Natural Language Research Articles

ChatMol: Interactive Molecular Discovery with Natural Language.

Natural language is poised to become a key medium for human-machine interactions in the era of large language models. In the field of biochemistry, tasks such as property prediction and molecule mining are critically important yet technically challenging. Bridging molecular expressions in natural language and chemical language can significantly enhance the interpretability and ease of these tasks. Moreover, it can integrate chemical knowledge from various sources, leading to a deeper understanding of molecules. Recognizing these advantages, we introduce the concept of conversational molecular design, a novel task that utilizes natural language to describe and edit target molecules. To better accomplish this task, we develop ChatMol, a knowledgeable and versatile generative pre-trained model. This model is enhanced by incorporating experimental property information, molecular spatial knowledge, and the associations between natural and chemical languages. Several typical solutions including large language models (e.g., ChatGPT) are evaluated, proving the challenge of conversational molecular design and the effectiveness of our knowledge enhancement approach. Case observations and analysis offer insights and directions for further exploration of natural-language interaction in molecular discovery. Codes and data are provided in https://github.com/Ellenzzn/ChatMol/tree/main. Supplementary data are available online.

Protocol for Designing a Model to Predict the Likelihood of Psychosis From Electronic Health Records Using Natural Language Processing and Machine Learning.

Rapid identification of individuals developing a psychotic spectrum disorder (PSD) is crucial because untreated psychosis is associated with poor outcomes and decreased treatment response. Lack of recognition of early psychotic symptoms often delays diagnosis, further worsening these outcomes. The proposed study is a cross-sectional, retrospective analysis of electronic health record data including clinician documentation and patient-clinician secure messages for patients aged 15-29 years with ≥ 1 primary care encounter between 2017 and 2019 within 2 Kaiser Permanente regions. Patients with new-onset PSD will be distinguished from those without a diagnosis if they have ≥ 1 PSD diagnosis within 12 months following the primary care encounter. The prediction model will be trained using a trisourced natural language processing feature extraction design and validated both within each region separately and in a modified combined sample. This proposed model leverages the strengths of the large volume of patient-specific data from an integrated electronic health record with natural language processing to identify patients at elevated chance of developing a PSD. This project carries the potential to reduce the duration of untreated psychosis and thereby improve long-term patient outcomes.

Interactive Table Synthesis With Natural Language.

Tables are a ubiquitous data format for insight communication. However, transforming data into consumable tabular views remains a challenging and time-consuming task. To lower the barrier of such a task, research efforts have been devoted to developing interactive approaches for data transformation, but many approaches still presume that their users have considerable knowledge of various data transformation concepts and functions. In this study, we leverage natural language (NL) as the primary interaction modality to improve the accessibility of average users to performing complex data transformation and facilitate intuitive table generation and editing. Designing an NL-driven data transformation approach introduces two challenges: 1) NL-driven synthesis of interpretable pipelines and 2) incremental refinement of synthesized tables. To address these challenges, we present NL2Rigel, an interactive tool that assists users in synthesizing and improving tables from semi-structured text with NL instructions. Based on a large language model and prompting techniques, NL2Rigel can interpret the given NL instructions into a table synthesis pipeline corresponding to Rigel specifications, a declarative language for tabular data transformation. An intuitive interface is designed to visualize the synthesis pipeline and the generated tables, helping users understand the transformation process and refine the results efficiently with targeted NL instructions. The comprehensiveness of NL2Rigel is demonstrated with an example gallery, and we further confirmed NL2Rigel's usability with a comparative user study by showing that the task completion time with NL2Rigel is significantly shorter than that with the original version of Rigel with comparable completion rates.

Data Augmentation using Generative-AI

This study presents an approachable tool for data augmentation that makes use of artificial intelligence (AI). It can handle text and visual data, assisting customers in optimizing their data collecting for a range of applications. The system breaks down CSV documents providing insights using libraries such as transformers, which are used in the field of Natural Language Processing (NLP). It assesses the insights in addition to applying data augmentation techniques like word control and equivalent substitution. This method improves the text data by quickly balancing the final dataset. This study uses Generative III-disposed Organizations (GANs) to handle the images. Users can change settings like rotation, scale, and translation for a variety of high-quality images. This use case goes beyond simple growth and touches on the territory of artificial intelligence. With an emphasis on usability, the User Interface (UI) enables researchers to customize the processes according to their specific datasets.

