将神经句子编码器用于跨域主题细分进行比较:这不是你典型的文本相似性任务
Iacopo Ghinassi1, Lin Wang1, Chris Newell2
1School of Electronic Engineering and Computer Science, Queen Mary University of London, London, United Kingdom.
PeerJ. Computer science
|December 11, 2023
概括
神经句子编码器 (NSEs) 在主题细分方面表现出不同的成功. 性能取决于文本域和编码器类型,并引入了一个新的指标ARP来评估词汇凝聚力.
科学领域:
- 自然语言处理自然语言处理.
- 计算语言学 计算语言学
- 机器学习 机器学习
背景情况:
- 神经句子编码器 (NSEs) 在NLP任务中被广泛使用.
- 它们在话题细分方面的有效性尚未被系统地比较.
- 现有的研究表明,NSEs的整体绩效增长.
研究的目的:
- 系统地比较各种NSE在主题细分方面的表现.
- 调查影响不同数据集和领域NSE表现的因素.
- 引入一个新的指标 (ARP) 来评估话题细分中的词汇凝聚力.
主要方法:
- 基于NSE的监督和无监督主题细分模型的比较.
- 评估现有和新型的NSE,并制定一个特设的预培训策略.
- 引入和应用ARP指标来分析词汇凝聚力.
主要成果:
- NSE通常会比基线提高话题细分,但不是普遍的 (例如,新闻节目).
- 基于变压器的编码器显示了改进,但微调并不能保证更好的话题细分性能.
- 性能在NSEs,数据集和应用领域之间有很大的差异.
结论:
- 话题细分的成功不仅仅取决于词汇凝聚力建模;它因文本类型而异.
- 传统的句子编码器在对话数据中的话题凝聚力方面扎.
- 该研究促进了对NSE在主题细分方面的理解,并为词汇凝聚分析引入了一种多功能度量.
相关概念视频
Neural Circuits
1.3K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
1.3K
Neural Regulation
39.5K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
39.5K
Encoding
174
Information enters the brain through encoding, which is the input of information into the memory system. Once sensory information is received from the environment, the brain labels or codes it. The information is then organized with similar information and connected to existing concepts. Encoding occurs through automatic processing and effortful processing.
Automatic processing involves the encoding of details like time, space, frequency, and the meaning of words, usually done without conscious...
Automatic processing involves the encoding of details like time, space, frequency, and the meaning of words, usually done without conscious...
174
Motor and Sensory Areas of the Cortex
3.9K
The cerebral cortex, the brain's outermost layer, is pivotal in processing complex cognitive tasks, emotions, and various sensory inputs and executing voluntary motor activities. This intricate structure is divided into three primary functional areas: the motor areas, sensory areas, and association areas.
Motor Areas
The motor areas located in the frontal lobe are central to controlling voluntary movements. This region is further subdivided into the primary motor cortex and the premotor cortex....
Motor Areas
The motor areas located in the frontal lobe are central to controlling voluntary movements. This region is further subdivided into the primary motor cortex and the premotor cortex....
3.9K
Neurons as Communicators of the Brain
1.2K
Neurons, the fundamental units of the brain and nervous system, function as the primary transmitters of information throughout the body. Their ability to communicate through electrical and chemical signals is vital for every bodily function, from regulating the heartbeat to processing complex thoughts. Each neuron has three main components: the cell body (soma), dendrites, and an axon, each specialized to facilitate swift and efficient neural communication.
Cell Body
The cell body, also known...
Cell Body
The cell body, also known...
1.2K
Classification of Signals
471
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
471


