Nasari: Integrating explicit knowledge and corpus statistics for a multilingual representation of concepts and entities

Camacho-Collados, José; Pilehvar, Mohammad Taher; Navigli, Roberto

doi:10.1016/j.artint.2016.07.005

Cited by 159 publications

(146 citation statements)

References 31 publications

Supporting

Mentioning

143

Contrasting

Order By: Relevance

“…Based on the same principle, various works have adapted the original algorithm by also taking into account definitions from related words (Banerjee and Pedersen, 2003), or by calculating the distributional similarity between definitions and the context of the target word (Basile et al, 2014;Chen et al, 2014). Distributional similarity has also been exploited in different settings in various works (Miller et al, 2012;CamachoCollados et al, 2015;Camacho-Collados et al, 2016b). In addition to these approaches based on distributional similarity, an important branch of knowledge-based systems found their techniques on the structural properties of semantic graphs from lexical resources (Agirre and Soroa, 2009;Guo and Diab, 2010;Ponzetto and Navigli, 2010;Agirre et al, 2014;Moro et al, 2014;Weissenborn et al, 2015;Tripodi and Pelillo, 2016).…”

Section: Knowledge-based Wsdmentioning

confidence: 99%

Word Sense Disambiguation: A Unified Evaluation Framework and Empirical Comparison

Raganato

Camacho-Collados²,

Navigli³

2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 1

Self Cite

271

298

View full text Add to dashboard Cite

Word Sense Disambiguation is a longstanding task in Natural Language Processing, lying at the core of human language understanding. However, the evaluation of automatic systems has been problematic, mainly due to the lack of a reliable evaluation framework. In this paper we develop a unified evaluation framework and analyze the performance of various Word Sense Disambiguation systems in a fair setup. The results show that supervised systems clearly outperform knowledge-based models. Among the supervised systems, a linear classifier trained on conventional local features still proves to be a hard baseline to beat. Nonetheless, recent approaches exploiting neural networks on unlabeled corpora achieve promising results, surpassing this hard baseline in most test sets.

show abstract

Section: Knowledge-based Wsdmentioning

confidence: 99%

Word Sense Disambiguation: A Unified Evaluation Framework and Empirical Comparison

Raganato

Camacho-Collados²,

Navigli³

2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 1

Self Cite

271

298

View full text Add to dashboard Cite

show abstract

“…In fact, a number of successful approaches to semantic similarity make explicit use of Wikipedia, from ESA (Gabrilovich and Markovitch, 2007) to NASARI (Camacho Collados et al, 2016). Others, like SENSEMBED (Iacobacci et al, 2015), report state-of-the-art results when trained on an automatically disambiguated version of a Wikipedia dump.…”

Section: Introductionmentioning

confidence: 99%

“…While many classical approaches to word similarity have been limited to the English language (Gabrilovich and Markovitch, 2007;Mihalcea, 2007;Pilehvar et al, 2013;Baroni et al, 2014), a growing interest for multilingual and cross-lingual models is emerging (Hassan and Mihalcea, 2011;Camacho Collados et al, 2016) and it is accompanied by the development of multilingual benchmarks (Gurevych, 2005;Granada et al, 2014;Camacho Collados et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

Sew-Embed at SemEval-2017 Task 2: Language-Independent Concept Representations from a Semantically Enriched Wikipedia

Bovi

Raganato

2017

Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)

View full text Add to dashboard Cite

This paper describes SEW-EMBED, our language-independent approach to multilingual and cross-lingual semantic word similarity as part of the SemEval-2017 Task 2. We leverage the Wikipediabased concept representations developed by Raganato et al. (2016), and propose an embedded augmentation of their explicit high-dimensional vectors, which we obtain by plugging in an arbitrary word (or sense) embedding representation, and computing a weighted average in the continuous vector space. We evaluate SEW-EMBED with two different off-the-shelf embedding representations, and report their performances across all monolingual and cross-lingual benchmarks available for the task. Despite its simplicity, especially compared with supervised or overly tuned approaches, SEW-EMBED achieves competitive results in the crosslingual setting (3rd best result in the global ranking of subtask 2, score 0.56).

show abstract

“…ADW (Pilehvar and Navigli, 2015) is another WordNet-based approach which exploits only the semantic network of this resource an obtains interpretable sense representations. Other work in this branch include SensEmbed (Iacobacci et al, 2015) and Nasari (Camacho-Collados et al, 2015;Camacho-Collados et al, 2016) which are based on the BabelNet sense inventory (Navigli and Ponzetto, 2012). The former technique first disambiguates words in a given corpus with the help of a knowledge-based WSD system and then uses the generated sense-annotated corpus as training data for Word2vec.…”

Section: Related Workmentioning

confidence: 99%

De-Conflated Semantic Representations

Pilehvar¹,

Collier²

2016

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

Self Cite

View full text Add to dashboard Cite

One major deficiency of most semantic representation techniques is that they usually model a word type as a single point in the semantic space, hence conflating all the meanings that the word can have. Addressing this issue by learning distinct representations for individual meanings of words has been the subject of several research studies in the past few years. However, the generated sense representations are either not linked to any sense inventory or are unreliable for infrequent word senses. We propose a technique that tackles these problems by de-conflating the representations of words based on the deep knowledge it derives from a semantic network. Our approach provides multiple advantages in comparison to the past work, including its high coverage and the ability to generate accurate representations even for infrequent word senses. We carry out evaluations on six datasets across two semantic similarity tasks and report state-of-the-art results on most of them.

show abstract

Nasari: Integrating explicit knowledge and corpus statistics for a multilingual representation of concepts and entities

Cited by 159 publications

References 31 publications

Word Sense Disambiguation: A Unified Evaluation Framework and Empirical Comparison

Word Sense Disambiguation: A Unified Evaluation Framework and Empirical Comparison

Sew-Embed at SemEval-2017 Task 2: Language-Independent Concept Representations from a Semantically Enriched Wikipedia

De-Conflated Semantic Representations

Contact Info

Product

Resources

About