• Publications
  • Influence
Word Sense Disambiguation: A Unified Evaluation Framework and Empirical Comparison
TLDR
In this paper we develop a unified evaluation framework and analyze the performance of various Word Sense Disambiguation systems in a fair setup. Expand
  • 142
  • 33
  • PDF
Nasari: Integrating explicit knowledge and corpus statistics for a multilingual representation of concepts and entities
TLDR
In this paper we put forward a novel multilingual vector representation, called Nasari, which not only enables accurate representation of word senses in different languages, but it also provides two main advantages over existing approaches: (1) high coverage, including both concepts and named entities, and (2) comparability across languages and linguistic levels (i.e., words, senses and concepts). Expand
  • 130
  • 14
  • PDF
SemEval-2017 Task 2: Multilingual and Cross-lingual Semantic Word Similarity
TLDR
This paper introduces a new task on Multilingual and Cross-lingual Semantic Word Similarity which measures the semantic similarity of word pairs within and across five languages. Expand
  • 92
  • 14
  • PDF
NASARI: a Novel Approach to a Semantically-Aware Representation of Items
TLDR
The semantic representation of individual word senses and concepts is of fundamental importance to several applications in Natural Language Processing. Expand
  • 92
  • 13
  • PDF
Embedding Words and Senses Together via Joint Knowledge-Enhanced Training
TLDR
We propose SW2V (Senses and Words to Vectors), a neural model which learns vector representations for words and senses in a joint training phase by exploiting both text corpora and knowledge from semantic networks. Expand
  • 61
  • 13
  • PDF
SemEval 2018 Task 2: Multilingual Emoji Prediction
TLDR
This paper describes the SemEval 2018 shared task in multilingual emoji prediction. Expand
  • 60
  • 7
  • PDF
A Unified Multilingual Semantic Representation of Concepts
TLDR
We put forward a novel multilingual concept representation, called MUFFIN, which not only enables accurate representation of word senses in different languages, but also provides multiple advantages over existing approaches. Expand
  • 55
  • 5
  • PDF
A Framework for the Construction of Monolingual and Cross-lingual Word Similarity Datasets
TLDR
We propose an automatic standardization for the construction of cross-lingual similarity datasets, and provide an evaluation, demonstrating its reliability and robustness. Expand
  • 50
  • 5
  • PDF
Find the word that does not belong: A Framework for an Intrinsic Evaluation of Word Vector Representations
TLDR
We present a new framework for an intrinsic evaluation of word vector representations based on the outlier detection task, which tests the capability of vector space models to create semantic clusters in the space. Expand
  • 34
  • 5
  • PDF
From Word to Sense Embeddings: A Survey on Vector Representations of Meaning
TLDR
We present a comprehensive overview of the wide range of techniques in the two main branches of sense representation, i.e., unsupervised and knowledge-based. Expand
  • 115
  • 4
  • PDF