Papers › ConCSE: Unified Contrastive Learning and Augmentation for Code-Switched Embeddings

ConCSE: Unified Contrastive Learning and Augmentation for Code-Switched Embeddings

28 Aug 2024arXiv:2409.00120archive 2025-07-28

Jangyeong Jeon, Sangyeon Cho, Minuk Ma, Junyoung Kim

This paper examines the Code-Switching (CS) phenomenon where two languages intertwine within a single utterance. There exists a noticeable need for research on the CS between English and Korean. We highlight that the current Equivalence Constraint (EC) theory for CS in other languages may only partially capture English-Korean CS complexities due to the intrinsic grammatical differences between the languages. We introduce a novel Koglish dataset tailored for English-Korean CS scenarios to mitigate such challenges. First, we constructed the Koglish-GLUE dataset to demonstrate the importance and need for CS datasets in various tasks. We found the differential outcomes of various foundation multilingual language models when trained on a monolingual versus a CS dataset. Motivated by this, we hypothesized that SimCSE, which has shown strengths in monolingual sentence embedding, would have limitations in CS scenarios. We construct a novel Koglish-NLI (Natural Language Inference) dataset using a CS augmentation-based approach to verify this. From this CS-augmented dataset Koglish-NLI, we propose a unified contrastive learning and augmentation method for code-switched embeddings, ConCSE, highlighting the semantics of CS sentences. Experimental results validate the proposed ConCSE with an average performance enhancement of 1.77\% on the Koglish-STS(Semantic Textual Similarity) tasks.

PaperPDFCode

Code

jjy961228/ConCSE officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive LearningNatural Language InferenceSTSSemantic Textual SimilaritySentenceSentence EmbeddingSentence-Embedding

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Contrastive LearningSimCSE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections