Domain Knowledge Transferring for Pre-trained Language Model via Calibrated Activation Boundary Distillation

In this investigation, we propose a solution for the author’s gender identification task called AGI-P. This task has several real-world applications across different fields, such as marketing and advertising, forensic linguistics, sociology, recommendation systems, language processing, historical analysis, education, and language learning. We created a new dataset to evaluate our proposed method. The dataset is balanced in terms of gender using a random sampling method and consists of 1944 samples in total. We use accuracy as an evaluation measure and compare the performance of the proposed solution (AGI-P) against state-of-the-art machine learning classifiers and fine-tuned pre-trained multilingual language models such as DistilBERT, mBERT, XLM-RoBERTa, and Multilingual DEBERTa. In this regard, we also propose a customized fine-tuning strategy that improves the accuracy of the pre-trained language models for the author gender identification task. Our extensive experimental studies reveal that our solution (AGI-P) outperforms the well-known machine learning classifiers and fine-tuned pre-trained multilingual language models with an accuracy level of 92.03%. Moreover, the pre-trained multilingual language models, fine-tuned with the proposed customized strategy, outperform the fine-tuned pre-trained language models using an out-of-the-box fine-tuning strategy. The codebase and the corpus will be publicly available for scholars in this area upon publication.

Pre-trained language models (PLMs) have become a prevalent technique in deep learning for code, utilizing a two-stage pre-training and fine-tuning procedure to acquire general knowledge about code and specialize in a variety of downstream tasks. However, the dynamic nature of software codebases poses a challenge to the effectiveness and robustness of PLMs. In particular, world-realistic scenarios potentially lead to significant differences between the distribution of the pre-training and test data, i.e., distribution shift, resulting in a degradation of the PLM's performance on downstream tasks. In this paper, we stress the need for adapting PLMs of code to software data whose distribution changes over time, a crucial problem that has been overlooked in previous works. The motivation of this work is to consider the PLM in a non-stationary environment, where fine-tuning data evolves over time according to a software evolution scenario. Specifically, we design a scenario where the model needs to learn from a stream of programs containing new, unseen APIs over time. We study two widely used PLM architectures, i.e., a GPT2 decoder and a RoBERTa encoder, on two downstream tasks, API call and API usage prediction. We demonstrate that the most commonly used fine-tuning technique from prior work is not robust enough to handle the dynamic nature of APIs, leading to the loss of previously acquired knowledge i.e., catastrophic forgetting. To address these issues, we implement five continual learning approaches, including replay-based and regularization-based methods. Our findings demonstrate that utilizing these straightforward methods effectively mitigates catastrophic forgetting in PLMs across both downstream tasks while achieving comparable or superior performance.

Korean is the native and official language spoken by Chinese-Korean people, and Weibo is a social media software with a huge number of users in China. Currently, there is few studies related to sentiment analysis of Korean-language Weibo texts posted by Chinese-Korean users. In this paper, we propose a sentiment classification method for Chinese-Korean Weibo based on pre-trained language model and transfer learning. Firstly, we crawled the Chinese-Korean Weibo data from Sina Weibo and label them with sentiment to get the Chinese-Korean Weibo sentiment analysis (CKWSA) dataset. Secondly, to solve the problem of few training samples of the Chinese-Korean Weibo sentiment analysis dataset, we fine-tune the classifier based on the pre-trained Korean language model on the Korean Twitter sentiment analysis dataset to obtain the Korean Twitter sentiment classification model; and further fine-tune the model on CKWSA dataset to get Chinese-Korean Weibo sentiment classification model. The experiments show that the proposed classification method based on pre-trained language model and transfer learning has great performance, and there is an improvement compared other baselines on the Chinese-Korean Weibo sentiment analysis dataset.

Transfer learning with large pretrained transformer-based language models like BERT has become a dominating approach for most NLP tasks. Simply fine-tuning those large language models on downstream tasks or combining it with task-specific pretraining is often not robust. In particular, the performance considerably varies as the random seed changes or the number of pretraining and/or fine-tuning iterations varies, and the fine-tuned model is vulnerable to adversarial attack. We propose a simple yet effective adapter-based approach to mitigate these issues. Specifically, we insert small bottleneck layers (i.e., adapter) within each layer of a pretrained model, then fix the pretrained layers and train the adapter layers on the downstream task data, with (1) task-specific unsupervised pretraining and then (2) task-specific supervised training (e.g., classification, sequence labeling). Our experiments demonstrate that such a training scheme leads to improved stability and adversarial robustness in transfer learning to various downstream tasks.

