CLAIJul 10, 2012

Challenges for Distributional Compositional Semantics

arXiv:1207.2265v11 citations
Originality Synthesis-oriented
AI Analysis

It addresses theoretical and practical challenges in natural language processing for researchers, but is incremental as it reviews existing work and outlines future directions.

The paper summarizes the state-of-the-art in distributional compositional semantics, identifying challenges such as generalised quantifiers and intensional semantics, and proposes focusing on tasks like textual entailment and machine translation for evaluation.

This paper summarises the current state-of-the art in the study of compositionality in distributional semantics, and major challenges for this area. We single out generalised quantifiers and intensional semantics as areas on which to focus attention for the development of the theory. Once suitable theories have been developed, algorithms will be needed to apply the theory to tasks. Evaluation is a major problem; we single out application to recognising textual entailment and machine translation for this purpose.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes