Usporedite metode

	Objašnjivi ugrađeni prikazi rečenica	Ugrađivanje rečenica
Područje	Duboko učenje	Duboko učenje
Obitelj	Machine learning	Machine learning
Godina nastanka	2016–2018	2015–2019
Tvorac	Conneau et al.; Ribeiro et al. (probing + LIME frameworks)	Kiros et al. (Skip-Thought, 2015); Reimers & Gurevych (Sentence-BERT, 2019)
Vrsta	Post-hoc interpretability applied to sentence encoders	Representation learning / embedding
Temeljni izvor	Conneau, A., Kruszewski, G., Lample, G., Barrault, L., & Baroni, M. (2018). What you can cram into a single $\vec{v}$ector: Probing sentence embeddings for linguistic properties. In Proceedings of ACL 2018, pp. 2126–2136.	Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP), 3980–3990.
Drugi nazivi	interpretable sentence representations, XAI sentence embeddings, probing sentence embeddings, explainable sentence vectors	sentence vectors, sentence representations, SBERT, semantic sentence encoding
Srodne	6	4
Sažetak	Explainable sentence embeddings combine dense sentence representation learning with post-hoc or intrinsic interpretability tools — such as probing classifiers, LIME, SHAP, or attention attribution — to reveal what linguistic and semantic information is encoded in a sentence vector and why a downstream model makes a given prediction. The goal is to retain the representational power of modern encoders while making their behavior auditable.	Sentence Embeddings convert a sentence or short text into a single fixed-length dense vector that captures its semantic meaning. These vectors allow downstream tasks — semantic similarity, clustering, retrieval, and classification — to operate on numerical representations instead of raw text, making them one of the most versatile building blocks in modern NLP pipelines.