Unsupervised Sentence Textual Similarity with Compositional Phrase Semantics
This work addresses the problem of efficient and domain-agnostic STS for NLP applications, offering a faster and more effective method, though it is incremental as it builds on prior formulations like optimal transport.
The paper tackles unsupervised sentence textual similarity (STS) by proposing a Recursive Optimal Transport Similarity (ROTS) algorithm that captures compositional phrase semantics, showing clear advantages in effectiveness and scalability over existing approaches across 29 STS tasks.
Measuring Sentence Textual Similarity (STS) is a classic task that can be applied to many downstream NLP applications such as text generation and retrieval. In this paper, we focus on unsupervised STS that works on various domains but only requires minimal data and computational resources. Theoretically, we propose a light-weighted Expectation-Correction (EC) formulation for STS computation. EC formulation unifies unsupervised STS approaches including the cosine similarity of Additively Composed (AC) sentence embeddings, Optimal Transport (OT), and Tree Kernels (TK). Moreover, we propose the Recursive Optimal Transport Similarity (ROTS) algorithm to capture the compositional phrase semantics by composing multiple recursive EC formulations. ROTS finishes in linear time and is faster than its predecessors. ROTS is empirically more effective and scalable than previous approaches. Extensive experiments on 29 STS tasks under various settings show the clear advantage of ROTS over existing approaches. Detailed ablation studies demonstrate the effectiveness of our approaches.