimental results show that the augmentation done using KARL can considerably boost the performance of our NER system and achieve significantly better results than existing approaches in the literature on three publicly available NER datasets, namely CoNLL 2003, CoNLL++, and OntoNotes v5. We also observe better generalization and application to a real-world setting from KARL on unseen entities.