Domain-specific text classification faces the challenge of scarce labeled data due to the high cost of manual labeling. Prompt-learning, known for its efficiency in few-shot scenarios, is proposed as an alternative to traditional fine-tuning methods. And besides, although large language models (LLMs) have gained prominence, small language models (SLMs, with under 1B parameters) offer significant customizability, adaptability, and cost-effectiveness for domain-specific tasks, given industry constraints. In this study, we investigate the potential of SLMs combined with prompt-learning paradigm for domain-specific text classification, specifically within customer-agent interactions in retail. Our evaluations show that, in few-shot settings when prompt-based model fine-tuning is possible, T5-base, a typical SLM with 220M parameters, achieve approximately 75% accuracy with limited labeled data (up to 15% of full data), which shows great potentials of SLMs with prompt-learning. Based on this, We further validate the effectiveness of active few-shot sampling and the ensemble strategy in the prompt-learning pipeline that contribute to a remarkable performance gain. Besides, in zero-shot settings with a fixed model, we underscore a pivotal observation that, although the GPT-3.5-turbo equipped with around 154B parameters garners an accuracy of 55.16%, the power of well designed prompts becomes evident when the FLAN-T5-large, a model with a mere 0.5% of GPT-3.5-turbo's parameters, achieves an accuracy exceeding 31% with the optimized prompt, a leap from its sub-18% performance with an unoptimized one. Our findings underscore the promise of prompt-learning in classification tasks with SLMs, emphasizing the benefits of active few-shot sampling, and ensemble strategies in few-shot settings, and the importance of prompt engineering in zero-shot settings.
Large language models (LLMs) enable in-context learning (ICL) by conditioning on a few labeled training examples as a text-based prompt, eliminating the need for parameter updates and achieving competitive performance. In this paper, we demonstrate that factual knowledge is imperative for the performance of ICL in three core facets: the inherent knowledge learned in LLMs, the factual knowledge derived from the selected in-context examples, and the knowledge biases in LLMs for output generation. To unleash the power of LLMs in few-shot learning scenarios, we introduce a novel Knowledgeable In-Context Tuning (KICT) framework to further improve the performance of ICL: 1) injecting knowledge into LLMs during continual self-supervised pre-training, 2) judiciously selecting the examples for ICL with high knowledge relevance, and 3) calibrating the prediction results based on prior knowledge. We evaluate the proposed approaches on autoregressive models (e.g., GPT-style LLMs) over multiple text classification and question-answering tasks. Experimental results demonstrate that KICT substantially outperforms strong baselines and improves by more than 13% and 7% on text classification and question-answering tasks, respectively.
In recent years, with the rapid development of information on the Internet, the number of complex texts and documents has increased exponentially, which requires a deeper understanding of deep learning methods in order to accurately classify texts using deep learning techniques, and thus deep learning methods have become increasingly important in text classification. Text classification is a class of tasks that automatically classifies a set of documents into multiple predefined categories based on their content and subject matter. Thus, the main goal of text classification is to enable users to extract information from textual resources and process processes such as retrieval, classification, and machine learning techniques together in order to classify different categories. Many new techniques of deep learning have already achieved excellent results in natural language processing. The success of these learning algorithms relies on their ability to understand complex models and non-linear relationships in data. However, finding the right structure, architecture, and techniques for text classification is a challenge for researchers. This paper introduces deep learning-based text classification algorithms, including important steps required for text classification tasks such as feature extraction, feature reduction, and evaluation strategies and methods. At the end of the article, different deep learning text classification methods are compared and summarized.
