One of the main issues associated with search engines is the query–document vocabulary mismatch problem, a long-standing problem in Information Retrieval (IR). This problem occurs when a user query does not match the content of stored documents, and it affects most search tasks. Automatic query expansion (AQE) is one of the most common approaches used to address this problem. Various AQE techniques have been proposed; these mainly involve finding synonyms or related words for the query terms. Word embedding (WE) is one of the methods that are currently receiving significant attention. Most of the existing AQE techniques focus on expanding the individual query terms rather the entire query during the expansion process, and this can lead to query drift if poor expansion terms are selected. In this article, we introduce Deep Averaging Networks (DANs), an architecture that feeds the average of the WE vectors produced by the Word2Vec toolkit for the terms in a query through several linear neural network layers. This average vector is assumed to represent the meaning of the query as a whole and can be used to find expansion terms that are relevant to the complete query. We explore the potential of DANs for AQE in Arabic document retrieval. We experiment with using DANs for AQE in the classic probabilistic BM25 model as well as for two recent expansion strategies: Embedding-Based Query Expansion approach (EQE1) and Prospect-Guided Query Expansion Strategy (V2Q). Although DANs did not improve all outcomes when used in the BM25 model, it outperformed all baselines when incorporated into the EQE1 and V2Q expansion strategies.
AzadHKDeepakA. Query expansion techniques for information retrieval: a survey. Inform Process Manag2019; 56: 1698–1735.
2.
Farhan YasirHNoah Shahrul AzmanMMohdM. Survey of automatic query expansion for Arabic text retrieval. J Inf Sci Theory Pract2020; 8: 67–86.
3.
BelkinNJOddyRNBrooksHM. Ask for information retrieval: part I. Background and theory. J Doc1982; 38: 61–71.
4.
RazaMAMokhtarRAhmadNet al. A taxonomy and survey of semantic approaches for query expansion. IEEE Access2019; 7: 17823–17833.
5.
EspositoMDamianoEMinutoloAet al. Hybrid query expansion using lexical resources and word embeddings for sentence retrieval in question answering. Inf Sci2020; 514: 88–105.
6.
CaiFDe RijkeM. A survey of query auto completion in information retrieval. Found Trends Inf Ret2016; 10: 273–363.
MiyanishiTSekiKUeharaK.Improving pseudo-relevance feedback via tweet selection. In: Proceedings of the 22nd ACM international conference on information & knowledge management, San Francisco, CA, 27 October 2013, pp. 439–448. New York: ACM.
9.
TakeuchiSISugiuraKAkahoshiYet al. Spatio-temporal pseudo relevance feedback for scientific data retrieval. IEEJ T Electr Electr2017; 12: 124–131.
10.
Fernández-ReyesFCHermosillo-ValadezJMontes-y-GómezM. A prospect-guided global query expansion strategy using word embeddings. Inform Process Manag2018; 54: 1–13.
11.
ALMasriMBerrutCChevalletJ-P. A comparison of deep learning based query expansion with pseudo-relevance feedback and mutual information. In: European conference on information retrieval, Padua, 20–23 March 2016, pp. 709–715. Cham: Springer.
12.
DiazFMitraBCraswellN.Query expansion with locally-trained word embeddings. In: Proceedings of the 54th annual meeting of the Association for Computational Linguistics, Berlin, 7–12 August 2016, pp. 367–377. Stroudsburg, PA: Association for Computational Linguistics.
13.
RoyDPaulDMitraMet al. Using word embeddings for automatic query expansion. In: Neu-IR ’16 SIGIR workshop on neural information retrieval, Pisa, 21 July 2016, pp. 1245–1246.
14.
MikolovTSutskeverIChenKet al. Distributed representations of words and phrases and their compositionality. In: Advances in neural information processing systems, Lake Tahoe, NV, 5–10 December 2013, pp. 3111–3119. San Diego, CA: NeurIPS.
15.
IyyerMManjunathaVBoyd-GraberJet al. Deep unordered composition rivals syntactic methods for text classification. In: Proceedings of the 53rd annual meeting of the Association for Computational Linguistics and the 7th international joint conference on natural language processing (volume 1: long papers), Beijing, China, 26–31 July 2015, pp. 1681–1691. Stroudsburg, PA: Association for Computational Linguistics.
16.
AlsmearatKAl-AyyoubMAl-ShalabiR. An extensive study of the Bag-Of-Words approach for gender identification of Arabic articles. In: 2014 IEEE/ACS 11th international conference on computer systems and applications (AICCSA), Doha, Qatar, 10–13 November 2014, pp. 601–608. New York: IEEE.
