Fine-tuning BERT for Low-Resource Natural Language Understanding via Active Learning
Institute for Applied Artificial Intelligence (IAAI)（应用人工智能研究所（IAAI））；Hochschule der Medien Stuttgart（斯图加特媒体大学）；Institute for Natural Language Processing (IMS)（自然语言处理研究所（IMS））；University of Stuttgart（斯图加特大学）
Daniel Grießhaber, Johannes Maucher, Ngoc Thang Vu
Recently, leveraging pre-trained Transformer based language models in down stream, task specific models has advanced state of the art results in natural language understanding tasks. However, only a little research has explored the suitability of this approach in low resource settings with less than 1,000 training data points. In this work, we explore fine-tuning methods of BERT -- a pre-trained Transformer based language model -- by utilizing pool-based active learning to speed up training while keeping the cost of labeling new data constant. Our experimental results on the GLUE data set show an advantage in model performance by maximizing the approximate knowledge gain of the model when querying from the pool of unlabeled data. Finally, we demonstrate and analyze the benefits of freezing layers of the language model during fine-tuning to reduce the number of trainable parameters, making it more suitable for low-resource settings.
RoZetta Technology（罗泽塔科技）；University of Technology Sydney（悉尼科技大学）
Neural machine translation models are often biased toward the limited translation references seen during training. To amend this form of overfitting, in this paper we propose fine-tuning the models with a novel training objective based on the recently-proposed BERTScore evaluation metric. BERTScore is a scoring function based on contextual embeddings that overcomes the typical limitations of n-gram-based metrics (e.g. synonyms, paraphrases), allowing translations that are different from the references, yet close in the contextual embedding space, to be treated as substantially correct. To be a…
Université de Montréal（蒙特利尔大学）；School of Information, Renmin University of China（中国人民大学信息学院）；Mila - Québec Artificial Intelligence Institute（米拉-魁北克人工智能研究所）
Sentence ordering aims to arrange the sentences of a given text in the correct order. Recent work frames it as a ranking problem and applies deep neural networks to it. In this work, we propose a new method, named BERT4SO, by fine-tuning BERT for sentence ordering. We concatenate all sentences and compute their representations by using multiple special tokens and carefully designed segment (interval) embeddings. The tokens across multiple sentences can attend to each other which greatly enhances their interactions. We also propose a margin-based listwise ranking loss based on ListMLE to facili…
Department of Computer and Information Science University of Delaware（特拉华大学计算机与信息科学系）；University of Delaware（特拉华大学）；Department of Computer and Information Science（计算机与信息科学系）
With the explosive growth of biomedical literature, designing automatic tools to extract information from the literature has great significance in biomedical research. Recently, transformer-based BERT models adapted to the biomedical domain have produced leading results. However, all the existing BERT models for relation classification only utilize partial knowledge from the last layer. In this paper, we will investigate the method of utilizing the entire layer in the fine-tuning process of BERT model. To the best of our knowledge, we are the first to explore this method. The experimental resu…
While there has been much recent work studying how linguistic information is encoded in pre-trained sentence representations, comparatively little is understood about how these models change when adapted to solve downstream tasks. Using a suite of analysis techniques (probing classifiers, Representational Similarity Analysis, and model ablations), we investigate how fine-tuning affects the representations of the BERT model. We find that while fine-tuning necessarily makes significant changes, it does not lead to catastrophic forgetting of linguistic phenomena. We instead find that fine-tuning …
