SHIKEBLCU at SemEval-2020 Task 2: An External Knowledge-enhanced Matrix for Multilingual and Cross-Lingual Lexical Entailment

Proceedings of the 14th International Workshop on Semantic Evaluation, pages 255–262 Barcelona, Spain (Online), December 12, 2020. 255 SHIKEBLCU at SemEval-2020 Task 2: An External Knowledge-enhanced Matrix for Multilingual and Cross-Lingual Lexical Entailment Shike Wang, Yuchen Fan, Xiangying Luo, Dong Yu� ∗ Beijing Language and Culture University, Beijing, China {shikewang98,savannahfan98}@gmail.com xiangying luo@163.com yudong@blcu.edu.cn Abstract Lexical entailment recognition plays an important role in tasks like Question Answering and Machine Translation. As important branches of lexical entailment, predicting multilingual and cross-lingual lexical entailment (LE) are two subtasks of SemEval2020 Task2. In previous monolingual LE studies, researchers leverage external linguistic constraints to transform word embeddings for LE relation. In our system, we expand the number of external constraints in multiple languages to obtain more specialised multilingual word embeddings. For the cross-lingual subtask, we apply a bilingual word embeddings mapping method in the model. The mapping method takes specialised embeddings as inputs and is able to retain the embeddings’ LE features after operations. Our results for multilingual subtask are about 20% and 10% higher than the baseline in graded and binary prediction respectively. 1 Introduction Lexical entailment (LE) refers to the hyponymy-hypernymy relation, also known as TYPE-OF, or IS-A, which is a fundamental asymmetric lexical relation (Vuli´c et al., 2017). It is a basic requirement for tasks like Question Answering (QA) and Recognizing Textual Entailment (RTE). And more general reasoning over cross-lingual and multilingual LE relationships can improve language understanding in multilingual contexts (Upadhyay et al., 2018). Cross-lingual LE recognition is crucial to tasks such as recognizing cross-lingual textual entailment (Conneau et al., 2018) and machine translation (Pad´o et al., 2009). Predicting binary and graded scores for multilingual and cross-lingual lexical entailment is the task of SemEval 2020 Task 2 (Glavaˇs et al., 2020). There are two subtasks. Subtask A is to predict binary or graded LE on a monolingual pair of words, e.g., (building, construction) and the subtask is in six multiple languages (i.e., English, German, Italian, Croatian, Turkish, Albanian). Subtask B, predicting cross-lingual LE, gives a pair of words in two different languages with prefix, e.g., (en dinosaur, de kreatur1). There are 15 cross-lingual pairs as languages above combine with each other, i.e., DE-X, EN-X, IT-X, HR-X and SQ-X sets2. Each subtask includes both binary and graded prediction for a given pair of words. Binary prediction is to determine whether there is a LE relation between two concepts, while graded lexical entailment (GR-LE) measures the strength of LE relation on a continuous 0-6 scale (Vuli´c et al., 2017; Rei et al., 2018). For instance, (apple, fruit) gains a score of 6, while the pair (apple, flower) gets 1.2. This is because apple is more like a kind of fruit instead of flower. Since LE is an asymmetric relation, the score of (fruit, apple) is not the same as (apple, fruit). Researches in monolingual GR-LE mainly focus on training LE-specialiased word embeddings based on external linguistic constraints (Vuli´c and Mrkˇsi´c, 2018; Kamath et al., 2019; Glavaˇs and Vuli´c, 2019). The constraints, namely external …

Content truncated to 500 words