Demographic biases and social stereotypes are common in pretrained language models (PLMs), and a burgeoning body of literature focuses on removing the unwanted stereotypical associations from PLMs. However, when fine-tuning these bias-mitigated PLMs in downstream natural language processing (NLP) applications, such as sentiment classification, the unwanted stereotypical associations resurface or even get amplified. Since pretrain&fine-tune is a major paradigm in NLP applications, separating the debiasing procedure of PLMs from fine-tuning would eventually harm the actual downstream utility. In this paper, we propose a unified debiasing framework Causal-Debias to remove unwanted stereotypical associations in PLMs during fine-tuning. Specifically, Causal-Debias mitigates bias from a causal invariant perspective by leveraging the specific downstream task to identify bias-relevant and label-relevant factors. We propose that bias-relevant factors are non-causal as they should have little impact on downstream tasks, while label-relevant factors are causal. We perform interventions on non-causal factors in different demographic groups and design an invariant risk minimization loss to mitigate bias while maintaining task performance. Experimental results on three downstream tasks show that our proposed method can remarkably reduce unwanted stereotypical associations after PLMs are fine-tuned, while simultaneously minimizing the impact on PLMs and downstream applications. © 2023 Association for Computational Linguistics.

Pre-trained language models with structured semantic knowledge have demonstrated remarkable performance in a variety of downstream natural language processing tasks. The typical methods of integrating knowledge are designing different pre-training tasks and training from scratch, which requires high-end hardware, massive storage resources, and long computing times. Prompt learning is an effective approach to tuning language models for specific tasks, and it can also be used to infuse knowledge. However, most prompt learning methods accept one token as the answer, instead of multiple tokens. To tackle this problem, we propose the long-answer prompt learning method (KLAPrompt), with three different long-answer strategies, to incorporate semantic knowledge into pre-trained language models, and we compare the performance of these three strategies through experiments. We also explore the effectiveness of the KLAPrompt method in the medical field. Additionally, we generate a word sense prediction dataset (WSP) based on the Xinhua Dictionary and a disease and category prediction dataset (DCP) based on MedicalKG. Experimental results show that discrete answers with the answer space partitioning strategy achieve the best results, and introducing structured semantic information can consistently improve language modeling and downstream tasks.

This paper describes the models designated for the MEDIQA 2019 shared tasks by the team PANLP. We take advantages of the recent advances in pre-trained bidirectional transformer language models such as BERT (Devlin et al., 2018) and MT-DNN (Liu et al., 2019b). We find that pre-trained language models can significantly outperform traditional deep learning models. Transfer learning from the NLI task to the RQE task is also experimented, which proves to be useful in improving the results of fine-tuning MT-DNN large. A knowledge distillation process is implemented, to distill the knowledge contained in a set of models and transfer it into an single model, whose performance turns out to be comparable with that obtained by the ensemble of that set of models. Finally, for test submissions, model ensemble and a re-ranking process are implemented to boost the performances. Our models participated in all three tasks and ranked the 1st place for the RQE task, and the 2nd place for the NLI task, and also the 2nd place for the QA task.

Biomedical text summarization is a critical task for comprehension of an ever-growing amount of biomedical literature. Pre-trained language models (PLMs) with transformer-based architectures have been shown to greatly improve performance in biomedical text mining tasks. However, existing methods for text summarization generally fine-tune PLMs on the target corpora directly and do not consider how fine-grained domain knowledge, such as PICO elements used in evidence-based medicine, can help to identify the context needed for generating coherent summaries. To fill the gap, we propose KeBioSum, a novel knowledge infusion training framework, and experiment using a number of PLMs as bases, for the task of extractive summarization on biomedical literature. We investigate generative and discriminative training techniques to fuse domain knowledge (i.e., PICO elements) into knowledge adapters and apply adapter fusion to efficiently inject the knowledge adapters into the basic PLMs for fine-tuning the extractive summarization task. Experimental results from the extractive summarization task on three biomedical literature datasets show that existing PLMs (BERT, RoBERTa, BioBERT, and PubMedBERT) are improved by incorporating the KeBioSum knowledge adapters, and our model outperforms the strong baselines.

Recently, pre-trained language models (PTM) have achieved great success on ad hoc search. However, the performance decline in low-resource scenarios demonstrates the capability of PTM has not been inspired fully. As a novel paradigm to apply PTM to downstream tasks, prompt learning is a feasible scheme to boost PTM’s performance by aligning the pre-training task and downstream task. This paper investigates the effectiveness of the standard prompt learning paradigm on the ad hoc search task. Based on various PTMs, two types of prompts are tailored for the ad hoc search task. Overall experimental results on the MS Marco dataset show the credible better performance of our prompt learning method than fine-tuning based methods and another previous prompt learning based model. Experiments conducted in various resource scenarios show the stability of prompt learning. RoBERTa and T5 deliver better results compared to BM25 using 100 training queries utilizing prompt learning, while fine-tuning based methods need more data. Further analysis shows the significance of the uniformity of tasks’ format and adding continuous tokens into training in our prompt learning method.KeywordsAd hoc searchPrompt learningPre-trained language model

