Automated Essay Scoring is one of the most important educational applications of naturallanguageprocessing. It helps teachers with automatic assessments, providing a cheaper, faster, and more deterministic approach ...
详细信息
ISBN:
(纸本)9783031790348;9783031790355
Automated Essay Scoring is one of the most important educational applications of naturallanguageprocessing. It helps teachers with automatic assessments, providing a cheaper, faster, and more deterministic approach than humans when scoring essays. Nevertheless, off-topic essays pose challenges in this area, causing an automated grader to overestimate the score of an essay that does not adhere to a proposed topic. Thus, detecting off-topic essays is important for dealing with unrelated text responses to a given topic. This paper explored approaches based on handcrafted features to feed supervised machine-learning algorithms, tuning a BERT model, and prompt engineering with a large language model. We assessed these strategies in a public corpus of Portuguese essays, achieving the best result using a fine-tuned BERT model with a 75% balanced accuracy. Furthermore, this strategy was able to identify low-quality essays.
Zero-shot event-relational reasoning is an important task in naturallanguageprocessing, and existing methods jointly learn a variety of event-relational prefixes and inference-form prefixes to achieve such tasks. Ho...
详细信息
Moroccan Dialect (MD), or "Darija," is a primary spoken variant of Arabic in Morocco, yet remains underrepresented in naturallanguageprocessing (NLP) research, particularly in tasks like summarization. Des...
详细信息
How can we effectively model arguments communicated in diverse environments? On the one hand, there is a great opportunity with the abundance of digitized speech across different contexts including online forums, offi...
详细信息
ISBN:
(纸本)9783031785405;9783031785412
How can we effectively model arguments communicated in diverse environments? On the one hand, there is a great opportunity with the abundance of digitized speech across different contexts including online forums, official proceedings, or transcripts of spoken debates. On the other hand, there is a great challenge in correctly detecting arguments, especially since each medium has its own set of conventions, lingo, affordances, and styles of argumentative engagement. We propose WIBA, a novel framework and suite of methods that enable the comprehensive understanding of " What Is Being Argued" across contexts. Our approach develops a comprehensive framework that detects: (a) the existence, (b) the topic, and (c) the stance of an argument, correctly accounting for the logical dependence among the three tasks. Our algorithm leverages the fine-tuning and prompt-engineering of Large language Models. We evaluate our approach and show that it performs well in all the three capabilities. First, we develop and release an Argument Detection model that can classify a piece of text as an argument with an F-1 score between 79% and 86% on three different benchmark datasets. Second, we release a language model that can identify the topic being argued in a sentence, be it implicit or explicit, with an average similarity score of 71%, outperforming current naive methods by nearly 40%. Finally, we develop a method for Argument Stance Classification, and evaluate the capability of our approach, showing it achieves a classification F-1 score between 71% and 78% across three diverse benchmark datasets. Our evaluation demonstrates that WIBA allows the comprehensive understanding of What Is Being Argued in large corpora across diverse contexts, which is of core interest to many applications in linguistics, communication, and social and computer science. To facilitate accessibility to the advancements outlined in this work, we release WIBA as a free open access platform (***) and API.
Recently, Large language models (LLMs) have revolutionized naturallanguageprocessing (NLP). Pretrained LLMs, due to limited training context size, struggle with handling long token sequences, limiting their performa...
详细信息
Large language Models (LLMs) have demonstrated exceptional performance across a broad spectrum of cross-lingual naturallanguageprocessing (NLP) tasks. However, previous methods predominantly focus on leveraging para...
详细信息
Large language Models (LLMs) have been widely employed in various text processing tasks. In computer vision, these models have found application in generating captions and text from natural images, as well as in Visua...
详细信息
ISBN:
(纸本)9783031790317;9783031790324
Large language Models (LLMs) have been widely employed in various text processing tasks. In computer vision, these models have found application in generating captions and text from natural images, as well as in Visual Question Answering (VQA) systems. In the field of medical imaging, there are studies based on text generation proposing automated diagnoses of X-rays, magnetic resonance imaging scans, computed tomography scans, and other modalities. Few initiatives seek to apply and harness the potential of LLMs in medical text generation;they use models with tens of billions of parameters and are thus computationally expensive. This work addresses this gap by evaluating the use of frozen pre-trained models (CXAS U-Net and BioGPT) for chest Xray report generation. We adapt the BLIP-2 modular architecture where only a cross-modal alignment module must be trained in order to generate text from images. We were able to achieve competitive scores over Clinical Efficacy (CE) metrics compared to some state-of-the-art (SOTA) methods, while obtaining lower scores for naturallanguage Generation (NLG) metrics. Our findings suggest that NLG metrics may not serve as suitable proxies for evaluating models in the chest X-ray generation task.
Pre-trained language models (PrLMs) demonstrate impressive performance on the sentiment analysis task. However, the large number of trainable parameters brings about heavy computational costs, which become more seriou...
详细信息
Large language models have garnered significant attention and are widely utilized across different fields due to their impressive performance. However, centralized training of these models can pose privacy risks like ...
详细信息
Recent advancements in Large language Models (LLMs) have catalyzed the exploration of Chain of Thought (CoT) approaches, particularly in extending their application to multimodal tasks to enhance reasoning capabilitie...
详细信息
暂无评论