We present the AWARE-TEXT package, an open-sourcesoftware package for collecting textual data on Android mobile devices. This package allows for collecting short message service (SMS or text messages) and character-l...
详细信息
The rise of ChatGPT1 has led to the development of artificial intelligence (AI) applications, particularly those that rely on large language models (LLMs). However, recalling LLM APIs can be expensive, and the respons...
详细信息
language model applications are becoming increasingly popular and complex, often including features like tool usage and retrieval augmentation. However, existing frameworks for such applications are often opinionated,...
详细信息
Knowledge extraction from scientific literature is a major issue, crucial to promoting transparency, reproducibility, and innovation in the research community. In this work, we present a novel approach towards the ide...
详细信息
This paper proposes a voice-controlled robotic system that uses Bluetooth to follow human commands. The voice commands are given to an android app built using MIT App Inventor. These commands are then sent to the Blue...
详细信息
This paper proposes a voice-controlled robotic system that uses Bluetooth to follow human commands. The voice commands are given to an android app built using MIT App Inventor. These commands are then sent to the Bluetooth module which then sends them to the controller interfaced with it. This interfacing was done using Universal Asynchronous Receiver-Transmitter (UART) Protocol. After processing the commands, the microcontroller controls the movement of the robot in different directions. An open-source hardware and software is used in the proposed research work. Further, the proposed model can be implemented by almost every student for educational and understanding purposes as it is both economical and easy-to-use. This study considers the domain of naturallanguageprocessing (nlp) as well as communication using Bluetooth, both of which have high possibilities in future based on the technological advancement.
Program comprehension usually focuses on the significance of textual information to capture the programmers' intent and knowledge in the software, in particular the source code. In the source code, most of the dat...
详细信息
ISBN:
(纸本)9781450329651
Program comprehension usually focuses on the significance of textual information to capture the programmers' intent and knowledge in the software, in particular the source code. In the source code, most of the data is unstructured data, such as the naturallanguage text in comments and identifier names. Researchers in software engineering community have developed many techniques for handling such unstructured data, such as naturallanguageprocessing (nlp) and information retrieval (IR). Before using the IR technique on the unstructured source code, we must preprocess the source code since these data is different from that used in our daily life. During this process, several operations, i.e, tokenization, splitting, stemming, etc., are usually used. These preprocessing operations will affect the quality of the data used in the IR process. But how these preprocessing operations affect the results of IR is still an open problem. To the best of our knowledge, there are still no studies focusing on this problem. This paper attempts to fill this gap, and conducts some empirical studies to show what are the differences before and after these preprocessing operations. The empirical results show some interesting phenomena based on using or not using these preprocessing operations.
This paper discusses an opensource project1 which provides a framework for working with Indian language scripts using a uniform syllable based text encoding scheme. It also discusses the design and implementation of ...
详细信息
暂无评论