Large Pre-trained Language Models Research Articles

A Comprehensive Survey on Relation Extraction: Recent Advances and New Frontiers

Relation extraction (RE) involves identifying the relations between entities from underlying content. RE serves as the foundation for many natural language processing (NLP) and information retrieval applications, such as knowledge graph completion and question answering. In recent years, deep neural networks have dominated the field of RE and made noticeable progress. Subsequently, the large pre-trained language models (PLMs) have taken the state-of-the-art RE to a new level. This survey provides a comprehensive review of existing deep learning techniques for RE. First, we introduce RE resources, including datasets and evaluation metrics. Second, we propose a new taxonomy to categorize existing works from three perspectives, i.e., text representation, context encoding, and triplet prediction. Third, we discuss several important challenges faced by RE and summarize potential techniques to tackle these challenges. Finally, we outline some promising future directions and prospects in this field. This survey is expected to facilitate researchers’ collaborative efforts to address the challenges of real-world RE systems.

Automatically Recommend Code Updates: Are We There Yet?

In recent years, large pre-trained Language Models of Code (CodeLMs) have shown promising results on various software engineering tasks. One such task is automatic code update recommendation, which transforms outdated code snippets into their approved and revised counterparts. Although many CodeLM-based approaches have been proposed, claiming high accuracy, their effectiveness and reliability on real-world code update tasks remain questionable. In this paper, we present the first extensive evaluation of state-of-the-art CodeLMs for automatically recommending code updates. We assess their performance on two diverse datasets of paired updated methods, considering factors such as temporal evolution, project specificity, method size, and update complexity. Our results reveal that while CodeLMs exhibit higher performance in settings that ignore temporal information, they struggle in more realistic time-wise scenarios and generalize poorly to new projects. Furthermore, CodeLM performance decreases significantly for larger methods and more complex updates. Furthermore, we observe that many CodeLM-generated “updates” are actually null, especially in time-wise settings, and meaningful edits remain challenging. Our findings highlight the significant gap between the perceived and actual effectiveness of CodeLMs for real-world code update recommendation and emphasize the need for more research on improving their practicality, robustness, and generalizability.

TurkishBERTweet: Fast and reliable large language model for social media analysis

Turkish is one of the most spoken languages in the world; however, it is still among the low-resource languages. Wide us of this language on social media platforms such as Twitter, Instagram, or Tiktok and strategic position of the country in the world politics makes it appealing for the social network researchers and industry. To address this need, we introduce TurkishBERTweet, the first large scale pre-trained language model for Turkish social media built using over 894 million Turkish tweets. The model shares the same architecture as RoBERTa-base model with smaller input length, making TurkishBERTweet lighter than the most used model, called BERTurk, and can have significantly lower inference time. We trained our model using the same approach for RoBERTa model and evaluated on two tasks: Sentiment Classification and Hate Speech Detection. We demonstrate that TurkishBERTweet outperforms the other available alternatives on generalizability and its lower inference time gives significant advantage to process large-scale datasets. We also show custom preprocessors for social media can acquire information from platform specific entities. We also conduct comparison with the commercial solutions like OpenAI and Gemini, and other available Turkish LLMs in terms of cost and performance to demonstrate TurkishBERTweet is scalable and cost-effective.

User Engagement Triggers in Social Media Discourse on Biodiversity Conservation

Studies in digital conservation have increasingly used social media in recent years as a source of data to understand the interactions between humans and nature, model and monitor biodiversity, and analyse online discourse about the conservation of species. Current approaches to digital conservation are for the most part purely frequentist, i.e. focused on easily trackable and quantifiable features, or purely qualitative, which allows a deeper level of interpretation, but is less scalable. Our approach aims to evaluate the applicability of recent advances in deep learning in combination with semi-automatic analysis. We present a multimodal neural learning framework that experiments with different combinations of linguistic and visual features and metadata of tweets to predict user engagement from a function of likes and retweets . Experimental results show that text is the single most effective modality for prediction when a large amount of training data is available. For smaller datasets, drawing information from multiple modalities can boost performance. Notably, we find a negative effect of large pre-trained language models when dealing with substantially unbalanced datasets. A qualitative analysis into the triggers of user engagement with tweets reveals that it emerges from a combination of online discourse topic and sentiment, and is often amplified by user activity, e.g. when content originates from an influencer account. We find clear evidence of existing sub-communities around specific topics, including animal photography and sightings , illegal wildlife trade and trophy hunting , deforestation and destruction of nature and climate change and action in a broader sense.

