普什图诗歌世代:为低资源语言使用预训练的转换器进行深度学习
Imran Ullah1, Khalil Ullah1, Hamad Khan1
1Software Engineering, University of Malakand, Chakdara, Pakistan.
PeerJ. Computer science
|September 24, 2024
概括
这项研究使用先进的变压器模型来产生高质量的普什图诗歌. 机器学习方法取得的结果与人类创建的普什图语诗歌相当.
科学领域:
- 计算语言学 计算语言学
- 自然语言处理自然语言处理.
- 人工智能的人工智能
背景情况:
- 使用机器学习生成诗歌是一个复杂的研究领域.
- 普什托语诗歌的产生带来了独特的语言挑战.
- 变压器模型为文本生成提供了高级功能.
研究的目的:
- 开发和评估一种新的方法来产生高质量的普什图诗歌.
- 为了利用预先训练的变压器模型来完成巴什托语任务.
- 评估与人类标准相比,机器生成的普什图语诗歌的质量.
主要方法:
- 使用了两个预先训练的变压器模型:LaMini-Cerebras-590M和bloomz-560m.
- 在一个新的,广泛的帕什托诗歌数据集上训练模型.
- 使用种子文本提示诗歌生成.
- 进行主观和客观评估,包括人类评估.
主要成果:
- 提出的方法成功地产生了巴什图诗歌.
- 实验结果表明,生成的诗歌质量与人类生成的诗歌质量相当.
- 证明了变压器模型对普什图诗歌的产生效果.
结论:
- 该研究对普什图语语言和诗歌的产生做出了重大贡献.
- 开发的方法显示了在自然语言处理和计算语言学中的应用潜力.
- 机器学习模型可以产生出色质量的巴什图诗歌.
相关概念视频
Non-equilibrium in the Cell
4.3K
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
4.3K
Generation of Three-Phase Voltage
363
A three-phase AC generator has a rotor with a rotating magnet placed within the stator mounted with the stationary three-phase winding to generate three-phase voltages via mutual induction. These windings are evenly distributed around the inner circumference of the stator and are arranged 120 electrical degrees apart. Three-phase stator windings consist of three separate coils or groups of coils, known as phases, each connected in Y (star) configuration or Delta configuration.
As the rotor...
As the rotor...
363
Source Transformation
3.9K
Source transformation is a fundamental technique employed in circuit analysis, offering a valuable tool for simplifying complex electrical circuits. This technique involves the replacement of either a voltage source in series with a resistor by a current source in parallel with a resistor, or vice versa. The key concept here is that when the original sources are deactivated (turned off), the equivalent resistance at the circuit's end terminals remains the same.
It is essential to note that when...
It is essential to note that when...
3.9K
Improving Translational Accuracy
2.5K
2.5K
Translation
14.7K
Translation is the process of synthesizing proteins from the genetic information carried by messenger RNA (mRNA). Following transcription, it constitutes the final step in the expression of genes. This process is carried out by ribosomes, complexes of protein and specialized RNA molecules. Ribosomes, transfer RNA (tRNA), and other proteins produce a chain of amino acids—the polypeptide—as the end product of translation.
Translation Produces the Building Blocks of Life
Proteins are...
Translation Produces the Building Blocks of Life
Proteins are...
14.7K
Downsampling
135
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
135


