Sirwe Saeedi


2022

pdf bib
CS/NLP at SemEval-2022 Task 4: Effective Data Augmentation Methods for Patronizing Language Detection and Multi-label Classification with RoBERTa and GPT3
Daniel Saeedi | Sirwe Saeedi | Aliakbar Panahi | Alvis C.M. Fong
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)

This paper presents a combination of data augmentation methods to boost the performance of state-of-the-art transformer-based language models for Patronizing and Condescending Language (PCL) detection and multi-label PCL classification tasks. These tasks are inherently different from sentiment analysis because positive/negative hidden attitudes in the context will not necessarily be considered positive/negative for PCL tasks. The oblation study observes that the imbalance degree of PCL dataset is in the extreme range. This paper presents a modified version of the sentence paraphrasing deep learning model (PEGASUS) to tackle the limitation of maximum sequence length. The proposed algorithm has no specific maximum input length to paraphrase sequences. Our augmented underrepresented class of annotated data achieved competitive results among top-16 SemEval-2022 participants. This paper’s approaches rely on fine-tuning pretrained RoBERTa and GPT3 models such as Davinci and Curie engines with an extra-enriched PCL dataset. Furthermore, we discuss Few-Shot learning technique to overcome the limitation of low-resource NLP problems.

2020

pdf bib
CS-NLP Team at SemEval-2020 Task 4: Evaluation of State-of-the-art NLP Deep Learning Architectures on Commonsense Reasoning Task
Sirwe Saeedi | Aliakbar Panahi | Seyran Saeedi | Alvis C Fong
Proceedings of the Fourteenth Workshop on Semantic Evaluation

In this paper, we investigate a commonsense inference task that unifies natural language understanding and commonsense reasoning. We describe our attempt at SemEval-2020 Task 4 competition: Commonsense Validation and Explanation (ComVE) challenge. We discuss several state-of-the-art deep learning architectures for this challenge. Our system uses prepared labeled textual datasets that were manually curated for three different natural language inference subtasks. The goal of the first subtask is to test whether a model can distinguish between natural language statements that make sense and those that do not make sense. We compare the performance of several language models and fine-tuned classifiers. Then, we propose a method inspired by question/answering tasks to treat a classification problem as a multiple choice question task to boost the performance of our experimental results (96.06%), which is significantly better than the baseline. For the second subtask, which is to select the reason why a statement does not make sense, we stand within the first six teams (93.7%) among 27 participants with very competitive results. Our result for last subtask of generating reason against the nonsense statement shows many potentials for future researches as we applied the most powerful generative model of language (GPT-2) with 6.1732 BLEU score among first four teams. .