Revealing the Unseen: AI Chain on LLMs for Predicting Implicit Data Flows to Generate Data Flow Graphs in Dynamically-Typed Code

Data flow graphs (DFGs) capture definitions (defs) and uses across program blocks, which is a fundamental program representation for program analysis, testing and maintenance. However, dynamically-typed programming languages like Python present implicit data flow issues that make it challenging to determine def-use flow information at compile time. Static analysis methods like Soot and WALA are inadequate for handling these issues, and manually enumerating comprehensive heuristic rules is impractical. Large pre-trained language models (LLMs) offer a potential solution, as they have powerful language understanding and pattern matching abilities, allowing them to predict implicit data flow by analyzing code context and relationships between variables, functions, and statements in code. We propose leveraging LLMs’ in-context learning ability to learn implicit rules and patterns from code representation and contextual information to solve implicit data flow problems. To further enhance the accuracy of LLMs, we design a five-step Chain of Thought (CoT) and break it down into an AI chain, with each step corresponding to a separate AI unit to generate accurate DFGs for Python code. Our approach’s performance is thoroughly assessed, demonstrating the effectiveness of each AI unit in the AI Chain. Compared to static analysis, our method achieves 82% higher def coverage and 58% higher use coverage in DFG generation on implicit data flow. We also prove the indispensability of each unit in the AI Chain. Overall, our approach offers a promising direction for building software engineering tools by utilizing foundation models, eliminating significant engineering and maintenance effort, but focusing on identifying problems for AI to solve.

End-to-end pseudonymization of fine-tuned clinical BERT models

Many state-of-the-art results in natural language processing (NLP) rely on large pre-trained language models (PLMs). These models consist of large amounts of parameters that are tuned using vast amounts of training data. These factors cause the models to memorize parts of their training data, making them vulnerable to various privacy attacks. This is cause for concern, especially when these models are applied in the clinical domain, where data are very sensitive. Training data pseudonymization is a privacy-preserving technique that aims to mitigate these problems. This technique automatically identifies and replaces sensitive entities with realistic but non-sensitive surrogates. Pseudonymization has yielded promising results in previous studies. However, no previous study has applied pseudonymization to both the pre-training data of PLMs and the fine-tuning data used to solve clinical NLP tasks. This study evaluates the effects on the predictive performance of end-to-end pseudonymization of Swedish clinical BERT models fine-tuned for five clinical NLP tasks. A large number of statistical tests are performed, revealing minimal harm to performance when using pseudonymized fine-tuning data. The results also find no deterioration from end-to-end pseudonymization of pre-training and fine-tuning data. These results demonstrate that pseudonymizing training data to reduce privacy risks can be done without harming data utility for training PLMs.

Zero-Shot Building Age Classification from Facade Image Using GPT-4

Abstract. A building’s age of construction is crucial for supporting many geospatial applications. Much current research focuses on estimating building age from facade images using deep learning. However, building an accurate deep learning model requires a considerable amount of labelled training data, and the trained models often have geographical constraints. Recently, large pre-trained vision language models (VLMs) such as GPT-4 Vision, which demonstrate significant generalisation capabilities, have emerged as potential training-free tools for dealing with specific vision tasks, but their applicability and reliability for building information remain unexplored. In this study, a zero-shot building age classifier for facade images is developed using prompts that include logical instructions. Taking London as a test case, we introduce a new dataset, FI-London, comprising facade images and building age epochs. Although the training-free classifier achieved a modest accuracy of 39.69%, the mean absolute error of 0.85 decades indicates that the model can predict building age epochs successfully albeit with a small bias. The ensuing discussion reveals that the classifier struggles to predict the age of very old buildings and is challenged by fine-grained predictions within 2 decades. Overall, the classifier utilising GPT-4 Vision is capable of predicting the rough age epoch of a building from a single facade image without any training. The code and dataset are available at https://zichaozeng.github.io/ba_classifier.