Although previous research on Aspect-based Sentiment Analysis (ABSA) for Indonesian reviews in hotel domain has been conducted using CNN and XGBoost, its model did not generalize well in test data and high number of OOV words contributed to misclassification cases. Nowadays, most state-of-the-art results for wide array of NLP tasks are achieved by utilizing pretrained language representation. In this paper, we intend to incorporate one of the foremost language representation model, BERT, to perform ABSA in Indonesian reviews dataset. By combining multilingual BERT (m-BERT) with task transforma…
Large pre-trained sentence encoders like BERT start a new chapter in natural language processing. A common practice to apply pre-trained BERT to sequence classification tasks (e.g., classification of sentences or sentence pairs) is by feeding the embedding of [CLS] token (in the last layer) to a task-specific classification layer, and then fine tune the model parameters of BERT and classifier jointly. In this paper, we conduct systematic analysis over several sequence classification datasets to examine the embedding values of [CLS] token before the fine tuning phase, and present the biased emb…
Given the prevalence of pre-trained contextualized representations in today's NLP, there have been many efforts to understand what information they contain, and why they seem to be universally successful. The most common approach to use these representations involves fine-tuning them for an end task. Yet, how fine-tuning changes the underlying embedding space is less studied. In this work, we study the English BERT family and use two probing techniques to analyze how fine-tuning changes the space. We hypothesize that fine-tuning affects classification performance by increasing the distances be…
Université Paris-Saclay（巴黎-萨克雷大学）；CNRS, LIMSI（法国国家科学研究中心，LIMSI实验室）；University of Helsinki（赫尔辛基大学）
We present the MULTISEM systems submitted to SemEval 2020 Task 3: Graded Word Similarity in Context (GWSC). We experiment with injecting semantic knowledge into pre-trained BERT models through fine-tuning on lexical semantic tasks related to GWSC. We use existing semantically annotated datasets and propose to approximate similarity through automatically generated lexical substitutes in context. We participate in both GWSC subtasks and address two languages, English and Finnish. Our best English models occupy the third and fourth positions in the ranking for the two subtasks. Performance is low…
School of Computer Science, Fudan University（复旦大学计算机科学技术学院）；Shanghai Key Laboratory of Intelligent Information Processing, Fudan University（复旦大学上海市智能信息处理重点实验室）
Pre-trained models are widely used in fine-tuning downstream tasks with linear classifiers optimized by the cross-entropy loss, which might face robustness and stability problems. These problems can be improved by learning representations that focus on similarities in the same class and contradictions in different classes when making predictions. In this paper, we utilize the K-Nearest Neighbors Classifier in pre-trained model fine-tuning. For this KNN classifier, we introduce a supervised momentum contrastive learning framework to learn the clustered representations of the supervised downstre…
Moscow Institute of Physics and Technology（莫斯科物理技术学院）；ABBYY；HSE University（俄罗斯国立高等经济学院）
This paper presents our contribution to SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation (MCL-WiC). Our experiments cover English (EN-EN) sub-track from the multilingual setting of the task. We experiment with several pre-trained language models and investigate an impact of different top-layers on fine-tuning. We find the combination of Cosine Similarity and ReLU activation leading to the most effective fine-tuning procedure. Our best model results in accuracy 92.7%, which is the fourth-best score in EN-EN sub-track.
Language model pre-training has proven to be useful in learning universal language representations. As a state-of-the-art language model pre-training model, BERT (Bidirectional Encoder Representations from Transformers) has achieved amazing results in many language understanding tasks. In this paper, we conduct exhaustive experiments to investigate different fine-tuning methods of BERT on text classification task and provide a general solution for BERT fine-tuning. Finally, the proposed solution obtains new state-of-the-art results on eight widely-studied text classification datasets.
Fine-tuning pre-trained language models like BERT has become an effective way in NLP and yields state-of-the-art results on many downstream tasks. Recent studies on adapting BERT to new tasks mainly focus on modifying the model structure, re-designing the pre-train tasks, and leveraging external data and knowledge. The fine-tuning strategy itself has yet to be fully explored. In this paper, we improve the fine-tuning of BERT with two effective mechanisms: self-ensemble and self-distillation. The experiments on text classification and natural language inference tasks show our proposed methods c…
University of Information Technology（信息技术大学）；Vietnam National University, Ho Chi Minh City（胡志明市越南国家大学）
Sentiment analysis is an important task in the field ofNature Language Processing (NLP), in which users' feedbackdata on a specific issue are evaluated and analyzed. Manydeep learning models have been proposed to tackle this task, including the recently-introduced Bidirectional Encoder Rep-resentations from Transformers (BERT) model. In this paper,we experiment with two BERT fine-tuning methods for thesentiment analysis task on datasets of Vietnamese reviews: 1) a method that uses only the [CLS] token as the input for anattached feed-forward neural network, and 2) another methodin which all BE…
The explosion in novel NLP word embedding and deep learning techniques has induced significant endeavors into potential applications. One of these directions is in the financial sector. Although there is a lot of work done in state-of-the-art models like GPT and BERT, there are relatively few works on how well these methods perform through fine-tuning after being pre-trained, as well as info on how sensitive their parameters are. We investigate the performance and sensitivity of transferred neural architectures from pre-trained GPT-2 and BERT models. We test the fine-tuning performance based o…
Tsinghua University（清华大学）；Alibaba Group（阿里巴巴集团）；Alberta Machine Intelligence Institute（阿尔伯塔机器智能研究所）；University of Alberta（阿尔伯塔大学）
Despite of the superb performance on a wide range of tasks, pre-trained language models (e.g., BERT) have been proved vulnerable to adversarial texts. In this paper, we present RoChBERT, a framework to build more Robust BERT-based models by utilizing a more comprehensive adversarial graph to fuse Chinese phonetic and glyph features into pre-trained representations during fine-tuning. Inspired by curriculum learning, we further propose to augment the training dataset with adversarial texts in combination with intermediate samples. Extensive experiments demonstrate that RoChBERT outperforms prev…
Department of Electrical and Electronics Engineering（电气与电子工程系）
Fine-tuning a pretrained BERT model is the state of the art method for extractive/abstractive text summarization, in this paper we showcase how this fine-tuning method can be applied to the Arabic language to both construct the first documented model for abstractive Arabic text summarization and show its performance in Arabic extractive summarization. Our model works with multilingual BERT (as Arabic language does not have a pretrained BERT of its own). We show its performance in English corpus first before applying it to Arabic corpora in both extractive and abstractive tasks.
The problem of online offensive language limits the health and security of online users. It is essential to apply the latest state-of-the-art techniques in developing a system to detect online offensive language and to ensure social justice to the online communities. Our study investigates the effects of fine-tuning across several Arabic offensive language datasets. We develop multiple classifiers that use four datasets individually and in combination in order to gain knowledge about online Arabic offensive content and classify users comments accordingly. Our results demonstrate the limited ef…
Boston Children’s Hospital（波士顿儿童医院）；Harvard Medical School（哈佛医学院）
Large scale contextual representation models, such as BERT, have significantly advanced natural language processing (NLP) in recently years. However, in certain area like healthcare, accessing diverse large scale text data from multiple institutions is extremely challenging due to privacy and regulatory reasons. In this article, we show that it is possible to both pretrain and fine tune BERT models in a federated manner using clinical texts from different silos without moving the data.
University of Rochester（罗切斯特大学）；Baidu Research（百度研究院）；University of Macau（澳门大学）
Fine-tuning pre-trained language models such as BERT has become a common practice dominating leaderboards across various NLP tasks. Despite its recent success and wide adoption, this process is unstable when there are only a small number of training samples available. The brittleness of this process is often reflected by the sensitivity to random seeds. In this paper, we propose to tackle this problem based on the noise stability property of deep nets, which is investigated in recent literature (Arora et al., 2018; Sanyal et al., 2020). Specifically, we introduce a novel and effective regulari…
