Bilingual Evaluation Understudy Research Articles

GPT-Driven Radiology Report Generation with Fine-Tuned Llama 3.

The integration of deep learning into radiology has the potential to enhance diagnostic processes, yet its acceptance in clinical practice remains limited due to various challenges. This study aimed to develop and evaluate a fine-tuned large language model (LLM), based on Llama 3-8B, to automate the generation of accurate and concise conclusions in magnetic resonance imaging (MRI) and computed tomography (CT) radiology reports, thereby assisting radiologists and improving reporting efficiency. A dataset comprising 15,000 radiology reports was collected from the University of Medicine and Pharmacy of Craiova's Imaging Center, covering a diverse range of MRI and CT examinations made by four experienced radiologists. The Llama 3-8B model was fine-tuned using transfer-learning techniques, incorporating parameter quantization to 4-bit precision and low-rank adaptation (LoRA) with a rank of 16 to optimize computational efficiency on consumer-grade GPUs. The model was trained over five epochs using an NVIDIA RTX 3090 GPU, with intermediary checkpoints saved for monitoring. Performance was evaluated quantitatively using Bidirectional Encoder Representations from Transformers Score (BERTScore), Recall-Oriented Understudy for Gisting Evaluation (ROUGE), Bilingual Evaluation Understudy (BLEU), and Metric for Evaluation of Translation with Explicit Ordering (METEOR) metrics on a held-out test set. Additionally, a qualitative assessment was conducted, involving 13 independent radiologists who participated in a Turing-like test and provided ratings for the AI-generated conclusions. The fine-tuned model demonstrated strong quantitative performance, achieving a BERTScore F1 of 0.8054, a ROUGE-1 F1 of 0.4998, a ROUGE-L F1 of 0.4628, and a METEOR score of 0.4282. In the human evaluation, the artificial intelligence (AI)-generated conclusions were preferred over human-written ones in approximately 21.8% of cases, indicating that the model's outputs were competitive with those of experienced radiologists. The average rating of the AI-generated conclusions was 3.65 out of 5, reflecting a generally favorable assessment. Notably, the model maintained its consistency across various types of reports and demonstrated the ability to generalize to unseen data. The fine-tuned Llama 3-8B model effectively generates accurate and coherent conclusions for MRI and CT radiology reports. By automating the conclusion-writing process, this approach can assist radiologists in reducing their workload and enhancing report consistency, potentially addressing some barriers to the adoption of deep learning in clinical practice. The positive evaluations from independent radiologists underscore the model's potential utility. While the model demonstrated strong performance, limitations such as dataset bias, limited sample diversity, a lack of clinical judgment, and the need for large computational resources require further refinement and real-world validation. Future work should explore the integration of such models into clinical workflows, address ethical and legal considerations, and extend this approach to generate complete radiology reports.

HybridEval: An Improved Novel Hybrid Metric for Evaluation of Text Summarization

The present work re-evaluates the evaluation method for text summarization tasks. Two state-of-the-art assessment measures e.g., Recall-Oriented Understudy for Gisting Evaluation (ROUGE) and Bilingual Evaluation Understudy (BLEU) are discussed along with their limitations before presenting a novel evaluation metric. The evaluation scores are significantly different because of the length and vocabulary of the sentences, this suggests that the primary restriction is its inability to preserve the semantics and meaning of the sentences and consistent weight distribution over the whole sentence. To address this, the present work organizes the phrases into six different groups and to evaluate “text summarization” problems, a new hybrid approach (HybridEval) is proposed. Our approach uses a weighted sum of cosine scores from InferSent’s SentEval algorithms combined with original scores, achieving high accuracy. HybridEval outperforms existing state-of-the-art models by 10-15% in evaluation scores.