Optimization techniques for sentiment analysis based on LLM (GPT-3)

With the rapid development of natural language processing (NLP) technology, large-scale pre-trained language models such as GPT-3 have become a popular research object in NLP field. This paper aims to explore sentiment analysis optimization techniques based on large pre-trained language models such as GPT-3 to improve model performance and effect and further promote the development of natural language processing (NLP). By introducing the importance of sentiment analysis and the limitations of traditional methods, GPT-3 and Fine-tuning techniques are introduced in this paper, and their applications in sentiment analysis are explained in detail. The experimental results show that the Fine-tuning technique can optimize GPT-3 model and obtain good performance in sentiment analysis task. This study provides an important reference for future sentiment analysis using large-scale language models.

Language Models in the Loop: Incorporating Prompting into Weak Supervision

We propose a new strategy for applying large pre-trained language models to novel tasks when labeled training data is limited. Rather than apply the model in a typical zero-shot or few-shot fashion, we treat the model as the basis for labeling functions in a weak supervision framework. To create a classifier, we first prompt the model to answer multiple distinct queries about an example and define how the possible responses should be mapped to votes for labels and abstentions. We then denoise these noisy label sources using the Snorkel system and train an end classifier with the resulting training data. Our experimental evaluation shows that prompting large language models within a weak supervision framework can provide significant gains in accuracy. On the WRENCH weak supervision benchmark, this approach can significantly improve over zero-shot performance, an average 19.5% reduction in errors. We also find that this approach produces classifiers with comparable or superior accuracy to those trained from hand-engineered rules.

Depression symptoms modelling from social media text: an LLM driven semi-supervised learning approach

AbstractA fundamental component of user-level social media language based clinical depression modelling is depression symptoms detection (DSD). Unfortunately, there does not exist any DSD dataset that reflects both the clinical insights and the distribution of depression symptoms from the samples of self-disclosed depressed population. In our work, we describe a semi-supervised learning (SSL) framework which uses an initial supervised learning model that leverages (1) a state-of-the-art large mental health forum text pre-trained language model further fine-tuned on a clinician annotated DSD dataset, (2) a Zero-Shot learning model for DSD, and couples them together to harvest depression symptoms related samples from our large self-curated depressive tweets repository (DTR). Our clinician annotated dataset is the largest of its kind. Furthermore, DTR is created from the samples of tweets in self-disclosed depressed users Twitter timeline from two datasets, including one of the largest benchmark datasets for user-level depression detection from Twitter. This further helps preserve the depression symptoms distribution of self-disclosed tweets. Subsequently, we iteratively retrain our initial DSD model with the harvested data. We discuss the stopping criteria and limitations of this SSL process, and elaborate the underlying constructs which play a vital role in the overall SSL process. We show that we can produce a final dataset which is the largest of its kind. Furthermore, a DSD and a Depression Post Detection model trained on it achieves significantly better accuracy than their initial version.

Exploring the Potential of Pre-Trained Language Models of Code for Automated Program Repair

In the realm of software development, automated program repair (APR) emerges as a pivotal technique, autonomously debugging faulty code to boost productivity. Despite the notable advancements of large pre-trained language models of code (PLMCs) in code generation, their efficacy in complex tasks like APR remains suboptimal. This limitation is attributed to the generic development of PLMCs, whose specialized potential for APR is yet be to fully explored. In this paper, we propose a novel approach designed to enhance PLMCs’ APR performance through source code augmentation and curriculum learning. Our approach employs code augmentation operators to generate a spectrum of syntactically varied yet semantically congruent bug-fixing programs, thus enriching the dataset’s diversity. Furthermore, we design a curriculum learning strategy, enabling PLMCs to develop a deep understanding of program semantics from these enriched code variants, thereby refining their APR fine-tuning prowess. We apply our approach across different PLMCs and systematically evaluate it on three benchmarks: BFP-small, BFP-medium, and Defects4J. The experimental results show that our approach outperforms both original models and existing baseline methods, demonstrating the promising future of adapting PLMCs for code debugging in practice.

The Defeat of the Winograd Schema Challenge (Abstract Reprint)

The Winograd Schema Challenge—a set of twin sentences involving pronoun reference disambiguation that seem to require the use of commonsense knowledge—was proposed by Hector Levesque in 2011. By 2019, a number of AI systems, based on large pre-trained transformer-based language models and fine-tuned on these kinds of problems, achieved better than 90% accuracy. In this paper, we review the history of the Winograd Schema Challenge and discuss the lasting contributions of the flurry of research that has taken place on the WSC in the last decade. We discuss the significance of various datasets developed for WSC, and the research community's deeper understanding of the role of surrogate tasks in assessing the intelligence of an AI system.

Liberating Seen Classes: Boosting Few-Shot and Zero-Shot Text Classification via Anchor Generation and Classification Reframing

Few-shot and zero-shot text classification aim to recognize samples from novel classes with limited labeled samples or no labeled samples at all. While prevailing methods have shown promising performance via transferring knowledge from seen classes to unseen classes, they are still limited by (1) Inherent dissimilarities among classes make the transformation of features learned from seen classes to unseen classes both difficult and inefficient. (2) Rare labeled novel samples usually cannot provide enough supervision signals to enable the model to adjust from the source distribution to the target distribution, especially for complicated scenarios. To alleviate the above issues, we propose a simple and effective strategy for few-shot and zero-shot text classification. We aim to liberate the model from the confines of seen classes, thereby enabling it to predict unseen categories without the necessity of training on seen classes. Specifically, for mining more related unseen category knowledge, we utilize a large pre-trained language model to generate pseudo novel samples, and select the most representative ones as category anchors. After that, we convert the multi-class classification task into a binary classification task and use the similarities of query-anchor pairs for prediction to fully leverage the limited supervision signals. Extensive experiments on six widely used public datasets show that our proposed method can outperform other strong baselines significantly in few-shot and zero-shot tasks, even without using any seen class samples.

Let the Laser Beam Connect the Dots: Forecasting and Narrating Stock Market Volatility

Forecasting market volatility, especially high-volatility incidents, is a critical issue in financial market research and practice. Business news as an important source of market information is often exploited by artificial intelligence–based volatility forecasting models. Computationally, deep learning architectures, such as recurrent neural networks, on extremely long input sequences remain infeasible because of time complexity and memory limitations. Meanwhile, understanding the inner workings of deep neural networks is challenging because of the largely black box nature of large neural networks. In this work, we address the first challenge by proposing a long- and short-term memory retrieval (LASER) architecture with flexible memory and horizon configurations to forecast market volatility. Then, we tackle the interpretability issue by devising a BEAM algorithm that leverages a large pretrained language model (GPT-2). It generates human-readable narratives verbalizing the evidence leading to the model prediction. Experiments on a Wall Street Journal news data set demonstrate the superior performance of our proposed LASER-BEAM pipeline in predicting high-volatility market scenarios and generating high-quality narratives compared with existing methods in the literature. History: Accepted by Ram Ramesh, Area Editor for Date Science & Machine Learning. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2022.0055 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2022.0055 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .

Understanding latent affective bias in large pre-trained neural language models

Groundbreaking inventions and highly significant performance improvements in deep learning based Natural Language Processing are witnessed through the development of transformer based large Pre-trained Language Models (PLMs). The wide availability of unlabeled data within human generated data deluge along with self-supervised learning strategy helps to accelerate the success of large PLMs in language generation, language understanding, etc. But at the same time, latent historical bias/unfairness in human minds towards a particular gender, race, etc., encoded unintentionally/intentionally into the corpora harms and questions the utility and efficacy of large PLMs in many real-world applications, particularly for the protected groups. In this paper, we present an extensive investigation towards understanding the existence of “Affective Bias” in large PLMs to unveil any biased association of emotions such as anger, fear, joy, etc., towards a particular gender, race or religion with respect to the downstream task of textual emotion detection. We conduct our exploration of affective bias from the very initial stage of corpus level affective bias analysis by searching for imbalanced distribution of affective words within a domain, in large scale corpora that are used to pre-train and fine-tune PLMs. Later, to quantify affective bias in model predictions, we perform an extensive set of class-based and intensity-based evaluations using various bias evaluation corpora. Our results show the existence of statistically significant affective bias in the PLM based emotion detection systems, indicating biased association of certain emotions towards a particular gender, race, and religion.