Models based on BERT have been extremely successful in solving a variety of natural language processing (NLP) tasks. Unfortunately, many of these large models require a great deal of computational resources and/or time for pre-training and fine-tuning which limits wider adoptability. While self-attention layers have been well-studied, a strong justification for inclusion of the intermediate layers which follow them remains missing in the literature. In this work, we show that reducing the number of intermediate layers in BERT-Base results in minimal fine-tuning accuracy loss of downstream task…
Inria（法国国家信息与自动化研究所）；Sorbonne Université（索邦大学）；Bar Ilan University（巴伊兰大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Multilingual pretrained language models have demonstrated remarkable zero-shot cross-lingual transfer capabilities. Such transfer emerges by fine-tuning on a task of interest in one language and evaluating on a distinct language, not seen during the fine-tuning. Despite promising results, we still lack a proper understanding of the source of this transfer. Using a novel layer ablation technique and analyses of the model's internal representations, we show that multilingual BERT, a popular multilingual language model, can be viewed as the stacking of two sub-networks: a multilingual encoder fol…
East China University of Science and Technology（华东理工大学）；Shanghai Hospital Development Center（上海医院发展中心）
Entity and relation extraction is the necessary step in structuring medical text. However, the feature extraction ability of the bidirectional long short term memory network in the existing model does not achieve the best effect. At the same time, the language model has achieved excellent results in more and more natural language processing tasks. In this paper, we present a focused attention model for the joint entity and relation extraction task. Our model integrates well-known BERT language model into joint learning through dynamic range attention mechanism, thus improving the feature repre…
DB-BERT is a database tuning tool that exploits information gained via natural language analysis of manuals and other relevant text documents. It uses text to identify database system parameters to tune as well as recommended parameter values. DB-BERT applies large, pre-trained language models (specifically, the BERT model) for text analysis. During an initial training phase, it fine-tunes model weights in order to translate natural language hints into recommended settings. At run time, DB-BERT learns to aggregate, adapt, and prioritize hints to achieve optimal performance for a specific datab…
Athens University of Economics and Business（雅典经济与商业大学）；NCSR “Demokritos”（德谟克利特国家科学研究中心）；University of Sheffield（谢菲尔德大学）
BERT has achieved impressive performance in several NLP tasks. However, there has been limited investigation on its adaptation guidelines in specialised domains. Here we focus on the legal domain, where we explore several approaches for applying BERT models to downstream legal tasks, evaluating on multiple datasets. Our findings indicate that the previous guidelines for pre-training and fine-tuning, often blindly followed, do not always generalize well in the legal domain. Thus we propose a systematic investigation of the available strategies when applying BERT in specialised domains. These ar…
ASAPP Inc.（ASAPP公司）；Stanford University（斯坦福大学）；Penn State University（宾夕法尼亚州立大学）；Cornell University（康奈尔大学）
This paper is a study of fine-tuning of BERT contextual representations, with focus on commonly observed instabilities in few-sample scenarios. We identify several factors that cause this instability: the common use of a non-standard optimization method with biased gradient estimation; the limited applicability of significant parts of the BERT network for down-stream tasks; and the prevalent practice of using a pre-determined, and small number of training iterations. We empirically test the impact of these factors, and identify alternative practices that resolve the commonly observed instabili…
Language model pre-training, such as BERT, has achieved remarkable results in many NLP tasks. However, it is unclear why the pre-training-then-fine-tuning paradigm can improve performance and generalization capability across different tasks. In this paper, we propose to visualize loss landscapes and optimization trajectories of fine-tuning BERT on specific datasets. First, we find that pre-training reaches a good initial point across downstream tasks, which leads to wider optima and easier optimization compared with training from scratch. We also demonstrate that the fine-tuning procedure is r…
School of Intelligence Science and Technology, Peking University（北京大学智能科学与技术学院）；Xiaomi AI Lab（小米人工智能实验室）；School of Psychological and Cognitive Sciences and Beijing Key Laboratory of Behavior and Mental Health, Peking University（北京大学心理与认知科学学院及行为与心理健康北京市重点实验室）
Previous works on emotion recognition in conversation (ERC) follow a two-step paradigm, which can be summarized as first producing context-independent features via fine-tuning pretrained language models (PLMs) and then analyzing contextual information and dialogue structure information among the extracted features. However, we discover that this paradigm has several limitations. Accordingly, we propose a novel paradigm, i.e., exploring contextual information and dialogue structure information in the fine-tuning step, and adapting the PLM to the ERC task in terms of input text, classification s…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research（微软研究院）；Sun Yat-sen University（中山大学）；Peking University（北京大学）
