Кросс-языковое СТС
task
ID: crosslingualsts
Related Papers
Extending Monolingual Semantic Textual Similarity Task to Multiple Cross-lingual Settings
AbstractThis paper describes our independent effort for extending the monolingual semantic textual similarity (STS) task setting to multiple cross-lingual settings involving English, Japanese, and Chinese. So far, we have adopted …...
Fully Unsupervised Crosslingual Semantic Textual Similarity Metric Based on BERT for Identifying Parallel Data
AbstractWe present a fully unsupervised crosslingual semantic textual similarity (STS) metric, based on contextual embeddings extracted from BERT – Bidirectional Encoder Representations from Transformers (Devlin et al., 2019). The goal …...
Evaluation Datasets for Cross-lingual Semantic Textual Similarity
AbstractSemantic textual similarity (STS) systems estimate the degree of the meaning similarity between two sentences. Cross-lingual STS systems estimate the degree of the meaning similarity between two sentences, each in …...