Search

Bias is a disproportionate prejudice in favor of one side against another. Due to the success of transformer-based masked language models (MLMs) and their impact on many NLP tasks, a systematic evaluation of bias in these models is now needed more than ever. While many studies have evaluated gender bias in English MLMs, only a few have explored gender bias in other languages. This paper proposes a multilingual approach to estimating gender bias in MLMs from five languages: Chinese, English, German, Portuguese, and Spanish. Unlike previous work, our approach does not depend on parallel corpora coupled with English to detect gender bias in other languages using multilingual lexicons. Moreover, a novel model-based method is presented to generate sentence pairs for a more robust analysis of gender bias. For each language, lexicon-based and model-based methods are applied to create two datasets, which are used to evaluate gender bias in an MLM specifically trained for that language using one existing and three new scoring metrics. Our results show that the previous approach is data-sensitive and unstable, suggesting that gender bias should be assessed on a large dataset using multiple evaluation metrics for best practice. [ABSTRACT FROM AUTHOR]

Generative AI applications have played an increasingly significant role in real-time tracking applications in many domains including, for example, healthcare, consultancy, dialog boxes (common types of window in a graphical user interface of operating systems), monitoring systems, and emergency response. This paper considers generative AI and presents an approach which combines hedge algebra and a multilingual large language model to find hidden rules in big data for ChatGPT. We present a novel method for extracting natural language knowledge from large datasets by leveraging fuzzy sets and hedge algebra to extract these rules, presented in meta data for ChatGPT and generative AI applications. The proposed model has been developed to minimize the computational and staff costs for medium-sized enterprises which are typically resource and time limited. The proposed model has been designed to automate question–response interactions for rules extracted from large data in a multiplicity of domains. The experimental results show that the proposed model performs well using datasets associated with specific domains in healthcare to validate the effectiveness of the proposed model. The ChatGPT application in case studies of healthcare is tested using datasets for English and Vietnamese languages. In comparative experimental testing, the proposed model outperformed the state of the art, achieving in the range of 96.70–97.50% performance using a heart dataset. [ABSTRACT FROM AUTHOR]

ChatGPT plays significant roles in the third decade of the 21st Century. Smart cities applications can be integrated with ChatGPT in various fields. This research proposes an approach for developing large language models using generative artificial intelligence models suitable for small- and medium-sized enterprises with limited hardware resources. There are many generative AI systems in operation and in development. However, the technological, human, and financial resources required to develop generative AI systems are impractical for small- and medium-sized enterprises. In this study, we present a proposed approach to reduce training time and computational cost that is designed to automate question–response interactions for specific domains in smart cities. The proposed model utilises the BLOOM approach as its backbone for using generative AI to maximum the effectiveness of small- and medium-sized enterprises. We have conducted a set of experiments on several datasets associated with specific domains to validate the effectiveness of the proposed model. Experiments using datasets for the English and Vietnamese languages have been combined with model training using low-rank adaptation to reduce training time and computational cost. In comparative experimental testing, the proposed model outperformed the 'Phoenix' multilingual chatbot model by achieving a 92% performance compared to 'ChatGPT' for the English benchmark. [ABSTRACT FROM AUTHOR]

The use of pre-trained language models fine-tuned to address specific downstream tasks is a common approach in natural language processing (NLP). However, acquiring domain-specific knowledge via fine-tuning is challenging. Traditional methods involve pretraining language models using vast amounts of domain-specific data before fine-tuning for particular tasks. This study investigates emergency/non-emergency classification tasks based on electronic medical record (EMR) data obtained from pediatric emergency departments (PEDs) in Korea. Our findings reveal that existing domain-specific pre-trained language models underperform compared to general language models in handling N-lingual free-text data characteristics of non-English-speaking regions. To address these limitations, we propose a domain knowledge transfer methodology that leverages knowledge distillation to infuse general language models with domain-specific knowledge via fine-tuning. This study demonstrates the effective transfer of specialized knowledge between models by defining a general language model as the student model and a domain-specific pre-trained model as the teacher model. In particular, we address the complexities of EMR data obtained from PEDs in non-English-speaking regions, such as Korea, and demonstrate that the proposed method enhances classification performance in such contexts. The proposed methodology not only outperforms baseline models on Korean PED EMR data, but also promises broader applicability in various professional and technical domains. In future works, we intend to extend this methodology to include diverse non-English-speaking regions and address additional downstream tasks, with the aim of developing advanced model architectures using state-of-the-art KD techniques. The code is available in https://github.com/JoSangYeon/DSG-KD.