The recently proposed BERT has shown great power on a variety of natural language understanding tasks, such as text classification, reading comprehension, etc. However, how to effectively apply BERT to neural machine translation (NMT) lacks enough exploration. While BERT is more commonly used as fine-tuning instead of contextual embedding for downstream language understanding tasks, in NMT, our preliminary exploration of using BERT as contextual embedding is better than using for fine-tuning. This motivates us to think how to better leverage BERT for NMT along this direction. We propose a new …
Recently, a simple combination of passage retrieval using off-the-shelf IR techniques and a BERT reader was found to be very effective for question answering directly on Wikipedia, yielding a large improvement over the previous state of the art on a standard benchmark dataset. In this paper, we present a data augmentation technique using distant supervision that exploits positive as well as negative examples. We apply a stage-wise approach to fine tuning BERT on multiple datasets, starting with data that is "furthest" from the test data and ending with the "closest". Experimental results show …
Resource-constrained devices are increasingly the deployment targets of machine learning applications. Static models, however, do not always suffice for dynamic environments. On-device training of models allows for quick adaptability to new scenarios. With the increasing size of deep neural networks, as noted with the likes of BERT and other natural language processing models, comes increased resource requirements, namely memory, computation, energy, and time. Furthermore, training is far more resource intensive than inference. Resource-constrained on-device learning is thus doubly difficult, …
Institut Supérieur d’Electronique de Paris（巴黎高等电子学院）；Université de Reims Champagne Ardenne（兰斯大学）
In the era of digitization, different actors in agriculture produce numerous data. Such data contains already latent historical knowledge in the domain. This knowledge enables us to precisely study natural hazards within global or local aspects, and then improve the risk prevention tasks and augment the yield, which helps to tackle the challenge of growing population and changing alimentary habits. In particular, French Plants Health Bulletins (BSV, for its name in French Bulletin de Sant{é} du V{é}g{é}tal) give information about the development stages of phytosanitary risks in agricultural pr…
Owing to the phenomenal success of BERT on various NLP tasks and benchmark datasets, industry practitioners are actively experimenting with fine-tuning BERT to build NLP applications for solving industry use cases. For most datasets that are used by practitioners to build industrial NLP applications, it is hard to guarantee absence of any noise in the data. While BERT has performed exceedingly well for transferring the learnings from one use case to another, it remains unclear how BERT performs when fine-tuned on noisy text. In this work, we explore the sensitivity of BERT to noise in the data…
Pompeu Fabra University（庞培法布拉大学）；Amazon AI（亚马逊人工智能）；Catalan Institute for Research and Advanced Studies (ICREA)（加泰罗尼亚研究与高级研究院（ICREA））
The adaptation of pretrained language models to solve supervised tasks has become a baseline in NLP, and many recent works have focused on studying how linguistic information is encoded in the pretrained sentence representations. Among other information, it has been shown that entire syntax trees are implicitly embedded in the geometry of such models. As these models are often fine-tuned, it becomes increasingly important to understand how the encoded knowledge evolves along the fine-tuning. In this paper, we analyze the evolution of the embedded syntax trees along the fine-tuning process of B…
In this work we focus on fine-tuning a pre-trained BERT model and applying it to patent classification. When applied to large datasets of over two millions patents, our approach outperforms the state of the art by an approach using CNN with word embeddings. In addition, we focus on patent claims without other parts in patent documents. Our contributions include: (1) a new state-of-the-art method based on pre-trained BERT model and fine-tuning for patent classification, (2) a large dataset USPTO-3M at the CPC subclass level with SQL statements that can be used by future researchers, (3) showing…
Osaka University（大阪大学）；University of Manchester（曼彻斯特大学）
A semantic equivalence assessment is defined as a task that assesses semantic equivalence in a sentence pair by binary judgment (i.e., paraphrase identification) or grading (i.e., semantic textual similarity measurement). It constitutes a set of tasks crucial for research on natural language understanding. Recently, BERT realized a breakthrough in sentence representation learning (Devlin et al., 2019), which is broadly transferable to various NLP tasks. While BERT's performance improves by increasing its model size, the required computational power is an obstacle preventing practical applicati…
