Yuan Ma


pdf bib
Improving Text Simplification with Factuality Error Detection
Yuan Ma | Sandaru Seneviratne | Elena Daskalaki
Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022)

In the past few years, the field of text simplification has been dominated by supervised learning approaches thanks to the appearance of large parallel datasets such as Wikilarge and Newsela. However, these datasets suffer from sentence pairs with factuality errors which compromise the models’ performance. So, we proposed a model-independent factuality error detection mechanism, considering bad simplification and bad alignment, to refine the Wikilarge dataset through reducing the weight of these samples during training. We demonstrated that this approach improved the performance of the state-of-the-art text simplification model TST5 by an FKGL reduction of 0.33 and 0.29 on the TurkCorpus and ASSET testing datasets respectively. Our study illustrates the impact of erroneous samples in TS datasets and highlights the need for automatic methods to improve their quality.


pdf bib
Multi-lingual Argumentative Corpora in English, Turkish, Greek, Albanian, Croatian, Serbian, Macedonian, Bulgarian, Romanian and Arabic
Alfred Sliwa | Yuan Ma | Ruishen Liu | Niravkumar Borad | Seyedeh Ziyaei | Mina Ghobadi | Firas Sabbah | Ahmet Aker
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)


pdf bib
What works and what does not: Classifier and feature analysis for argument mining
Ahmet Aker | Alfred Sliwa | Yuan Ma | Ruishen Lui | Niravkumar Borad | Seyedeh Ziyaei | Mina Ghobadi
Proceedings of the 4th Workshop on Argument Mining

This paper offers a comparative analysis of the performance of different supervised machine learning methods and feature sets on argument mining tasks. Specifically, we address the tasks of extracting argumentative segments from texts and predicting the structure between those segments. Eight classifiers and different combinations of six feature types reported in previous work are evaluated. The results indicate that overall best performing features are the structural ones. Although the performance of classifiers varies depending on the feature combinations and corpora used for training and testing, Random Forest seems to be among the best performing classifiers. These results build a basis for further development of argument mining techniques and can guide an implementation of argument mining into different applications such as argument based search.