Neural machine translation (NMT) is a software that uses neural network techniques to translate text from one language to another. However, one of the most famous NMT models—Google Translate—failed to give an accurate English translation of a famous Korean nursery rhyme, "Airplane" (비행기). The authors fine-tuned a pre-trained model first with a dataset from the lyrics domain, and then with a smaller dataset containing the rhythmical properties, to teach the model to translate rhythmically accurate lyrics. This stacked fine-tuning method resulted in an NMT model that could maintain the rhythmical characteristics of lyrics during translation while single fine-tuned models failed to do so.
Although there has been great progress in the field of Natural language processing (NLP) over the last few years, particularly with the development of attention-based models, less research has contributed towards modeling keystroke log data. State of the art methods handle textual data directly and while this has produced excellent results, the time complexity and resource usage are quite high for such methods. Additionally, these methods fail to incorporate the actual writing process when assessing text and instead solely focus on the content. Therefore, we proposed a framework for modeling textual data using keystroke-based features. Such methods pay attention to how a document or response was written, rather than the final text that was produced. These features are vastly different from the kind of features extracted from raw text but reveal information that is otherwise hidden. We hypothesized that pairing efficient machine learning techniques with keystroke log information should produce results comparable to transformer techniques, models which pay more or less attention to the different components of a text sequence in a far quicker time. Transformer-based methods dominate the field of NLP currently due to the strong understanding they display of natural language. We showed that models trained on keystroke log data are capable of effectively evaluating the quality of writing and do it in a significantly shorter amount of time compared to traditional methods. This is significant as it provides a necessary fast and cheap alternative to increasingly larger and slower LLMs.
The authors looked at the ability of machine learning algorithms to interpret language given their increasing use in moderating content on social media. Using an explainable model they were able to achieve 81% accuracy in detecting fake vs. real news based on language of posts alone.
Studying exoplanets, or planets that orbit a star other than the Sun, is critical to a greater understanding the formation of planets and how Earth's solar system differs from others. In this study the authors analyze the transit light curves of three hot Jupiter exoplanets to ultimately determine if and how these planets have changed since their discovery.
Depression affects millions globally, yet identifying symptoms remains challenging. This study explored detecting depression-related patterns in social media texts using natural language processing and machine learning algorithms, including decision trees and random forests. Our findings suggest that analyzing online text activity can serve as a viable method for screening mental disorders, potentially improving diagnosis accuracy by incorporating both physical and psychological indicators.
This study explored whether planaria, known for their regenerative abilities, can retain learned memories after regeneration and how stressors like alcohol affect memory.
The authors develop a new method for training machine learning algorithms to differentiate between hate speech and cultural speech in online platforms.
The goal of this study was to further confirm, characterize, and classify LHS 3844 b, an exoplanet detected by the Transiting Exoplanet Survey Satellite (TESS). Additionally, we strove to determine the likeliness of LHS 3844 b and similar planets as qualified candidates for observation with the James Webb Space Telescope (JWST).