Nagoya University（名古屋大学）；Academia Sinica（中央研究院）；National Taiwan University of Science and Technology（台湾科技大学）
We propose a simple method for automatic speech recognition (ASR) by fine-tuning BERT, which is a language model (LM) trained on large-scale unlabeled text data and can generate rich contextual representations. Our assumption is that given a history context sequence, a powerful LM can narrow the range of possible choices and the speech signal can be used as a simple clue. Hence, comparing to conventional ASR systems that train a powerful acoustic model (AM) from scratch, we believe that speech recognition is possible by simply fine-tuning a BERT model. As an initial study, we demonstrate the e…
University of Science and Technology of China（中国科学技术大学）
We present our work on Track 4 in the Dialogue System Technology Challenges 8 (DSTC8). The DSTC8-Track 4 aims to perform dialogue state tracking (DST) under the zero-shot settings, in which the model needs to generalize on unseen service APIs given a schema definition of these target APIs. Serving as the core for many virtual assistants such as Siri, Alexa, and Google Assistant, the DST keeps track of the user's goal and what happened in the dialogue history, mainly including intent prediction, slot filling, and user state tracking, which tests models' ability of natural language understanding…
Peking University（北京大学）；University of Technology Sydney（悉尼科技大学）
Pre-trained models have brought significant improvements to many NLP tasks and have been extensively analyzed. But little is known about the effect of fine-tuning on specific tasks. Intuitively, people may agree that a pre-trained model already learns semantic representations of words (e.g. synonyms are closer to each other) and fine-tuning further improves its capabilities which require more complicated reasoning (e.g. coreference resolution, entity boundary detection, etc). However, how to verify these arguments analytically and quantitatively is a challenging task and there are few works fo…
Fine-tuning pre-trained language models (PTLMs), such as BERT and its better variant RoBERTa, has been a common practice for advancing performance in natural language understanding (NLU) tasks. Recent advance in representation learning shows that isotropic (i.e., unit-variance and uncorrelated) embeddings can significantly improve performance on downstream tasks with faster convergence and better generalization. The isotropy of the pre-trained embeddings in PTLMs, however, is relatively under-explored. In this paper, we analyze the isotropy of the pre-trained [CLS] embeddings of PTLMs with str…
Deep Learning for Medical Text Processing: BERT Model Fine-Tuning and Comparative Study
Tulane University（杜兰大学）；Northeastern University（东北大学）；San Francisco State University（旧金山州立大学）；Brandeis University（布兰迪斯大学）；University of California, Los Angeles（加州大学洛杉矶分校）；Johns Hopkins University（约翰斯·霍普金斯大学）
HLTCOE, Johns Hopkins University（约翰斯·霍普金斯大学人类语言技术卓越中心）；University of Glasgow（格拉斯哥大学）；Reveal-Brainspace（Reveal-Brainspace 公司）；IRLab, Georgetown University（乔治城大学信息检索实验室）
Technology-assisted review (TAR) refers to iterative active learning workflows for document review in high recall retrieval (HRR) tasks. TAR research and most commercial TAR software have applied linear models such as logistic regression to lexical features. Transformer-based models with supervised tuning are known to improve effectiveness on many text classification tasks, suggesting their use in TAR. We indeed find that the pre-trained BERT model reduces review cost by 10% to 15% in TAR workflows simulated on the RCV1-v2 newswire collection. In contrast, we likewise determined that linear mo…
University of Malta（马耳他大学）；Idiap Research Institute（伊迪亚普研究所）；Utrecht University（乌得勒支大学）
Recent work has shown evidence that the knowledge acquired by multilingual BERT (mBERT) has two components: a language-specific and a language-neutral one. This paper analyses the relationship between them, in the context of fine-tuning on two tasks -- POS tagging and natural language inference -- which require the model to bring to bear different degrees of language-specific knowledge. Visualisations reveal that mBERT loses the ability to cluster representations by language after fine-tuning, a result that is supported by evidence from language identification experiments. However, further exp…
Adversarial training (AT) is one of the most reliable methods for defending against adversarial attacks in machine learning. Variants of this method have been used as regularization mechanisms to achieve SOTA results on NLP benchmarks, and they have been found to be useful for transfer learning and continual learning. We search for the reasons for the effectiveness of AT by contrasting vanilla and adversarially fine-tuned BERT models. We identify partial preservation of BERT's syntactic abilities during fine-tuning as the key to the success of AT. We observe that adversarially fine-tuned model…