CancerGPT for few shot drug pair synergy prediction using large pretrained language models

Large language models (LLMs) have been shown to have significant potential in few-shot learning across various fields, even with minimal training data. However, their ability to generalize to unseen tasks in more complex fields, such as biology and medicine has yet to be fully evaluated. LLMs can offer a promising alternative approach for biological inference, particularly in cases where structured data and sample size are limited, by extracting prior knowledge from text corpora. Here we report our proposed few-shot learning approach, which uses LLMs to predict the synergy of drug pairs in rare tissues that lack structured data and features. Our experiments, which involved seven rare tissues from different cancer types, demonstrate that the LLM-based prediction model achieves significant accuracy with very few or zero samples. Our proposed model, the CancerGPT (with ~ 124M parameters), is comparable to the larger fine-tuned GPT-3 model (with ~ 175B parameters). Our research contributes to tackling drug pair synergy prediction in rare tissues with limited data, and also advancing the use of LLMs for biological and medical inference tasks.

Masked Siamese Prompt Tuning for Few-Shot Natural Language Understanding

Recently, prompt-based learning has shown excellent performance on few-shot scenarios. Using frozen language models to tune trainable continuous prompt embeddings has become a popular and powerful methodology. For few-shot natural language understanding, even if we freeze the parameters of the pre-trained language model, the learned pseudo-prompts might still be overfitted. In this paper, we propose a novel masked siamese prompt tuning (MSP-tuning) to improve few-shot natural language understanding. Concretely, MSP-tuning masks randomly out part of the prompt tokens to get a pair of masked siamese prompts for each sample. Each training sample is then fed to the model twice with the masked siamese prompts. Finally, MSP-tuning minimizes the JS-divergence between the two output probability distributions of the pre-trained language model to regularize the model further. Experiment results on the few-shot GLUE benchmark and SuperGLUE benchmark show that MSP-tuning outperforms previous approaches. Numerically, our MSP-tuning achieves an average improvement of 1.79% (BERT-base) and 1.39% (BERT-large) of the GLUE benchmark and 1.90% (RoBERTa-base) and 1.71% (RoBERTa-large) of the SuperGLUE benchmark compared to state-of-the-art method P-tuning. Our method facilitates applying large pre-trained language models in natural language understanding.

AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning

<scp>AutoPEFT</scp>: Automatic Configuration Search for Parameter-Efficient Fine-Tuning

Few-Shot Relation Extraction With Automatically Generated Prompts.

Relation extraction (RE) tends to struggle when the supervised training data is few and difficult to be collected. In this article, we elicit relational and factual knowledge from large pretrained language models (PLMs) for few-shot RE (FSRE) with prompting techniques. Concretely, we automatically generate a diverse set of natural language templates and modulate PLM's behavior through these prompts for FSRE. To mitigate the template bias which leads to unstableness of few-shot learning, we propose a simple yet effective template regularization network (TRN) to prevent deep networks from over-fitting uncertain templates and thus stabilize the FSRE models. TRN alleviates the template bias with three mechanisms: 1) an attention mechanism over mini-batch to weight each template; 2) a ranking regularization mechanism to regularize the attention weights and constrain the importance of uncertain templates; and 3) a template calibration module with two calibrating techniques to modify the uncertain templates in the lowest-ranked group. Experimental results on two benchmark datasets (i.e., FewRel and NYT) show that our model has robust superiority over strong competitors. For reproducibility, we will release our code and data upon the publication of this article.

Building a Large Corpus and Pre-trained Language Models from National and Local Assembly Minutes

Building a Large Corpus and Pre-trained Language Models from National and Local Assembly Minutes