2016 CapturingSemanticSimilarityforE

(Francis-Landau et al., 2016) ⇒ Matthew Francis-Landau, Greg Durrett, and Dan Klein. (2016). “Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks.” In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2016).

Subject Headings: Semantic Similarity Neural Network; Entity Linking System; Convolutional Neural Network; Semantic Similarity Measure, CNN-SNN Entity Linking System.

Notes

Online Resource(s):
- Source code: https://github.com/matthewfl/nlp-entity-convnet
- ArXiv pre-print: https://arxiv.org/abs/1604.00734

Cited By

Google Scholar: ~ 144+ Citations.

Quotes

Abstract

A key challenge in entity linking is making effective use of contextual information to disambiguate mentions that might refer to different entities in different contexts. We present a model that uses convolutional neural networks to capture semantic correspondence between a mention's context and a proposed target entity. These convolutional networks operate at multiple granularities to exploit various kinds of topic information, and their rich parameterization gives them the capacity to learn which n-grams characterize different topics. We combine these networks with a sparse linear model to achieve state-of-the-art performance on multiple entity linking datasets, outperforming the prior systems of Durrett and Klein (2014) and Nguyen et al. (2014).

1. Introduction

2. Model

Our model focuses on two core ideas: first, that topic semantics at different granularities in a document are helpful in determining the genres of entities for entity linking, and second, that CNNs can distill a block of text into a meaningful topic vector.

Our entity linking model is a log-linear model that places distributions over target entities $t$ given a mention $x$ and its containing source document. For now, we take $P \left(t|x\right) \propto \exp w^{\top}f_C \left(x, t; \theta\right)$, where $f_C$ produces a vector of features based on CNNs with parameters $\theta$ as discussed in Section 2.1. Section 2.2 describes how we combine this simple model with a full-fledged entity linking system. As shown in the middle of Figure 1, each feature in $f_C$ is a cosine similarity between a topic vector associated with the source document and a topic vector associated with the target entity. These vectors are computed by distinct CNNs operating over different subsets of relevant text.

**Figure 1:** Extraction of convolutional vector space features $f_C\left (x, t_e\right)$. Three types of information from the input document and two types of information from the proposed title are fed through convolutional networks to produce vectors, which are systematically compared with cosine similarity to derive real-valued semantic similarity features.

(...)

3. Experimental Result

4. Conclusion

Acknowledgments

This work was partially supported by NSF Grant CNS-1237265 and a Google Faculty Research Award. Thanks to the anonymous reviewers for their helpful comments.

References

BibTeX

@inproceedings{2016_CapturingSemanticSimilarityforE,
  author    = {Matthew Francis-Landau and
               Greg Durrett and
               Dan Klein},
  editor    = {Kevin Knight and
               Ani Nenkova and
               Owen Rambow},
  title     = {{Capturing Semantic Similarity for Entity Linking with Convolutional
               Neural Networks},
  booktitle = {Proceedings of the 2016 Conference of the North American Chapter
               of the Association for Computational Linguistics: Human Language Technologies
               (NAACL-HLT 2016)},
  pages     = {1256--1261},
  publisher = {The Association for Computational Linguistics},
  year      = {2016},
  url       = {https://doi.org/10.18653/v1/n16-1150},
  doi       = {10.18653/v1/n16-1150},
}

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2016 CapturingSemanticSimilarityforE	Dan Klein Greg Durrett Matthew Francis-Landau			Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks						2016