Large Language Models (LLMs) have emerged as one of the most important breakthroughs in NLP for their impressive skills in language generation and other language-specific tasks. Though LLMs have been evaluated in various tasks, mostly in English, they have not yet undergone thorough evaluation in under-resourced languages such as Bengali (Bangla). To this end, this paper introduces BenLLM-Eval, which consists of a comprehensive evaluation of LLMs to benchmark their performance in the Bengali language that has modest resources. In this regard, we select various important and diverse Bengali NLP tasks, such as text summarization, question answering, paraphrasing, natural language inference, transliteration, text classification, and sentiment analysis for zero-shot evaluation of popular LLMs, namely, GPT-3.5, LLaMA-2-13b-chat, and Claude-2. Our experimental results demonstrate that while in some Bengali NLP tasks, zero-shot LLMs could achieve performance on par, or even better than current SOTA fine-tuned models; in most tasks, their performance is quite poor (with the performance of open-source LLMs like LLaMA-2-13b-chat being significantly bad) in comparison to the current SOTA results. Therefore, it calls for further efforts to develop a better understanding of LLMs in modest-resourced languages like Bengali.
Multi-label text classification (MLTC) is the task of assigning multiple labels to a given text, and has a wide range of application domains. Most existing approaches require an enormous amount of annotated data to learn a classifier and/or a set of well-defined constraints on the label space structure, such as hierarchical relations which may be complicated to provide as the number of labels increases. In this paper, we study the MLTC problem in annotation-free and scarce-annotation settings in which the magnitude of available supervision signals is linear to the number of labels. Our method follows three steps, (1) mapping input text into a set of preliminary label likelihoods by natural language inference using a pre-trained language model, (2) calculating a signed label dependency graph by label descriptions, and (3) updating the preliminary label likelihoods with message passing along the label dependency graph, driven with a collective loss function that injects the information of expected label frequency and average multi-label cardinality of predictions. The experiments show that the proposed framework achieves effective performance under low supervision settings with almost imperceptible computational and memory overheads added to the usage of pre-trained language model outperforming its initial performance by 70\% in terms of example-based F1 score.
With the advent of larger and more complex deep learning models, such as in Natural Language Processing (NLP), model qualities like explainability and interpretability, albeit highly desirable, are becoming harder challenges to tackle and solve. For example, state-of-the-art models in text classification are black-box by design. Although standard explanation methods provide some degree of explainability, these are mostly correlation-based methods and do not provide much insight into the model. The alternative of causal explainability is more desirable to achieve but extremely challenging in NLP due to a variety of reasons. Inspired by recent endeavors to utilize Large Language Models (LLMs) as experts, in this work, we aim to leverage the instruction-following and textual understanding capabilities of recent state-of-the-art LLMs to facilitate causal explainability via counterfactual explanation generation for black-box text classifiers. To do this, we propose a three-step pipeline via which, we use an off-the-shelf LLM to: (1) identify the latent or unobserved features in the input text, (2) identify the input features associated with the latent features, and finally (3) use the identified input features to generate a counterfactual explanation. We experiment with our pipeline on multiple NLP text classification datasets, with several recent LLMs, and present interesting and promising findings.
Mixup is an effective data augmentation method that generates new augmented samples by aggregating linear combinations of different original samples. However, if there are noises or aberrant features in the original samples, Mixup may propagate them to the augmented samples, leading to over-sensitivity of the model to these outliers . To solve this problem, this paper proposes a new Mixup method called AMPLIFY. This method uses the Attention mechanism of Transformer itself to reduce the influence of noises and aberrant values in the original samples on the prediction results, without increasing additional trainable parameters, and the computational cost is very low, thereby avoiding the problem of high resource consumption in common Mixup methods such as Sentence Mixup . The experimental results show that, under a smaller computational resource cost, AMPLIFY outperforms other Mixup methods in text classification tasks on 7 benchmark datasets, providing new ideas and new ways to further improve the performance of pre-trained models based on the Attention mechanism, such as BERT, ALBERT, RoBERTa, and GPT. Our code can be obtained at https://github.com/kiwi-lilo/AMPLIFY.
