LIIR at SemEval-2021 task 6: Detection of Persuasion Techniques In Texts and Images using CLIP features

Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 138–143 Bangkok, Thailand (online), August 5–6, 2021. ©2021 Association for Computational Linguistics 138 JCT at SemEval-2021 Task 1: Context-aware Representation for Lexical Complexity Prediction Chaya Liebeskind, Otniel Elkayam and Shmuel Liebeskind Department of Computer Science, Jerusalem College of Technology 21 Havaad Haleumi St., P.O.B. 16031 9116001 Jerusalem, Israel (liebchaya, otniel.elkayam, israellieb)@gmail.com Abstract In this paper, we present our contribution in SemEval-2021 Task 1: Lexical Complexity Prediction, where we integrate linguistic, sta- tistical, and semantic properties of the target word and its context as features within a Ma- chine Learning (ML) framework for predicting lexical complexity. In particular, we use BERT contextualized word embeddings to represent the semantic meaning of the target word and its context. We participated in the sub-task of pre- dicting the complexity score of single words. 1 Introduction Over the last decade, automated methods for de- tecting complex words have been developed. At the beginning, most of these methods assumed that lexical complexity is binary, words are either ”dif- ficult” or ”not difficult”. Thus, the first Complex Word Identification (CWI) shared task referred to binary identification of complex words (Zampieri et al., 2017). The main limitation of this assump- tion is that a word close to the decision boundary is considered to be as complex as one farther apart. Therefore, three years ago, the CWI included an additional probabilistic classification task where the participants were asked to give a probability of the given target word in particular context being complex (ˇStajner et al., 2018). Recently, CompLex, a new English corpus for lexical complexity prediction was introduced (Shardlow et al., 2020). The corpus is annotated using a 5-point Likert scale (1-5) (corresponding to very easy, easy, neutral, difficult, and very dif- ficult), and covers 3 genres: Bible translation, Eu- ropean Pariliament proceedings, and biomedical articles. SemEval-2021 (Task 1) shared task on Lexical Complexity Prediction (LCP) (Shardlow et al., 2021a,b) provided the participants with Com- plex and defined two sub-tasks: predicting the com- plexity score of single words, and predicting the complexity score of multi-word expressions. We present our system for the first sub-task of predicting the complexity score of single words. Our system incorporates linguistic, statistical, and semantic properties of the target word and its con- text as features within a Machine Learning (ML) framework for predicting lexical complexity. This paper is organized as follows: First, in Sec- tion 2, we describe features from previous works that we have adopted. Then, in Section 3, we de- scribe our feature sets, the feature selection process, and the results on the trial data. Finally, Our sys- tem results on the test data are detailed in Section 4, followed by conclusions in Section 5. 2 Related work In this section, we shortly describe linguistic, sta- tistical, and semantic features which were encoded as features in previous complexity prediction tasks and were integrated in our system. Linguistics features, such as Part-Of-Speech (POS) tag, dependency parsing relations, and syl- lable counts, as …

Content truncated to 500 words