Information Retrieval System Using Multiwords Expressions (Mwe) as Descriptors

Silva, Edson Marchetti da; Souza, Renato Rocha

doi:10.4301/s1807-17752012000200002

Cited by 3 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multi-word expressions (MWEs) are fundamental to language and, as such, having a robust semantic representation for MWEs is important for any natural language processing task that involves text understanding such as information extraction, or question answering (e.g., da Silva and Souza, 2012;Thurmair, 2018;Subramanian et al, 2018). While MWEs have received attention in recent years, leading to considerable progress in learning MWE representations (Mitchell and Lapata, 2010;Butnariu et al, 2010;Tratz, 2011;Hendrickx et al, 2013;Dima, 2016;Shwartz and Dagan, 2018;Shwartz, 2019), we argue that the proposed methods have limitations.…”

Section: Introductionmentioning

confidence: 99%

An Unsupervised Method for Learning Representations of Multi-word Expressions for Semantic Classification

Vacareanu¹,

Valenzuela-Escárcega²,

Sharp³

et al. 2020

Proceedings of the 28th International Conference on Computational Linguistics

View full text Add to dashboard Cite

This paper explores an unsupervised approach to learning a compositional representation function for multi-word expressions (MWEs), and evaluates it on the Tratz dataset, which associates two-word expressions with the semantic relation between the compound constituents (e.g. the label employer is associated with the noun compound government agency) (Tratz, 2011). The composition function is based on recurrent neural networks, and is trained using the Skip-Gram objective to predict the words in the context of MWEs. Thus our approach can naturally leverage large unlabeled text sources. Further, our method can make use of provided MWEs when available, but can also function as a completely unsupervised algorithm, using MWE boundaries predicted by a single, domain-agnostic part-of-speech pattern. With pre-defined MWE boundaries, our method outperforms the previous state-of-the-art performance on the coarse-grained evaluation of the Tratz dataset (Tratz, 2011), with an F1 score of 50.4%. The unsupervised version of our method approaches the performance of the supervised one, and even outperforms it in some configurations.

show abstract

Section: Introductionmentioning

confidence: 99%

An Unsupervised Method for Learning Representations of Multi-word Expressions for Semantic Classification

Vacareanu¹,

Valenzuela-Escárcega²,

Sharp³

et al. 2020

Proceedings of the 28th International Conference on Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…Integrating MWEs in NLP applications has evidently and consistently shown to improve the performance in tasks such as Information Retrieval (Acosta et al 2011;da Silva and Souza, 2012), Text Mining (SanJuan and IbekweSanJuan, 2006), Syntactic Parsing (Eryiğit et al, 2011;Nivre and Nilsson, 2004;Attia, 2006;Korkontzelos and Manandhar, 2010), Machine Translation (Deksne, 2008;Carpuat and Diab, 2010;Ghoneim and Diab 2013;Bouamor et al, 2011), Question Answering, and Named-Entity extraction (Bu et al, 2011).…”

Section: Introductionmentioning

confidence: 99%

A Framework for the Classification and Annotation of Multiword Expressions in Dialectal Arabic

Hawwari

Attia

Diab

2014

Proceedings of the EMNLP 2014 Workshop on Arabic Natural Language Processing (ANLP)

View full text Add to dashboard Cite

In this paper we describe a framework for classifying and annotating Egyptian Arabic Multiword Expressions (EMWE) in a specialized computational lexical resource. The framework intends to encompass comprehensive linguistic information for each MWE including: a. phonological and orthographic information; b. POS tags; c. structural information for the phrase structure of the expression; d. lexicographic classification; e. semantic classification covering semantic fields and semantic relations; f. degree of idiomaticity where we adopt a three-level rating scale; g. pragmatic information in the form of usage labels; h. Modern Standard Arabic equivalents and English translations, thereby rendering our resource a three-way -Egyptian Arabic, Modern Standard Arabic and English -repository for MWEs.

show abstract

Using Semantics for Granularities of Tokenization

Riedl

Biemann²

2018

Computational Linguistics

View full text Add to dashboard Cite

Depending on downstream applications, it is advisable to extend the notion of tokenization from low-level character-based token boundary detection to identification of meaningful and useful language units. This entails both identifying units composed of several single words that form a several single words that form a, as well as splitting single-word compounds into their meaningful parts. In this article, we introduce unsupervised and knowledge-free methods for these two tasks. The main novelty of our research is based on the fact that methods are primarily based on distributional similarity, of which we use two flavors: a sparse count-based and a dense neural-based distributional semantic model. First, we introduce DRUID, which is a method for detecting MWEs. The evaluation on MWE-annotated data sets in two languages and newly extracted evaluation data sets for 32 languages shows that DRUID compares favorably over previous methods not utilizing distributional information. Second, we present SECOS, an algorithm for decompounding close compounds. In an evaluation of four dedicated decompounding data sets across four languages and on data sets extracted from Wiktionary for 14 languages, we demonstrate the superiority of our approach over unsupervised baselines, sometimes even matching the performance of previous language-specific and supervised methods. In a final experiment, we show how both decompounding and MWE information can be used in information retrieval. Here, we obtain the best results when combining word information with MWEs and the compound parts in a bag-of-words retrieval set-up. Overall, our methodology paves the way to automatic detection of lexical units beyond standard tokenization techniques without language-specific preprocessing steps such as POS tagging.

show abstract

Information Retrieval System Using Multiwords Expressions (Mwe) as Descriptors

Cited by 3 publications

References 10 publications

An Unsupervised Method for Learning Representations of Multi-word Expressions for Semantic Classification

An Unsupervised Method for Learning Representations of Multi-word Expressions for Semantic Classification

A Framework for the Classification and Annotation of Multiword Expressions in Dialectal Arabic

Using Semantics for Granularities of Tokenization

Contact Info

Product

Resources

About