A machine learning and natural language processing-based smishing detection model for mobile money transactions

A machine learning and natural language processing-based smishing detection model for mobile money transactions

Enhancing Indoor Navigation for Visually Impaired Individuals with anAI Chatbot Utilizing VEO Optimized Nodes and Natural LanguageProcessing

Aims and Background: Visually impaired people face numerous challenges when it comes to indoor navigation. While outdoor navigation benefits from advancements in GPS and related technologies, indoor spaces present intricate, complex, and often less accessible environments for those with visual impairments. Objective and Methodology: In response to these challenges, we propose an innovative approach to enhance indoor navigation for individuals with visual impairments, leveraging the power of an AI chatbot. Our AI chatbot employs cutting-edge artificial intelligence techniques to provide realtime assistance and guidance, facilitating independent navigation within intricate indoor settings. By harnessing natural language processing technologies, the chatbot engages in intuitive interactions with users, comprehending their queries and offering detailed instructions for efficient indoor navigation. The main goal of this research is to enhance the independence of people with visual impairments by offering them a reliable and easily accessible tool. Results and conclusion: This tool, driven by our Volcano Eruption Optimization Network, promises to significantly enhance the independence and overall indoor navigation experience for visually impaired people, ultimately fostering a greater sense of autonomy in navigating complex indoor spaces.

Performance Comparison of AI Platforms in Solving Computer Science Problems

In the rapidly evolving landscape of artificial intelligence (AI), its significance and accelerated development are undeniable. AI has emerged as a cornerstone technology with profound implications across various domains, driving innovation and reshaping the way we approach complex problems. Particularly, the utilization of AI in coding tasks has garnered substantial attention, given its potential to streamline development processes and enhance the efficiency of software engineering practices. Against this backdrop, this paper presents a detailed comparative analysis of four different AI platforms, namely ChatGPT, Gemini, Blackbox, and Microsoft Copilot, in addressing key challenges within the realm of computer science, spanning natural language processing, image processing, and cybersecurity. The study focuses on leveraging the C++ programming language to develop solutions for these multifaceted problems across the aforementioned platforms. Each platform's outputs are meticulously evaluated on various parameters including accuracy, execution time, code size, and time complexity to provide a comprehensive understanding of their performance. Furthermore, an iterative optimization methodology is employed, entailing three rounds of refinement for the code produced by each platform, with the resultant outputs subjected to comparative analysis in each iteration. Through this rigorous approach, the paper not only elucidates the efficacy of different AI platforms in addressing diverse computational challenges but also underscores the iterative enhancement process on AI platforms for refining code quality and performance across multiple domains within computer science.

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>

Enhancing emotion detection with synergistic combination of word embeddings and convolutional neural networks

Recognizing emotions in textual data is crucial in a wide range of natural language processing (NLP) applications, from consumer sentiment research to mental health evaluation. The word embedding techniques play a pivotal role in text processing. In this paper, the performance of several well-known word embedding methods is evaluated in the context of emotion recognition. The classification of emotions is further enhanced using a convolutional neural network (CNN) model because of its propensity to capture local patterns and its recent triumphs in text-related tasks. The integration of CNN with word embedding techniques introduced an additional layer to the landscape of emotion detection from text. The synergy between word embedding techniques and CNN harnesses the strengths of both approaches. CNNs extract local patterns and features from sequential data, making them well-suited for capturing relevant information within the embeddings. The results obtained with various embeddings highlight the significance of choosing synergistic combinations for optimum performance. The combination of CNNs and word embeddings proved a versatile and effective approach.

KnowledgeVIS: Interpreting Language Models by Comparing Fill-in-the-Blank Prompts.

Recent growth in the popularity of large language models has led to their increased usage for summarizing, predicting, and generating text, making it vital to help researchers and engineers understand how and why they work. We present KnowledgeVIS, a human-in-the-loop visual analytics system for interpreting language models using fill-in-the-blank sentences as prompts. By comparing predictions between sentences, KnowledgeVIS reveals learned associations that intuitively connect what language models learn during training to natural language tasks downstream, helping users create and test multiple prompt variations, analyze predicted words using a novel semantic clustering technique, and discover insights using interactive visualizations. Collectively, these visualizations help users identify the likelihood and uniqueness of individual predictions, compare sets of predictions between prompts, and summarize patterns and relationships between predictions across all prompts. We demonstrate the capabilities of KnowledgeVIS with feedback from six NLP experts as well as three different use cases: (1) probing biomedical knowledge in two domain-adapted models; and (2) evaluating harmful identity stereotypes and (3) discovering facts and relationships between three general-purpose models.

