Semantic similarity prediction is better than other semantic similarity measures
Semantic similarity between natural language texts is typically measured either by looking at the overlap between subsequences (e.g., BLEU) or by using embeddings (e.g., BERTScore, S-BERT). Within this paper, we argue that when we are only interested in measuring the semantic similarity, it is better to directly predict the similarity using a fine-tuned model for such a task. Using a fine-tuned model for the Semantic Textual Similarity Benchmark tasks (STS-B) from the GLUE benchmark, we define the STSScore approach and show that the resulting similarity is better aligned with our expectations on a robust semantic similarity measure than other approaches.
Code (1)
Tasks
Semantic SimilaritySemantic Textual SimilaritySTSSTS-BSimilar Papers 제목 키워드 기반
SimMatch: Semi-supervised Learning with Similarity Matching
Learning with few labeled data has been a longstanding problem in the computer vision and machine learning research community. In this paper, we introduced a new semi-supervised learning framework, SimMatch, which simult…
Semantic SimilaritySemantic Textual SimilaritySemi-Supervised Image ClassificationImage Similarity using An Ensemble of Context-Sensitive Models
Image similarity has been extensively studied in computer vision. In recent years, machine-learned models have shown their ability to encode more semantics than traditional multivariate metrics. However, in labelling sem…
Dimensionality ReductionSemantic SimilaritySemantic Textual SimilarityLanguage-Independent Tokenisation Rivals Language-Specific Tokenisation for Word Similarity Prediction
Language-independent tokenisation (LIT) methods that do not require labelled language resources or lexicons have recently gained popularity because of their applicability in resource-poor languages. Moreover, they compac…
Semantic SimilaritySemantic Textual SimilarityvalidWord Embeddings+1Multi-Source Soft Pseudo-Label Learning with Domain Similarity-based Weighting for Semantic Segmentation
This paper describes a method of domain adaptive training for semantic segmentation using multiple source datasets that are not necessarily relevant to the target dataset. We propose a soft pseudo-label generation method…
Domain AdaptationPseudo LabelSemantic SegmentationSemantic Answer Similarity for Evaluating Question Answering Models
The evaluation of question answering models compares ground-truth annotations with model predictions. However, as of today, this comparison is mostly lexical-based and therefore misses out on answers that have no lexical…
Question AnsweringSemantic SimilaritySemantic Textual Similarity