Pre-trained language models (PLMs) achieve great success in NLP. However, their huge model sizes hinder their applications in many practical systems. Knowledge distillation is a popular technique to compress PLMs, which learns a small student model from a large teacher PLM. However, the knowledge learned from a single teacher may be limited and even biased, resulting in low-quality student model. In this paper, we propose a multi-teacher knowledge distillation framework named MT-BERT for pre-trained language model compression, which can train high-quality student model from multiple teacher PLMs. In MT-BERT we design a multi-teacher co-finetuning method to jointly finetune multiple teacher PLMs in downstream tasks with shared pooling and prediction layers to align their output space for better collaborative teaching. In addition, we propose a multi-teacher hidden loss and a multi-teacher distillation loss to transfer the useful knowledge in both hidden states and soft labels from multiple teacher PLMs to the student model. Experiments on three benchmark datasets validate the effectiveness of MT-BERT in compressing PLMs.

PurposeSafety management plays an important part in coal mine construction. Due to complex data, the implementation of the construction safety knowledge scattered in standards poses a challenge. This paper aims to develop a knowledge extraction model to automatically and efficiently extract domain knowledge from unstructured texts.Design/methodology/approachBidirectional encoder representations from transformers (BERT)-bidirectional long short-term memory (BiLSTM)-conditional random field (CRF) method based on a pre-training language model was applied to carry out knowledge entity recognition in the field of coal mine construction safety in this paper. Firstly, 80 safety standards for coal mine construction were collected, sorted out and marked as a descriptive corpus. Then, the BERT pre-training language model was used to obtain dynamic word vectors. Finally, the BiLSTM-CRF model concluded the entity’s optimal tag sequence.FindingsAccordingly, 11,933 entities and 2,051 relationships in the standard specifications texts of this paper were identified and a language model suitable for coal mine construction safety management was proposed. The experiments showed that F1 values were all above 60% in nine types of entities such as security management. F1 value of this model was more than 60% for entity extraction. The model identified and extracted entities more accurately than conventional methods.Originality/valueThis work completed the domain knowledge query and built a Q&A platform via entities and relationships identified by the standard specifications suitable for coal mines. This paper proposed a systematic framework for texts in coal mine construction safety to improve efficiency and accuracy of domain-specific entity extraction. In addition, the pretraining language model was also introduced into the coal mine construction safety to realize dynamic entity recognition, which provides technical support and theoretical reference for the optimization of safety management platforms.

JointMatcher: Numerically-aware entity matching using pre-trained language models with attention concentration

Continuous professional development of science teachers is closely related to their ability to reflect on their science lessons. For teachers to effectively reflect on their lesson, they need opportunities to make meaningful teaching-related experiences and receive guiding feedback for their reflections during initial teacher education. A sensible means to provide reflection opportunities for teachers is through written reflection assignments. However, assessing written reflections is conceptually challenging and resource-intensive. Recent developments suggest that artificial intelligence (AI) might provide novel opportunities for science teacher education and assessing written reflections. Consequently, we investigate ways in which AI in the form of a large language model can be utilized in a specific science teacher training program. The potential of AI for the use in higher education have been highlighted in recent years. However, it is noted that large language models oftentimes are too generic to be useful in specific science teacher education contexts. To address this issue, we used a pre-trained large language model and fine-tuned it to provide individualized feedback for pre-service physics teachers’ written reflection and investigated to which degree contextual factors impact the classification accuracy. Our results show that the pre-trained language model allowed a sufficient classification and that the classification accuracy can be improved by context specification. Our study highlights opportunities and challenges when utilizing AI, in particular large language models, for reflective writing analytics in science education.

Simile interpretation is a crucial task in natural language processing. Nowadays, pre-trained language models (PLMs) have achieved state-of-the-art performance on many tasks. However, it remains under-explored whether PLMs can interpret similes or not. In this paper, we investigate the ability of PLMs in simile interpretation by designing a novel task named Simile Property Probing, i.e., to let the PLMs infer the shared properties of similes. We construct our simile property probing datasets from both general textual corpora and human-designed questions, containing 1,633 examples covering seven main categories. Our empirical study based on the constructed datasets shows that PLMs can infer similes’ shared properties while still underperforming humans. To bridge the gap with human performance, we additionally design a knowledge-enhanced training objective by incorporating the simile knowledge into PLMs via knowledge embedding methods. Our method results in a gain of 8.58% in the probing task and 1.37% in the downstream task of sentiment classification.

With the success of down streaming task using English pre-trained language model, the pre-trained Chinese language model is also necessary to get better performance of Chinese NLP tasks. Unlike the English language, Chinese has its special characters such as glyph information. So in this article, we propose the Chinese pre-trained language model named StyleBERT which incorporate the following embedding information to enhance the savvy of language model, such as word, pinyin, five stroke and chaizi. The experiments show that the model achieves well performances on a wide range of Chinese NLP tasks.