Enhancing Neural Machine Translation Quality for Kannada–Tulu Language Pairs through Transformer Architecture: A Linguistic Feature Integration

The rise of intelligent systems demands good machine translation models that are less data hungry and more efficient, especially for low- and extremely-low-resource languages with few or no data available. By integrating a linguistic feature to enhance the quality of translation, we have developed a generic Neural Machine Translation (NMT) model for Kannada–Tulu language pairs. The NMT model uses Transformer architecture and a state-of-the-art model for translating text from Kannada to Tulu and learns based on the parallel data. Kannada and Tulu are both low-resource Dravidian languages, with Tulu recognised as an extremely-low-resource language. Dravidian languages are morphologically rich and are highly agglutinative in nature and there exist only a few NMT models for Kannada–Tulu language pairs. They exhibit poor translation scores as they fail to capture the linguistic features of the language. The proposed generic approach can benefit other low-resource Indic languages that have smaller parallel corpora for NMT tasks. Evaluation metrics like Bilingual Evaluation Understudy (BLEU), character-level F-score (chrF) and Word Error Rate (WER) are considered to obtain the improved translation scores for the linguistic-feature-embedded NMT model. These results hold promise for further experimentation with other low- and extremely-low-resource language pairs.

Dynamic Multi-Granularity Translation System: DAG-Structured Multi-Granularity Representation and Self-Attention

In neural machine translation (NMT), the sophistication of word embeddings plays a pivotal role in the model’s ability to render accurate and contextually relevant translations. However, conventional models with single granularity of word segmentation cannot fully embed complex languages like Chinese, where the granularity of segmentation significantly impacts understanding and translation fidelity. Addressing these challenges, our study introduces the Dynamic Multi-Granularity Translation System (DMGTS), an innovative approach that enhances the Transformer model by incorporating multi-granularity position encoding and multi-granularity self-attention mechanisms. Leveraging a Directed Acyclic Graph (DAG), the DMGTS utilizes four levels of word segmentation for multi-granularity position encoding. Dynamic word embeddings are also introduced to enhance the lexical representation by incorporating multi-granularity features. Multi-granularity self-attention mechanisms are applied to replace the conventional self-attention layers. We evaluate the DMGTS on multiple datasets, where our system demonstrates marked improvements. Notably, it achieves significant enhancements in translation quality, evidenced by increases of 1.16 and 1.55 in Bilingual Evaluation Understudy (BLEU) scores over traditional static embedding methods. These results underscore the efficacy of the DMGTS in refining NMT performance.

Design of a turbo-based deep semantic autoencoder for marine Internet of Things

With the rapid growth of the global marine economy and flourishing maritime activities, the marine Internet of Things (IoT) is gaining unprecedented momentum. However, current marine equipment is deficient in data transmission efficiency and semantic comprehension. To address these issues, this paper proposes a novel End-to-End (E2E) coding scheme, namely the Turbo-based Deep Semantic Autoencoder (Turbo-DSA). The Turbo-DSA achieves joint source-channel coding at the semantic level through the E2E design of transmitter and receiver, while learning to adapt to environment changes. The semantic encoder and decoder are composed of transformer technology, which efficiently converts messages into semantic vectors. These vectors are dynamically adjusted during neural network training according to channel characteristics and background knowledge base. The Turbo structure further enhances the semantic vectors. Specifically, the channel encoder utilizes Turbo structure to separate semantic vectors, ensuring precise transmission of meaning, while the channel decoder employs Turbo iterative decoding to optimize the representation of semantic vectors. This deep integration of the transformer and Turbo structure is ensured by the design of the objective function, semantic extraction, and the entire training process. Compared with traditional Turbo coding techniques, the Turbo-DSA shows a faster convergence speed, thanks to its efficient processing of semantic vectors. Simulation results demonstrate that the Turbo-DSA surpasses existing benchmarks in key performance indicators, such as bilingual evaluation understudy scores and sentence similarity. This is particularly evident under low signal-to-noise ratio conditions, where it shows superior text semantic transmission efficiency and adaptability to variable marine channel environments.

