A Sentiwordnet Strategy for Curriculum Learning in Sentiment Analysis

Abstract

Curriculum Learning (CL) is the idea that learning on a training set sequenced or ordered in a manner where samples range from easy to difficult, results in an increment in performance over otherwise random ordering. The idea parallels cognitive science's theory of how human brains learn, and that learning a difficult task can be made easier by phrasing it as a sequence of easy to difficult tasks. This idea has gained a lot of traction in machine learning and image processing for a while and recently in Natural Language Processing (NLP). In this paper, we apply the ideas of curriculum learning, driven by SentiWordNet in a sentiment analysis setting. In this setting, given a text segment, our aim is to extract its sentiment or polarity. SentiWordNet is a lexical resource with sentiment polarity annotations. By comparing performance with other curriculum strategies and with no curriculum, the effectiveness of the proposed strategy is presented. Convolutional, Recurrence and Attention based architectures are employed to assess this improvement. The models are evaluated on standard sentiment dataset, Stanford Sentiment Treebank.

Assessing the impact of minor modifications on the interior structure of GRU: GRU1 and GRU2

“…It is commonly used in computer vision, that is, classification tasks, NLP, that is, neural machine translation (NMT), sentiment classification, and so forth. Systems using curriculum learning operate faster and yield better performances than unstructured, random sampling examples 25‐27 …”

“…Systems using curriculum learning operate faster and yield better performances than unstructured, random sampling examples. [25][26][27] In this section, the experiments are conducted on the synthetically produced dataset mentioned above. The first step is how to determine the difficulty level of the samples.…”

Curricular Next Conversation Prediction Pretraining for Transcript Segmentation

“…We give two major reasons for this improvement -First, our ordering of pretraining samples in Curricular NCP is relevant to the segmentation task. Prior research in curriculum learning show such sample orderings are more effective than arbitrary sample orderings such as sentence length for sentiment analysis (Rao et al, 2020). Second, the transcript segmentation data is small in size and previous works note the efficacy of curriculum learning in resource poor settings (Cirik et al, 2016;Nagatsuka et al, 2021).…”

Active Curriculum Learning

“…CL algorithm is presented in Algorithm 2. CL has been investigated in computer vision (Gui, Baltrusaitis, and Morency 2017), Natural Language Processing (NLP) (Rao, Anuranjana, and Mamidi 2020), and speech recognition (Braun, Neil, and Liu 2016) among others (Soviany et al 2021). Specifically within NLP, CL has been used on tasks such as question answering (Sachan and Xing 2016), natural language understanding (Xu et al 2020), as well as learning word representations (Tsvetkov et al 2016).…”