An effective and efficient review of construction contracts is essential for minimizing construction projects losses, but current methods are time-consuming and error-prone. Studies using methods based on Natural Language Processing (NLP) exist, but their scope is often limited to text classification or segmented label prediction. This paper investigates whether integrating Large Language Models (LLMs) and Knowledge Graphs (KGs) can enhance the accuracy and interpretability of automated contract risk identification. A tuning-free approach is proposed that integrates LLMs with a Nested Contract Knowledge Graph (NCKG) using a Graph Retrieval-Augmented Generation (GraphRAG) framework for contract knowledge retrieval and reasoning. Tested on international EPC contracts, the method achieves more accurate risk evaluation and interpretable risk summaries than baseline models. These findings demonstrate the potential of combining LLMs and KGs for reliable reasoning in tasks that are knowledge-intensive and specialized, such as contract review.
Prompt Tuning is emerging as a scalable and cost-effective method to fine-tune Pretrained Language Models (PLMs), which are often referred to as Large Language Models (LLMs). This study benchmarks the performance and computational efficiency of Prompt Tuning and baselines for multi-label text classification. This is applied to the challenging task of classifying companies into an investment firm's proprietary industry taxonomy, supporting their thematic investment strategy. Text-to-text classification is frequently reported to outperform task-specific classification heads, but has several limitations when applied to a multi-label classification problem where each label consists of multiple tokens: (a) Generated labels may not match any label in the label taxonomy; (b) The fine-tuning process lacks permutation invariance and is sensitive to the order of the provided labels; (c) The model provides binary decisions rather than appropriate confidence scores. Limitation (a) is addressed by applying constrained decoding using Trie Search, which slightly improves classification performance. All limitations (a), (b), and (c) are addressed by replacing the PLM's language head with a classification head, which is referred to as Prompt Tuned Embedding Classification (PTEC). This improves performance significantly, while also reducing computational costs during inference. In our industrial application, the training data is skewed towards well-known companies. We confirm that the model's performance is consistent across both well-known and less-known companies. Our overall results indicate the continuing need to adapt state-of-the-art methods to domain-specific tasks, even in the era of PLMs with strong generalization abilities. We release our codebase and a benchmarking dataset at https://github.com/EQTPartners/PTEC.
In-context learning (ICL) using large language models for tasks with many labels is challenging due to the limited context window, which makes it difficult to fit a sufficient number of examples in the prompt. In this paper, we use a pre-trained dense retrieval model to bypass this limitation, giving the model only a partial view of the full label space for each inference call. Testing with recent open-source LLMs (OPT, LLaMA), we set new state of the art performance in few-shot settings for three common intent classification datasets, with no finetuning. We also surpass fine-tuned performance on fine-grained sentiment classification in certain cases. We analyze the performance across number of in-context examples and different model scales, showing that larger models are necessary to effectively and consistently make use of larger context lengths for ICL. By running several ablations, we analyze the model's use of: a) the similarity of the in-context examples to the current input, b) the semantic content of the class names, and c) the correct correspondence between examples and labels. We demonstrate that all three are needed to varying degrees depending on the domain, contrary to certain recent works.
How can we perform computations over natural language representations to solve tasks that require symbolic and numeric reasoning? We propose natural language embedded programs (NLEP) as a unifying framework for addressing math/symbolic reasoning, natural language understanding, and instruction following tasks. Our approach prompts a language model to generate full Python programs that define functions over data structures which contain natural language representations of structured knowledge. A Python interpreter then executes the generated code and prints the output. Despite using a task-general prompt, we find that this approach can improve upon strong baselines across a range of different tasks including math and symbolic reasoning, text classification, question answering, and instruction following. We found that the generated programs are interpretable since they outline the exact reasoning process followed by the program interpreter.
We study semantic compression for text where meanings contained in the text are conveyed to a source decoder, e.g., for classification. The main motivator to move to such an approach of recovering the meaning without requiring exact reconstruction is the potential resource savings, both in storage and in conveying the information to another node. Towards this end, we propose semantic quantization and compression approaches for text where we utilize sentence embeddings and the semantic distortion metric to preserve the meaning. Our results demonstrate that the proposed semantic approaches result in substantial (orders of magnitude) savings in the required number of bits for message representation at the expense of very modest accuracy loss compared to the semantic agnostic baseline. We compare the results of proposed approaches and observe that resource savings enabled by semantic quantization can be further amplified by semantic clustering. Importantly, we observe the generalizability of the proposed methodology which produces excellent results on many benchmark text classification datasets with a diverse array of contexts.