Indonesian to Bengkulu Malay Statistical Machine Translation System

Machine translation is an automatic tool that can process language translation from one language to another. This research focuses on developing Statistical Machine Translation (SMT) from Indonesian to Bengkulu Malay and evaluating the quality of the machine translation output. The training and testing data consist of parallel corpora taken from Bengkulu Malay dictionaries and online resources for Indonesian corpora, with a total of 5261 parallel sentence pairs. Several steps are performed in SMT. The initial step is preprocessing, aimed at preparing the parallel corpus. After that, a training phase is conducted, where the parallel corpus is processed to build language and translation models. Subsequently, a testing phase is carried out, followed by an evaluation phase. Based on the research results, various factors influence the quality of SMT translation output. The most important factor is the quantity and quality of the parallel corpus used as the foundation for developing translation and language models. The machine translation output is automatically evaluated using the Bilingual Evaluation Understudy (BLEU), indicating accuracy values observed when using 500 sentences, 1500 sentences, 2500 sentences, 4000 sentences, and 5261 sentences are 80.56%, 90.86%, 92.50%, 92.91%, and 94.48% respectively.

An optimized Transformer algorithm: Implementation for intelligent English translation

There is an increasing demand for high-quality translations in the realm of intelligent English translation. This paper optimized the traditional Transformer algorithm by enhancing position coding and the softmax layer. Bidirectional long short-term memory (BiLST) was employed to realize position encoding, capturing both contextual and positional information simultaneously. Additionally, the softmax function was replaced with the sparsemax function to obtain sparser results. The translation performance of some algorithms on Chinese and English datasets was compared and analyzed. It was found that that the optimized Transformer algorithm performed better than the RNNSearch, ConvS2S, and Transformer-base algorithms in terms of bilingual evaluation understudy (BLEU) score on the test set. It achieved an average BLEU score of 23.72, representing an improvement of 1.56 over the RNNSearch algorithm, 1.17 over the ConvS2S algorithm, and 0.73 over the Transformer-base algorithm. The parameter quantity of the optimized algorithm was 6.83 M, which was 0.05 M higher than the Transformer-base algorithm. Furthermore, its running time was 4,862.76 s, showing a marginal increase of 0.21% compared to the Transformer-base algorithm. These findings validate the reliability of the optimized Transformer algorithm for intelligent English translation and its potential practical application.

Reinforcement of low-resource language translation with neural machine translation and backtranslation synergies

<p><span lang="EN-US">This research investigates challenges and advancements in neural machine translation (NMT), specifically targeting English-to-Kannada translation. Emphasizing the scarcity of data and linguistic complexity in low-resource languages (LRL), particularly Kannada, the study underscores the need for specialized techniques. Starting with exploration of Kannada's historical and cultural significance, the paper highlights critical importance of linguistic comprehension. The primary objective is to develop robust NMT models for precise and contextually relevant translations in low-resource scenarios. The novelty of this research lies in its innovative approach to Kannada NMT challenges, incorporating comprehensive examination of historical and cultural context to establish strong linguistic foundation. Motivated by the urgency to address translation needs in LRL, the paper proposes novel strategies, advocating notably for backtranslation to generate synthetic parallel corpora. Rigorous testing, including bilingual evaluation understudy (BLEU) score assessments, evaluates effectiveness of these proposed approaches. Beyond assessing backtranslation, the study explores challenges faced by Kannada NMT in handling dialectical and spelling variations. The research reports substantial 83-percentage-point average increase in BLEU scores, contingent on aligning unique Kannada terms with the same domain as existing occurrences. This study contributes significantly to Kannada natural language processing by offering novel insights into NMT intricacies and providing practical solutions for enhancing translation accuracy in low-resource settings.</span></p>

Exploration on Advanced Intelligent Algorithms of Artificial Intelligence for Verb Recognition in Machine Translation

This article aimed to address the problems of word order confusion, context dependency, and ambiguity in traditional machine translation (MT) methods for verb recognition. By applying advanced intelligent algorithms of artificial intelligence, verb recognition can be better processed and the quality and accuracy of MT can be improved. Based on Neural machine translation (NMT), basic attention mechanisms, historical attention information, dynamically obtain information related to the generated words, and constraint mechanisms were introduced to embed semantic information, represent polysemy, and annotate semantic roles of verbs. This article used the Workshop on MT (WMT), British National Corpus (BNC), Gutenberg, Reuters Corpus, and OpenSubtitles corpus, and enhanced the data in the corpora. The improved NMT model was compared with traditional NMT models, Rule-Based MT (RBMT), and Statistical MT (SMT). The experimental results showed that the average verb semantic matching degree of the improved NMT model in five corpora was 0.85, and the average Bilingual Evaluation Understudy (BLEU) score in five corpora was 0.90. The improved NMT model in this article can effectively improve the accuracy of verb recognition in MT, providing new methods for verb recognition in MT.

CSAMDT: Conditional Self Attention Memory-Driven Transformers for Radiology Report Generation from Chest X-Ray.

A radiology report plays a crucial role in guiding patient treatment, but writing these reports is a time-consuming task that demands a radiologist's expertise. In response to this challenge, researchers in the subfields of artificial intelligence for healthcare have explored techniques for automatically interpreting radiographic images and generating free-text reports, while much of the research on medical report creation has focused on image captioning methods without adequately addressing particular report aspects. This study introduces a Conditional Self Attention Memory-Driven Transformer model for generating radiological reports. The model operates in two phases: initially, a multi-label classification model, utilizing ResNet152 v2 as an encoder, is employed for feature extraction and multiple disease diagnosis. In the second phase, the Conditional Self Attention Memory-Driven Transformer serves as a decoder, utilizing self-attention memory-driven transformers to generate text reports. Comprehensive experimentation was conducted to compare existing and proposed techniques based on Bilingual Evaluation Understudy (BLEU) scores ranging from 1 to 4. The model outperforms the other state-of-the-art techniques by increasing the BLEU 1 (0.475), BLEU 2 (0.358), BLEU 3 (0.229), and BLEU 4 (0.165) respectively. This study's findings can alleviate radiologists' workloads and enhance clinical workflows by introducing an autonomous radiological report generation system.

Statistical machine translation for Indic languages

Abstract Statistical Machine Translation (SMT) systems use various probabilistic and statistical Natural Language Processing (NLP) methods to automatically translate from one language to another language while retaining the originality of the context. This paper aims to discuss the development of bilingual SMT models for translating English into fifteen low-resource Indic languages (ILs) and vice versa. The process to build the SMT model is described and explained using a workflow diagram. Samanantar and OPUS corpus are utilized for training, and Flores200 corpus is used for fine-tuning and testing purposes. The paper also highlights various preprocessing methods used to deal with corpus noise. The Moses open-source SMT toolkit is being investigated for the system’s development. The impact of distance-based reordering and Morpho-syntactic Descriptor Bidirectional Finite-State Encoder (msd-bidirectional-fe) reordering on ILs is compared in the paper. This paper provides a comparison of SMT models with Neural Machine Translation (NMT) for ILs. All the experiments assess the translation quality using standard metrics such as BiLingual Evaluation Understudy, Rank-based Intuitive Bilingual Evaluation Score, Translation Edit Rate, and Metric for Evaluation of Translation with Explicit Ordering. From the result, it is observed that msd-bidirectional-fe reordering performs better than the distance-based reordering model for ILs. It is also noticed that even though the IL-English and English-IL systems are trained using the same corpus, the former performs better for all the evaluation metrics. The comparison between SMT and NMT shows that across various languages, SMT performs better in some cases, while NMT outperforms in others.