Exploring RoBERTa model for cross-domain suggestion detection in online reviews

Detecting suggestions in online review requires contextual understanding of review text, which is an important real-world application of natural language processing. Given the disparate text domains found in product reviews, a common strategy involves fine-tuning bidirectional encoder representations from transformers (BERT) models using reviews from various domains. However, there hasn't been an empirical examination of how BERT models behave across different domains in tasks related to detecting suggestion sentences from online reviews. In this study, we explore BERT models for suggestion classification that have been fine-tuned using single-domain and cross-domain Amazon review datasets. Our results indicate that while single-domain models achieved slightly better performance within their respective domains compared to cross-domain models, the latter outperformed single-domain models when evaluated on cross-domain data. This was also observed for single-domain data not used for fine-tuning the single-domain model and on average across all tests. Although fine-tuning single-domain models can lead to minor accuracy improvements, employing multi-domain models that perform well across domains can help in cold start problems and reduce annotation costs.

A Semantic and Motion-Aware Spatiotemporal Transformer Network for Action Detection.

This paper presents a novel spatiotemporal transformer network that introduces several original components to detect actions in untrimmed videos. First, the multi-feature selective semantic attention model calculates the correlations between spatial and motion features to model spatiotemporal interactions between different action semantics properly. Second, the motion-aware network encodes the locations of action semantics in video frames utilizing the motion-aware 2D positional encoding algorithm. Such a motion-aware mechanism memorizes the dynamic spatiotemporal variations in action frames that current methods cannot exploit. Third, the sequence-based temporal attention model captures the heterogeneous temporal dependencies in action frames. In contrast to standard temporal attention used in natural language processing, primarily aimed at finding similarities between linguistic words, the proposed sequence-based temporal attention is designed to determine both the differences and similarities between video frames that jointly define the meaning of actions. The proposed approach outperforms the state-of-the-art solutions on four spatiotemporal action datasets: AVA 2.2, AVA 2.1, UCF101-24, and EPIC-Kitchens.

BERT-based models for classifying multi-dialect Arabic texts

<p><a name="_Hlk133997549"></a><a name="_Hlk127607325"></a><span lang="EN-US">The area of natural language processing (NLP) is presently a rapidly developing field characterized by innovation and research. Despite this progress, several </span><a name="_Hlk148089340"></a><span lang="EN-US">dialects of Arabic</span><span><span lang="EN-US"> (DA) are classified as low-resource languages, making it challenging for NLP systems to process DA data. One approach to address this issue is to train NLP models on social media data sets containing DA texts. </span><span lang="IN">Therefore, these open-access social media datasets, as outlined in our paper, can serve as a valuable resource for developers and researchers involved in the processing of DA.</span><span lang="EN-US">To create our multilingual corpus, we gathered data from various datasets containing different versions of DA. These datasets will be used to classify texts in terms of sentiment classification, topic classification, and dialect identification. Our study contributes to the automated analysis of the classification of Arabic dialects. We aim to investigate and assess various machine learning and deep learning techniques, with a specific focus on utilizing the BERT model. </span><span lang="EN-US">The results of our experiments on our datasets show that DarijaBERT and DziriBERT trained on a similar DA outperform traditional machine learning methods and previous more general pre-trained models that were trained on multiple dialects or languages.</span></span></p>

Insights of learning approach towards determination of potentially objectional communication in social networking

<p><span lang="EN-US">Over the last decade, sentiment analysis has evolved significantly towards extracting the contextual knowledge associated with the communication exchanged in social networks. Irrespective of various approaches to natural language processing and constantly evolving machine learning, sentiment analysis has inherent shortcomings, which further act as an obstacle to determining hateful and offensive speech exchanged in social networks. Therefore, this paper offers a compact yet granular insight into the effectiveness of existing sentiment analysis approaches used distinctly for determining hateful and offensive speech with particular emphasis on machine learning-based methodologies. The paper further contributes towards research trend analysis followed by distinct highlights of the research gap. The paper offers a learning outcome that significantly benefits future researchers investigating the same field.</span></p>

Language awareness: On the semiotics of talk and text

The article argues for a necessity to increase human awareness of language as functional biological behavior rather than simply a tool in the service of communication, by emphasizing the difference between talk and text as ontologically different semiotic phenomena characteristic of the human cognitive domain. The established tradition to view written words as linguistic signs leads the studies of natural language astray, effectively hiding its nature as biologically functional orientational behavior in a consensual domain that evolved with the evolution of our species and was not a cultural invention. Because of the identification of text with talk in linguistic semiotics, the empirical validity of the core semiotic concept of natural linguistic sign, based on the so-called semiotic triangle, is undermined. While talk is a dynamic fact of nature, text is a static artifact; it is argued, therefore, that the analytical approach to linguistic signs as objects in the world is inadequate, and the notions of first- and second-order semiotics are introduced. It is concluded that awareness of the cognitive-semiotic difference between talk and text and their respective roles in the evolution of humans may facilitate further research into the nature and origin of humanness.