One of the most popular downstream tasks in the field of Natural Language Processing is text classification. Text classification tasks have become more daunting when the texts are code-mixed. Though they are not exposed to such text during pre-training, different BERT models have demonstrated success in tackling Code-Mixed NLP challenges. Again, in order to enhance their performance, Code-Mixed NLP models have depended on combining synthetic data with real-world data. It is crucial to understand how the BERT models' performance is impacted when they are pretrained using corresponding code-mixed languages. In this paper, we introduce Tri-Distil-BERT, a multilingual model pre-trained on Bangla, English, and Hindi, and Mixed-Distil-BERT, a model fine-tuned on code-mixed data. Both models are evaluated across multiple NLP tasks and demonstrate competitive performance against larger models like mBERT and XLM-R. Our two-tiered pre-training approach offers efficient alternatives for multilingual and code-mixed language understanding, contributing to advancements in the field.
User-generated texts available on the web and social platforms are often long and semantically challenging, making them difficult to annotate. Obtaining human annotation becomes increasingly difficult as problem domains become more specialized. For example, many health NLP problems require domain experts to be a part of the annotation pipeline. Thus, it is crucial that we develop low-resource NLP solutions able to work with this set of limited-data problems. In this study, we employ Abstract Meaning Representation (AMR) graphs as a means to model low-resource Health NLP tasks sourced from various online health resources and communities. AMRs are well suited to model online health texts as they can represent multi-sentence inputs, abstract away from complex terminology, and model long-distance relationships between co-referring tokens. AMRs thus improve the ability of pre-trained language models to reason about high-complexity texts. Our experiments show that we can improve performance on 6 low-resource health NLP tasks by augmenting text embeddings with semantic graph embeddings. Our approach is task agnostic and easy to merge into any standard text classification pipeline. We experimentally validate that AMRs are useful in the modeling of complex texts by analyzing performance through the lens of two textual complexity measures: the Flesch Kincaid Reading Level and Syntactic Complexity. Our error analysis shows that AMR-infused language models perform better on complex texts and generally show less predictive variance in the presence of changing complexity.
Most NLP tasks are modeled as supervised learning and thus require labeled training data to train effective models. However, manually producing such data at sufficient quality and quantity is known to be costly and time-intensive. Current research addresses this bottleneck by exploring a novel paradigm called zero-shot learning via dataset generation. Here, a powerful LLM is prompted with a task description to generate labeled data that can be used to train a downstream NLP model. For instance, an LLM might be prompted to "generate 500 movie reviews with positive overall sentiment, and another 500 with negative sentiment." The generated data could then be used to train a binary sentiment classifier, effectively leveraging an LLM as a teacher to a smaller student model. With this demo, we introduce Fabricator, an open-source Python toolkit for dataset generation. Fabricator implements common dataset generation workflows, supports a wide range of downstream NLP tasks (such as text classification, question answering, and entity recognition), and is integrated with well-known libraries to facilitate quick experimentation. With Fabricator, we aim to support researchers in conducting reproducible dataset generation experiments using LLMs and help practitioners apply this approach to train models for downstream tasks.
In this paper we present the first investigation into the effectiveness of Large Language Models (LLMs) for Failure Mode Classification (FMC). FMC, the task of automatically labelling an observation with a corresponding failure mode code, is a critical task in the maintenance domain as it reduces the need for reliability engineers to spend their time manually analysing work orders. We detail our approach to prompt engineering to enable an LLM to predict the failure mode of a given observation using a restricted code list. We demonstrate that the performance of a GPT-3.5 model (F1=0.80) fine-tuned on annotated data is a significant improvement over a currently available text classification model (F1=0.60) trained on the same annotated data set. The fine-tuned model also outperforms the out-of-the box GPT-3.5 (F1=0.46). This investigation reinforces the need for high quality fine-tuning data sets for domain-specific tasks using LLMs.
Predicting the personality type of text authors has a well-known usage in psychology with practical applications in business. From the data science perspective, we can look at this problem as a text classification task that can be tackled using natural language processing (NLP) and deep learning. This paper proposes a method and a novel loss function for multiclass classification using the Myers–Briggs Type Indicator (MBTI) approach for predicting the author’s personality type. Furthermore, this paper proposes an approach that improves the current results of the MBTI multiclass classification because it considers components of compound class labels as supportive elements for better classification according to MBTI. As such, it also provides a new perspective on this classification problem. The experimental results on long short-term memory (LSTM) and convolutional neural network (CNN) models outperform baseline models for multiclass classification, related research on multiclass classification, and most research with four binary approaches to MBTI classification. Moreover, other classification problems that target compound class labels and label parts with binary mutually exclusive values can benefit from this approach.
In-context learning (ICL) i.e. showing LLMs only a few task-specific demonstrations has led to downstream gains with no task-specific fine-tuning required. However, LLMs are sensitive to the choice of prompts, and therefore a crucial research question is how to select good demonstrations for ICL. One effective strategy is leveraging semantic similarity between the ICL demonstrations and test inputs by using a text retriever, which however is sub-optimal as that does not consider the LLM's existing knowledge about that task. From prior work (Lyu et al., 2023), we already know that labels paired with the demonstrations bias the model predictions. This leads us to our hypothesis whether considering LLM's existing knowledge about the task, especially with respect to the output label space can help in a better demonstration selection strategy. Through extensive experimentation on three text classification tasks, we find that it is beneficial to not only choose semantically similar ICL demonstrations but also to choose those demonstrations that help resolve the inherent label ambiguity surrounding the test example. Interestingly, we find that including demonstrations that the LLM previously mis-classified and also fall on the test example's decision boundary, brings the most performance gain.
Automatic identification of clinical trials for which a patient is eligible is complicated by the fact that trial eligibility is stated in natural language. A potential solution to this problem is to employ text classification methods for common types of eligibility criteria. In this study, we focus on seven common exclusion criteria in cancer trials: prior malignancy, human immunodeficiency virus, hepatitis B, hepatitis C, psychiatric illness, drug/substance abuse, and autoimmune illness. Our dataset consists of 764 phase III cancer trials with these exclusions annotated at the trial level. We experiment with common transformer models as well as a new pre-trained clinical trial BERT model. Our results demonstrate the feasibility of automatically classifying common exclusion criteria. Additionally, we demonstrate the value of a pre-trained language model specifically for clinical trials, which yields the highest average performance across all criteria.
Large Language Models (LLMs) have shown impressive performance across a variety of Artificial Intelligence (AI) and natural language processing tasks, such as content creation, report generation, etc. However, unregulated malign application of these models can create undesirable consequences such as generation of fake news, plagiarism, etc. As a result, accurate detection of AI-generated language can be crucial in responsible usage of LLMs. In this work, we explore 1) whether a certain body of text is AI generated or written by human, and 2) attribution of a specific language model in generating a body of text. Texts in both English and Spanish are considered. The datasets used in this study are provided as part of the Automated Text Identification (AuTexTification) shared task. For each of the research objectives stated above, we propose an ensemble neural model that generates probabilities from different pre-trained LLMs which are used as features to a Traditional Machine Learning (TML) classifier following it. For the first task of distinguishing between AI and human generated text, our model ranked in fifth and thirteenth place (with macro $F1$ scores of 0.733 and 0.649) for English and Spanish texts, respectively. For the second task on model attribution, our model ranked in first place with macro $F1$ scores of 0.625 and 0.653 for English and Spanish texts, respectively.