Abstract

We introduce a novel unsupervised algorithm for inducing semantic networks from noisy, crowd-sourced data. By framing network construction as a “relationship disambiguation” task, we process the entirety of Wiktionary to build a massive, WordNet-like semantic resource. The resulting network is an order of magnitude larger than Princeton WordNet and features over 344,000 linked example sentences (vs. WordNet’s 68k). Evaluation on standard word similarity benchmarks demonstrates that our fully data-driven approach yields semantic structures competitive with expert-annotated resources.

Key Contributions

  • Unsupervised Hierarchy Induction: We propose a deterministic algorithm to construct a Directed Acyclic Graph (DAG) of senses from pairwise relationships, effectively inducing a semantic hierarchy without human supervision.
  • A Massive Semantic Resource: We release a dataset enriched with hundreds of thousands of semantically linked usage examples, serving as a critical resource for tasks like Word Sense Disambiguation (WSD).
  • Novel Disambiguation Framework: We model “relationship disambiguation” using a Laplacian kernel and FastText embeddings to filter noisy user annotations.
  • Open-Source Infrastructure: We provide a full pipeline for downloading, parsing, and constructing networks from Wiktionary data.

Technical Approach

The core of our method addresses the noise inherent in crowd-sourced dictionaries. We frame the problem as Latent Semantic Network Induction:

  1. Relationship Disambiguation: For every linked pair of words (e.g., go ~ proceed), we define a semantic subspace using their definitions. We utilize FastText embeddings and a Laplacian kernel to identify which specific definitions participate in the relationship.
  2. Hierarchy Construction: We apply a custom intersection algorithm that treats more general senses as the “overlap” between specific definition sets. We formalize this as a set-theoretic “hole punching” operation, where a general sense $t$ is defined by the intersection of definition sets $\mathbb{D}’$, excluding any broader intersections:

$$f^{-1}(t) = \left(\bigcap_{\mathbb{D}’} D_{u\sim v}\right) \setminus \left(\bigcup_{\mathbb{D} \supset \mathbb{D}’} \bigcap_{\mathbb{D}} D_{u\sim v}\right)$$

Evaluation & Validation

To validate our method, we compared our induced network against the gold-standard Princeton WordNet:

  • Baseline Comparison: On standard noun-similarity benchmarks (RG-65), our unsupervised network achieves a Spearman rank correlation of $\rho = 0.83$, effectively matching the performance of Explicit Semantic Analysis (ESA) models built on the expert-annotated WordNet (0.82).
  • Scale & Structure: The resulting graph captures useful semantic structure, particularly for nouns, while offering significantly broader coverage of modern terminology and usage examples than traditional dictionaries.

Citation

@inproceedings{heidenreich2019latent,
  title={Latent semantic network induction in the context of linked example senses},
  author={Heidenreich, Hunter and Williams, Jake},
  booktitle={Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)},
  pages={170--180},
  year={2019}
}