ACL Findings2021
Representing Syntax and Composition with Geometric Transformations
Abstract
The exploitation of syntactic graphs (SyGs) as a word's context has been shown to be beneficial for distributional semantic models (DSMs), both at the level of individual word representations and in deriving phrasal representations via composition. However, notwithstanding the potential performance benefit, the syntactically-aware DSMs proposed to date have huge numbers of parameters (compared to conventional DSMs) and suffer from data sparsity. Furthermore, the encoding of the SyG links (i.e., the syntactic relations) has been largely limited to linear maps. The knowledge graphs' literature, on the other hand, has proposed light-weight models employing different geometric transformations (GTs) to encode edges in a knowledge graph (KG). Our work explores the possibility of adopting this family of models to encode SyGs. Furthermore, we investigate which GT better encodes syntactic relations, so that these representations can be used to enhance phrase-level composition via syntactic contextualisation.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers1
Builds on5
- SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment SemanticsDa Yin, Tao Meng, Kai-Wei ChangACL 2020 · 127 citations
- Low-Dimensional Hyperbolic Knowledge Graph EmbeddingsInes Chami, Adva Wolf, Da-Cheng Juan, Frederic Sala et al.ACL 2020 · 48 citations
- LSTMS Compose - and Learn - Bottom-UpNaomi Saphra, Adam LopezEMNLP Findings 2020 · 10 citations
- Autoencoding Pixies: Amortised Variational Inference with Graph Convolutions for Functional Distributional SemanticsGuy EmersonACL 2020 · 8 citations
- Finding Universal Grammatical Relations in Multilingual BERTEthan A. Chi, John Hewitt, Christopher D. ManningACL 2020 · 7 citations
Related papers
- ExpressivE: A Spatio-Functional Embedding For Knowledge Graph CompletionAleksandar Pavlovic, Emanuel SallingerICLR 2023 · 12 citations
- Compositional Generalization with Grounded Language ModelsSondre Wold, Étienne Simon, Lucas Georges Gabriel Charpentier, Egor V. Kostylev et al.ACL Findings 2024
- Improving Knowledge Graph Embedding Using Affine Transformations of Entities Corresponding to Each RelationJinfa Yang, Yongjie Shi, Xin Tong, Robin Wang et al.EMNLP Findings 2021 · 5 citations
- Semantic Composition with PSHRG for Derivation Tree Reconstruction from Graph-Based Meaning RepresentationsChun Hei Lo, Wai Lam, Hong ChengACL 2022 · 1 citation
- Space Efficient Context Encoding for Non-Task-Oriented Dialogue Generation with Graph Attention TransformerFabian Galetzka, Jewgeni Rose, David Schlangen, Jens LehmannACL 2021