Bias is a disproportionate prejudice in favor of one side against another. Due to the success of transformer-based masked language models (MLMs) and their impact on many NLP tasks, a systematic evaluation of bias in these models is now needed more than ever. While many studies have evaluated gender bias in English MLMs, only a few have explored gender bias in other languages. This paper proposes a multilingual approach to estimating gender bias in MLMs from five languages: Chinese, English, German, Portuguese, and Spanish. Unlike previous work, our approach does not depend on parallel corpora coupled with English to detect gender bias in other languages using multilingual lexicons. Moreover, a novel model-based method is presented to generate sentence pairs for a more robust analysis of gender bias. For each language, lexicon-based and model-based methods are applied to create two datasets, which are used to evaluate gender bias in an MLM specifically trained for that language using one existing and three new scoring metrics. Our results show that the previous approach is data-sensitive and unstable, suggesting that gender bias should be assessed on a large dataset using multiple evaluation metrics for best practice.

The advent of Multilingual Language Models (MLLMs) and Large Language Models (LLMs) has spawned innovation in many areas of natural language processing. Despite the exciting potential of this technology, its impact on developing high-quality Machine Translation (MT) outputs for low-resource languages remains relatively under-explored. Furthermore, an open-source application, dedicated to both fine-tuning MLLMs and managing the complete MT workflow for low-resources languages, remains unavailable. We aim to address these imbalances through the development of adaptMLLM, which streamlines all processes involved in the fine-tuning of MLLMs for MT. This open-source application is tailored for developers, translators, and users who are engaged in MT. It is particularly useful for newcomers to the field, as it significantly streamlines the configuration of the development environment. An intuitive interface allows for easy customisation of hyperparameters, and the application offers a range of metrics for model evaluation and the capability to deploy models as a translation service directly within the application. As a multilingual tool, we used adaptMLLM to fine-tune models for two low-resource language pairs: English to Irish (EN ↔ GA) and English to Marathi (EN ↔ MR). Compared with baselines from the LoResMT2021 Shared Task, the adaptMLLM system demonstrated significant improvements. In the EN → GA direction, an improvement of 5.2 BLEU points was observed and an increase of 40.5 BLEU points was recorded in the GA → EN direction representing relative improvements of 14% and 117%, respectively. Significant improvements in the translation performance of the EN ↔ MR pair were also observed notably in the MR → EN direction with an increase of 21.3 BLEU points which corresponds to a relative improvement of 68%. Finally, a fine-grained human evaluation of the MLLM output on the EN → GA pair was conducted using the Multidimensional Quality Metrics and Scalar Quality Metrics error taxonomies. The application and models are freely available. [ABSTRACT FROM AUTHOR]

Generative AI applications have played an increasingly significant role in real-time tracking applications in many domains including, for example, healthcare, consultancy, dialog boxes (common types of window in a graphical user interface of operating systems), monitoring systems, and emergency response. This paper considers generative AI and presents an approach which combines hedge algebra and a multilingual large language model to find hidden rules in big data for ChatGPT. We present a novel method for extracting natural language knowledge from large datasets by leveraging fuzzy sets and hedge algebra to extract these rules, presented in meta data for ChatGPT and generative AI applications. The proposed model has been developed to minimize the computational and staff costs for medium-sized enterprises which are typically resource and time limited. The proposed model has been designed to automate question–response interactions for rules extracted from large data in a multiplicity of domains. The experimental results show that the proposed model performs well using datasets associated with specific domains in healthcare to validate the effectiveness of the proposed model. The ChatGPT application in case studies of healthcare is tested using datasets for English and Vietnamese languages. In comparative experimental testing, the proposed model outperformed the state of the art, achieving in the range of 96.70–97.50% performance using a heart dataset.

ChatGPT plays significant roles in the third decade of the 21st Century. Smart cities applications can be integrated with ChatGPT in various fields. This research proposes an approach for developing large language models using generative artificial intelligence models suitable for small- and medium-sized enterprises with limited hardware resources. There are many generative AI systems in operation and in development. However, the technological, human, and financial resources required to develop generative AI systems are impractical for small- and medium-sized enterprises. In this study, we present a proposed approach to reduce training time and computational cost that is designed to automate question–response interactions for specific domains in smart cities. The proposed model utilises the BLOOM approach as its backbone for using generative AI to maximum the effectiveness of small- and medium-sized enterprises. We have conducted a set of experiments on several datasets associated with specific domains to validate the effectiveness of the proposed model. Experiments using datasets for the English and Vietnamese languages have been combined with model training using low-rank adaptation to reduce training time and computational cost. In comparative experimental testing, the proposed model outperformed the ‘Phoenix’ multilingual chatbot model by achieving a 92% performance compared to ‘ChatGPT’ for the English benchmark.

Copyright of Procesamiento del Lenguaje Natural is the property of Sociedad Espanola para el Procesamiento del Lenguaje Natural and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The advent of Multilingual Language Models (MLLMs) and Large Language Models (LLMs) has spawned innovation in many areas of natural language processing. Despite the exciting potential of this technology, its impact on developing high-quality Machine Translation (MT) outputs for low-resource languages remains relatively under-explored. Furthermore, an open-source application, dedicated to both fine-tuning MLLMs and managing the complete MT workflow for low-resources languages, remains unavailable. We aim to address these imbalances through the development of adaptMLLM, which streamlines all processes involved in the fine-tuning of MLLMs for MT. This open-source application is tailored for developers, translators, and users who are engaged in MT. It is particularly useful for newcomers to the field, as it significantly streamlines the configuration of the development environment. An intuitive interface allows for easy customisation of hyperparameters, and the application offers a range of metrics for model evaluation and the capability to deploy models as a translation service directly within the application. As a multilingual tool, we used adaptMLLM to fine-tune models for two low-resource language pairs: English to Irish (EN↔ GA) and English to Marathi (EN↔MR). Compared with baselines from the LoResMT2021 Shared Task, the adaptMLLM system demonstrated significant improvements. In the EN→GA direction, an improvement of 5.2 BLEU points was observed and an increase of 40.5 BLEU points was recorded in the GA→EN direction representing relative improvements of 14% and 117%, respectively. Significant improvements in the translation performance of the EN↔MR pair were also observed notably in the MR→EN direction with an increase of 21.3 BLEU points which corresponds to a relative improvement of 68%. Finally, a fine-grained human evaluation of the MLLM output on the EN→GA pair was conducted using the Multidimensional Quality Metrics and Scalar Quality Metrics error taxonomies. The application and models are freely available.

Computer-Supported Collaborative Learning (CSCL) is known to be productive if well structured. In CSCL, students construct knowledge by performing learning tasks while communicating about their work. This communication is most often done through online written chats. Understanding what is happening in chats is important from both research and practical perspectives. From a research perspective, insight into chat content offers a window into student interaction and learning. From a more practical standpoint, insight into chat content can (potentially) be used to trigger supportive elements in CSCL environments (e.g., context-sensitive tips or conversational agents). The latter requires real-time, and therefore automated, analysis of the chats. Such an automated analysis is also helpful from the research perspective, since hand-coding of chats is a very time and labour-consuming activity. In this article, we propose a new machine learning-based system for automated coding of student chats, which we labelled ConSent. The core of ConSent is an algorithm that uses contextual information and sentence encoding to produce a reliable estimation of chat message content (i.e. code). To optimize usability, ConSent was designed in such a way that it can cover various topics and various languages. To evaluate our approach, we used two sets of chats coming from different topics (within the domain of physics) and different languages (Dutch and Portuguese). We tested different algorithm configurations, including two multilingual sentence encoders, to find the model that yields the best reliability. As a result, analysis revealed that ConSent models can perform with substantial reliability levels and are able to transfer reliable coding of chats in a similar topic and different language. Finally, we discuss how ConSent can form the basis for a conversational agent, we explain the limitations of our approach, and we indicate possible paths for future work to contribute towards reliable and transferable models.

Multilingual information retrieval (MLIR) provides results that are more comprehensive than those of mono- and cross-lingual retrieval. Methods for MLIR are categorized as: (1) Fusion-based methods that merge results from multiple retrieval runs, and (2) Direct methods that build a unique index for the entire collection. Merging results of individual runs reduces the overall effectiveness, while more effective direct methods suffer from either time complexity and memory overhead, or over-weighting of index terms. In this paper, we propose a direct MLIR approach by using the language modeling framework that includes a novel multilingual language model estimation for documents, and a new way to globally estimate word statistics. These contributions enable ranking documents in multiple languages in one retrieval phase without having the problems of the previous direct methods. Moreover, our approach has the advantage of accommodating multilingual feedback information which helps to prevent query drift, and consequently to improve the performance. Finally, we effectively address the common case of incomplete coverage of translation resources in our proposed estimation methods. Experimental results show that the proposed approach outperforms the previous MLIR approaches. [ABSTRACT FROM AUTHOR]