Enhancing the English natural language processing dictionary using natural language processing++

<p><span lang="EN-US">Every natural language-based project requires the use of an English dictionary. But the current English dictionaries are not updated as the English language is constantly evolving. The English dictionary used for natural language processing (NLP) projects needs to be enhanced by adding more words and phrases. This helps in improving the accuracy of NLP applications such as machine translation, performance of text analysis, recognition, and part of speech (POS) tagging. Several approaches are proposed in this direction, this paper develops and demonstrates enhancement of the English dictionary using a more versatile and robust programming language known as NLP++, a plugin to distributed big data analytics platforms such as HPCC systems. The unique features of NLP++ language is the enabler for realization of the proposed approach. This paper also discusses key NLP techniques, dictionary refinements analysis using NLP and NLP++. The results show that the proposed approach using NLP++ has significantly improved the accuracy and comprehensiveness of the English dictionary.</span></p>

Comparing logistic regression and extreme gradient boosting on student arguments

<p>Identifying the effectiveness level and quality of students' arguments poses a challenge for teachers. This is due to the lack of techniques that can accurately assist in identifying the effectiveness and quality of students' arguments. This research aims to develop a model that can identify effectiveness categories in students' arguments. The method employed involves the logistic regression+XGBoost algorithm combined with separate implementations of term frequency-inverse document frequency (TF-IDF) and CountVectorizer. Student argument data were collected and processed using natural language processing techniques. The research results indicate that TF-IDF outperforms in identifying effectiveness classes in student arguments with an accuracy of 66.20%. The multi-output classification yielded an accuracy of 89.32% in the initial testing, which further improved to 92.34% after implementing one-hot encoding. A novel finding in this research is the superiority of TF-IDF as a technique for identifying effectiveness classes in student arguments compared to CountVectorizer. The implications of this research include the development of a model that can assist teachers in identifying the effectiveness level of students' arguments, thereby improving the quality of learning and enhancing students' argumentative competence.</p>

Combining hierarchies for spatial reasoning of hierarchical relations among places in different contexts

Spatial reasoning of hierarchical relations is an important research topic in geographic information science. Existing literature focuses mainly on hierarchical relations according to ordered containment of point sets based on the 9-Intersection Model (9IM). However, in natural language descriptions, hierarchical relations expressed by prepositions such as in can have spatial configurations conflicting with those hierarchical relations based on 9IM. This paper proposes an algorithm employing combined hierarchies to infer hierarchical relations among places in different contexts. Two graph databases containing combined hierarchies conforming to administrative reach and geometric enclosure are established with places represented by polygons with misaligned boundaries on prototypical and real data. The 13170 pairs of conflicting hierarchical relations with the same start nodes but different end nodes detected in the combined hierarchies on real data validate the proposed algorithm for spatial reasoning of hierarchical relations in different contexts. This research facilitates consistent spatial reasoning of hierarchical relations in different contexts for spatial information retrieval and question answering.

Automatic detection of safety requests in web and mobile applications using natural language processing techniques

<p class="p1">Web and mobile applications have become an essential part of our daily lives. However, as the usage of these applications increases, so does the potential for safety concerns. It is crucial for application developers to ensure that their applications are safe and secure for users. One way to achieve this is through the identification and processing of safety requests made by users. This research paper proposes a method for identifying safety requests made by users in web and mobile applications using natural language processing (NLP) and deep learning techniques. The approach involves training a machine learning and deep learning model on a dataset of user requests to identify and classify safety requests. The models are then integrated into the application’s code to automatically detect and respond to safety requests. A case study on a ride-sharing application showed that the proposed approach achieved high accuracy in identifying safety requests, with an F1 score of 0.85. The proposed method can be applied to vari- ous web and mobile applications to improve safety and security, and reduce the workload of manual safety request processing.</p>

Reviewing approaches employed in Arabic chatbots

<p>The field of chatbots has witnessed a remarkable evolution in recent years, marked by a transition from simplistic rule-based structures to sophisticated systems employing advanced natural language processing (NLP) techniques. While most languages benefit from NLP support, the majority of chatbot research and development has been conducted in English, leaving a notable scarcity of comparable works in Arabic. This scarcity is attributed to the myriad challenges posed by the linguistically intricate nature of Arabic, encompassing orthographic variations and diverse dialects. This study systematically reviews articles that represent implementations of Arabic chatbots, revealing a discernible shift from rule-based frameworks to the predominant adoption of machine learning (ML) and deep learning (DL) methods. The results highlight the dynamic trajectory of chatbot technology, with a notable emphasis on the pivotal role of DL, as evidenced by a significant peak in 2023. Looking forward, the study anticipates a more sophisticated future for chatbot development, driven by ongoing advancements in artificial intelligence (AI) and NLP, offering valuable insights into the current state of Arabic chatbot research and laying the foundation for continued exploration in this evolving and dynamic field.</p>