A multi-domain adaptive neural machine translation method based on domain data balancer

Most methods for multi-domain adaptive neural machine translation (NMT) currently rely on mixing data from multiple domains in a single model to achieve multi-domain translation. However, this mixing can lead to imbalanced training data, causing the model to focus on training for the large-scale general domain while ignoring the scarce resources of specific domains, resulting in a decrease in translation performance. In this paper, we propose a multi-domain adaptive NMT method based on Domain Data Balancer (DDB) to address the problems of imbalanced data caused by simple fine-tuning. By adding DDB to the Transformer model, we adaptively learn the sampling distribution of each group of training data, replace the maximum likelihood estimation criterion with empirical risk minimization training, and introduce a reward-based iterative update of the bilevel optimizer based on reinforcement learning. Experimental results show that the proposed method improves the baseline model by an average of 1.55 and 0.14 BLEU (Bilingual Evaluation Understudy) scores respectively in English-German and Chinese-English multi-domain NMT.

Multilingual Neural Machine Translation for Indic to Indic Languages

The method of translation from one language to another without human intervention is known as Machine Translation (MT). Multilingual neural machine translation (MNMT) is a technique for MT that builds a single model for multiple languages. It is preferred over other approaches, since it decreases training time and improves translation in low-resource contexts, i.e., for languages that have insufficient corpus. However, good-quality MT models are yet to be built for many scenarios such as for Indic-to-Indic Languages (IL-IL). Hence, this article is an attempt to address and develop the baseline models for low-resource languages i.e., IL-IL (for 11 Indic Languages (ILs)) in a multilingual environment. The models are built on the Samanantar corpus and analyzed on the Flores-200 corpus. All the models are evaluated using standard evaluation metrics i.e., Bilingual Evaluation Understudy (BLEU) score (with the range of 0 to 100). This article examines the effect of the grouping of related languages, namely, East Indo-Aryan (EI), Dravidian (DR), and West Indo-Aryan (WI) on the MNMT model. From the experiments, the results reveal that related language grouping is beneficial for the WI group only while it is detrimental for the EI group and it shows an inconclusive effect on the DR group. The role of pivot-based MNMT models in enhancing translation quality is also investigated in this article. Owing to the presence of large good-quality corpora from English (EN) to ILs, MNMT IL-IL models using EN as a pivot are built and examined. To achieve this, English-Indic Language (EN-IL) models are developed with and without the usage of related languages. Results show that the use of related language grouping is advantageous specifically for EN to ILs. Thus, related language groups are used for the development of pivot MNMT models. It is also observed that the usage of pivot models greatly improves MNMT baselines. Furthermore, the effect of transliteration on ILs is also analyzed in this article. To explore transliteration, the best MNMT models from the previous approaches (in most of cases pivot model using related groups) are determined and built on corpus transliterated from the corresponding scripts to a modified Indian language Transliteration script (ITRANS). The outcome of the experiments indicates that transliteration helps the models built for lexically rich languages, with the best increment of BLEU scores observed in Malayalam (ML) and Tamil (TA), i.e., 6.74 and 4.72, respectively. The BLEU score using transliteration models ranges from 7.03 to 24.29. The best model obtained is the Punjabi (PA)-Hindi (HI) language pair trained on PA-WI transliterated corpus.

An Evaluation of ChatGPT's Translation Accuracy Using BLEU Score

Traditional views have long held that machine translation cannot achieve the quality and accuracy of human translators, especially in complex language pairs like Persian and English. This study challenges this perspective by demonstrating that ChatGPT-4, with access to vast amounts of multilingual data and leveraging advanced large language model algorithms, significantly outperforms widely utilized open-source machine translation tools and approaches the realm of human translation quality. This research aims to critically assess the translation accuracy of ChatGPT-4 against a traditional open-source machine translation tool from Persian to English, highlighting the advancements in artificial intelligence-driven translation technologies. Using Bilingual Evaluation Understudy scores for a comprehensive evaluation, this study compares the translation outputs from ChatGPT-4 with MateCat, providing a quantitative basis for comparing their accuracy and quality. ChatGPT-4 achieves a BLUE score of 0.88 and an accuracy of 0.68, demonstrating superior performance compared to MateCat, with a 0.82 BLUE score and 0.49 accuracy. The results indicate that the translations generated by ChatGPT-4 surpass those produced by MateCat and nearly mirror the quality of human translations. The evaluation demonstrates the effectiveness of OpenAI's large language model algorithms in improving translation accuracy.

Quality of Answers of Generative Large Language Models Versus Peer Users for Interpreting Laboratory Test Results for Lay Patients: Evaluation Study.

Although patients have easy access to their electronic health records and laboratory test result data through patient portals, laboratory test results are often confusing and hard to understand. Many patients turn to web-based forums or question-and-answer (Q&A) sites to seek advice from their peers. The quality of answers from social Q&A sites on health-related questions varies significantly, and not all responses are accurate or reliable. Large language models (LLMs) such as ChatGPT have opened a promising avenue for patients to have their questions answered. We aimed to assess the feasibility of using LLMs to generate relevant, accurate, helpful, and unharmful responses to laboratory test-related questions asked by patients and identify potential issues that can be mitigated using augmentation approaches. We collected laboratory test result-related Q&A data from Yahoo! Answers and selected 53 Q&A pairs for this study. Using the LangChain framework and ChatGPT web portal, we generated responses to the 53 questions from 5 LLMs: GPT-4, GPT-3.5, LLaMA 2, MedAlpaca, and ORCA_mini. We assessed the similarity of their answers using standard Q&A similarity-based evaluation metrics, including Recall-Oriented Understudy for Gisting Evaluation, Bilingual Evaluation Understudy, Metric for Evaluation of Translation With Explicit Ordering, and Bidirectional Encoder Representations from Transformers Score. We used an LLM-based evaluator to judge whether a target model had higher quality in terms of relevance, correctness, helpfulness, and safety than the baseline model. We performed a manual evaluation with medical experts for all the responses to 7 selected questions on the same 4 aspects. Regarding the similarity of the responses from 4 LLMs; the GPT-4 output was used as the reference answer, the responses from GPT-3.5 were the most similar, followed by those from LLaMA 2, ORCA_mini, and MedAlpaca. Human answers from Yahoo data were scored the lowest and, thus, as the least similar to GPT-4-generated answers. The results of the win rate and medical expert evaluation both showed that GPT-4's responses achieved better scores than all the other LLM responses and human responses on all 4 aspects (relevance, correctness, helpfulness, and safety). LLM responses occasionally also suffered from lack of interpretation in one's medical context, incorrect statements, and lack of references. By evaluating LLMs in generating responses to patients' laboratory test result-related questions, we found that, compared to other 4 LLMs and human answers from a Q&A website, GPT-4's responses were more accurate, helpful, relevant, and safer. There were cases in which GPT-4 responses were inaccurate and not individualized. We identified a number of ways to improve the quality of LLM responses, including prompt engineering, prompt augmentation, retrieval-augmented generation, and response evaluation.

BiLSTMs and BPE for English to Telugu CLIR

A crucial component of Cross Lingual Information Retrieval (CLIR) is Neural Machine Translation (NMT). NMT performs a good job of transforming queries in the English language into Indian languages. This study focuses on the translation of English queries into Telugu. For translations, the NMT will make use of a parallel corpus. Due to a lack of resources in the Telugu language, it is exceedingly challenging to provide NMT with sizable parallel corpora. Thus, the NMT will encounter an issue known as Out of Vocabulary (OOV). Long Short-Term Memory (LSTM) with Byte Pair Encoding (BPE), which breaks up rare words into subwords and attempts to translate them to solve the OOV issue. Issues such as Named Entity Recognition (NER) continue to plague it. In sequence-to-sequence models, bidirectional LSTMs can solve certain NER challenges. Systems that need to be trained in both directions to recognize named entities can benefit from the use of Bidirectional LSTMs (BiLSTMs). The translation efficiency of NMT with BiLSTMs is significantly higher than normal LSTMs, as indicated by the accuracy metrics and Bilingual Evaluation Understudy (BLEU) score.

GCMSFormer: A Fully Automatic Method for the Resolution of Overlapping Peaks in Gas Chromatography-Mass Spectrometry.

Gas chromatography-mass spectrometry (GC-MS) is one of the most important instruments for analyzing volatile organic compounds. However, the complexity of real samples and the limitations of chromatographic separation capabilities lead to coeluting compounds without ideal separation. In this study, a Transformer-based automatic resolution method (GCMSFormer) is proposed to resolve mass spectra from GC-MS peaks in an end-to-end manner, predicting the mass spectra of components directly from the raw overlapping peaks data. Furthermore, orthogonal projection resolution (OPR) was integrated into GCMSFormer to resolve minor components. The GCMSFormer model was trained, validated, and tested using 100,000 augmented data. It achieves 99.88% of the bilingual evaluation understudy (BLEU) value on the test set, significantly higher than the 97.68% BLEU value of the baseline sequence-to-sequence model long short-term memory (LSTM). GCMSFormer was also compared with two nondeep learning resolution tools (MZmine and AMDIS) and two deep learning resolution tools (PARAFAC2 with DL and MSHub/GNPS) on a real plant essential oil GC-MS data set. Their resolution results were compared on evaluation metrics, including the number of compounds resolved, mass spectral match score, correlation coefficient, explained variance, and resolution speed. The results demonstrate that GCMSFormer has better resolution performance, higher automation, and faster resolution speed. In summary, GCMSFormer is an end-to-end, fast, fully automatic, and accurate method for analyzing GC-MS data of complex samples.

Exploring the potential of data augmentation in poetry generation with small-scale corpora

Poetry generation is a complex task in the field of natural language processing, especially when working with small datasets. Data augmentation techniques have been shown to be an effective way to improve the performance of deep learning models in various tasks, including image classification and speech recognition. Therefore, this study focuses on exploring the impact of four different data augmentation methods - Synonym Replacement, Random Insertion, Random Swap, and Random Deletion - on the performance of poetry generation with a small poetry dataset. The results of the study reveal that Random Insertion performed well in terms of Bilingual Evaluation Understudy (BLEU), Recall-Oriented Understudy for Gisting Evaluation (ROUGE), and manual evaluation when compared to other data augmentation techniques. Synonym Replacement performed poorly in all three evaluations. This study confirms the potential value of data augmentation technology in poetry generation tasks and provides innovative perspectives and directions for future research in this area. Data augmentation can be employed to help address the problem of limited data in poetry generation tasks and enhance the efficiency of deep learning models. Future research could focus on exploring more advanced data augmentation techniques and their impact on poetry generation tasks.

Asm2Seq: Explainable Assembly Code Functional Summary Generation for Reverse Engineering and Vulnerability Analysis

Reverse engineering is the process of understanding the inner working of a software system without having the source code. It is critical for firmware security validation, software vulnerability research, and malware analysis. However, it often requires a significant amount of manual effort. Recently, data-driven solutions were proposed to reduce manual effort by identifying the code clones on the assembly or the source level. However, security analysts still have to understand the matched assembly or source code to develop an understanding of the functionality, and it is assumed that such a matched candidate always exists. This research bridges the gap by introducing the problem of assembly code summarization. Given the assembly code as input, we propose a machine-learning-based system that can produce human-readable summarizations of the functionalities in the context of code vulnerability analysis. We generate the first assembly code to function summary dataset and propose to leverage the encoder-decoder architecture. With the attention mechanism, it is possible to understand what aspects of the assembly code had the largest impact on generating the summary. Our experiment shows that the proposed solution achieves high accuracy and the Bilingual Evaluation Understudy (BLEU) score. Finally, we have performed case studies on real-life CVE vulnerability cases to better understand the proposed method’s performance and practical implications.

ICGA-GPT: report generation and question answering for indocyanine green angiography images

BackgroundIndocyanine green angiography (ICGA) is vital for diagnosing chorioretinal diseases, but its interpretation and patient communication require extensive expertise and time-consuming efforts. We aim to develop a bilingual ICGA report...