Random Walks for Knowledge-Based Word Sense Disambiguation

Agirre, Eneko; Lacalle, Oier López de; Soroa, Aitor

doi:10.1162/coli_a_00164

Cited by 223 publications

(210 citation statements)

References 36 publications

Supporting

Mentioning

205

Contrasting

Unclassified

Order By: Relevance

“…In contrast, knowledge-based systems do not require sense-annotated data and often draw upon the structural properties of lexicosemantic resources (Agirre et al, 2014;Moro et al, 2014;Weissenborn et al, 2015). Such systems construct a model based only on the underlying resource, which is then able to handle multiple target words at the same time and disambiguate them jointly, whereas word experts are forced to treat each disambiguation target in isolation.…”

Section: Introductionmentioning

confidence: 99%

Neural Sequence Learning Models for Word Sense Disambiguation

Raganato¹,

Bovi²,

Navigli³

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

172

180

View full text Add to dashboard Cite

Word Sense Disambiguation models exist in many flavors. Even though supervised ones tend to perform best in terms of accuracy, they often lose ground to more flexible knowledge-based solutions, which do not require training by a word expert for every disambiguation target. To bridge this gap we adopt a different perspective and rely on sequence learning to frame the disambiguation problem: we propose and study in depth a series of end-to-end neural architectures directly tailored to the task, from bidirectional Long Short-Term Memory to encoder-decoder models. Our extensive evaluation over standard benchmarks and in multiple languages shows that sequence learning enables more versatile all-words models that consistently lead to state-of-the-art results, even against word experts with engineered features.

show abstract

Section: Introductionmentioning

confidence: 99%

Neural Sequence Learning Models for Word Sense Disambiguation

Raganato¹,

Bovi²,

Navigli³

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

172

180

View full text Add to dashboard Cite

show abstract

“…This may be done by applying a resource-based WSD approach similar to (Brody et al, 2006;Agirre et al, 2014), detecting the concept node that matches the term's sense in the given context.…”

Section: Discussionmentioning

confidence: 99%

Learning to Exploit Structured Resources for Lexical Inference

Shwartz

Levy

Dagan

et al. 2015

Proceedings of the Nineteenth Conference on Computational Natural Language Learning

View full text Add to dashboard Cite

Massive knowledge resources, such as Wikidata, can provide valuable information for lexical inference, especially for proper-names. Prior resource-based approaches typically select the subset of each resource's relations which are relevant for a particular given task. The selection process is done manually, limiting these approaches to smaller resources such as WordNet, which lacks coverage of propernames and recent terminology. This paper presents a supervised framework for automatically selecting an optimized subset of resource relations for a given target inference task. Our approach enables the use of large-scale knowledge resources, thus providing a rich source of high-precision inferences over proper-names. 1

show abstract

“…In order to contrast our results with the two related techniques, we used UKB 5 , a publicly available implementation of Personalized PageRank (Agirre et al, 2014), and ran it over the same graph as our proposed methods. We used it out-of-the-box with a damping value of 0.85.…”

Section: Methodsmentioning

confidence: 99%

Random Walks and Neural Network Language Models on Knowledge Bases

Goikoetxea

Soroa

Agirre

2015

Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

Self Cite

View full text Add to dashboard Cite

Random walks over large knowledge bases like WordNet have been successfully used in word similarity, relatedness and disambiguation tasks. Unfortunately, those algorithms are relatively slow for large repositories, with significant memory footprints. In this paper we present a novel algorithm which encodes the structure of a knowledge base in a continuous vector space, combining random walks and neural net language models in order to produce novel word representations. Evaluation in word relatedness and similarity datasets yields equal or better results than those of a random walk algorithm, using a dense representation (300 dimensions instead of 117K). Furthermore, the word representations are complementary to those of the random walk algorithm and to corpus-based continuous representations, improving the stateof-the-art in the similarity dataset. Our technique opens up exciting opportunities to combine distributional and knowledge-based word representations.

show abstract

Random Walks for Knowledge-Based Word Sense Disambiguation

Cited by 223 publications

References 36 publications

Neural Sequence Learning Models for Word Sense Disambiguation

Neural Sequence Learning Models for Word Sense Disambiguation

Learning to Exploit Structured Resources for Lexical Inference

Random Walks and Neural Network Language Models on Knowledge Bases

Contact Info

Product

Resources

About