17.
FaqeehMAbdullaNAl-AyyoubMet al. Cross-lingual short-text document classification for Facebook comments. In: 2014 International conference on future internet of things and cloud, Barcelona, 27–29 August 2014, pp. 573–578. New York: IEEE.
18.
MohsenGAl-AyyoubMHmeidiIet al. On the automatic construction of an Arabic thesaurus. In: 2018 9th international conference on information and communication systems (ICICS), Irbid, Jordan, 3–5 April 2018, pp. 243–247. New York: IEEE.
19.
AbuElKhairI. Arabic information retrieval. Annu Rev Inform Sci2007; 41: 505–533.
20.
LarkeyLSBallesterosLConnellME. Improving stemming for Arabic information retrieval: light stemming and co-occurrence analysis. In: Proceedings of the 25th annual international ACM SIGIR conference on research and development in information retrieval, Tampere, 11–15 August 2002, pp. 275–282. New York: ACM.
21.
AbdelaliADarwishKDurraniNet al. Farasa: a fast and furious segmenter for Arabic. In: Proceedings of the 2016 conference of the North American chapter of the Association for Computational Linguistics: demonstrations, San Diego, CA, June 2016, pp. 11–16. Stroudsburg, PA: Association for Computational Linguistics.
22.
GuiratSBBounhasISlimaniY. Combining indexing units for Arabic information retrieval. Int J Softw Innov2016; 4: 1–14.
23.
ZamaniHCroftWB.Embedding-based query language models. In: Proceedings of the 2016 ACM international conference on the theory of information retrieval, Newark, DE, September 2016, pp. 147–156. New York: ACM.
24.
Baeza-YatesRRibeiro-NetoB. Modern information retrieval, vol. 463. New York: ACM Press, 1999.
25.
CarpinetoCRomanoG. A survey of automatic query expansion in information retrieval. ACM Comput Surv2012; 44: 1–50.
26.
AbbacheAMezianeFBelalemGet al. Arabic query expansion using WordNet and association rules. In: Information Resources Management Association (ed.) Information retrieval and management: concepts, methodologies, tools, and applications. Hershey, PA: IGI Global, 2016, pp. 1239–1254.
27.
El MahdaouyAEl AlaouiSOGaussierE. Word-embedding-based pseudo-relevance feedback for Arabic information retrieval. J Inf Sci2018; 45: 429–442.
28.
BengioY. Learning deep architectures for AI. Found Trends Mach Learn2009; 2: 1–127.
29.
TurneyPDPantelP. From frequency to meaning: vector space models of semantics. J Artif Intell Res2010; 37: 141–188.
30.
KimHKKimHChoS. Bag-Of-Concepts: comprehending document representation through clustering words in distributed representation. Neurocomputing2017; 266: 336–352.
RoyDGangulyDMitraMet al. Word vector compositionality based relevance feedback using kernel density estimation. In: Proceedings of the 25th ACM international on conference on information and knowledge management, Indianapolis IN, October 2016, pp. 1281–1290. New York: ACM.
33.
AkloucheBBounhasISlimaniY. Query expansion based on NLP and word embeddings. In: Proceedings of the twenty-seventh text retrieval conference, Gaithersburg, MD, 14–16 November 2018.
34.
El MahdaouyAEl AlaouiSOGaussierE. Improving Arabic information retrieval using word embedding similarities. Int J Speech Technol2018; 21: 121–136.
35.
PenningtonJSocherRManningCD. Glove: global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), Doha, Qatar, 25–19 October 2014, pp. 1532–1543. Stroudsburg, PA: Association for Computational Linguistics.
36.
FangHZhaiC.Semantic term matching in axiomatic approaches to information retrieval. In: Proceedings of the 29th annual international ACM SIGIR conference on research and development in information retrieval, Seattle, WA, August 2006, pp. 115–122. New York: ACM.
37.
ZucconGKoopmanBBruzaPet al. Integrating and evaluating neural word embeddings in information retrieval. In: Proceedings of the 20th Australasian document computing symposium, Parramatta, NSW, Australia, December 2015.
38.
GangulyDRoyDMitraMet al. Word embedding based generalized language model for information retrieval. In: Proceedings of the 38th international ACM SIGIR conference on research and development in information retrieval, Santiago, Chile, August 2015, pp. 795–798. New York: ACM.
39.
LavrenkoVCroftWB.Relevance based language models. In: Proceedings of the 24th annual international ACM SIGIR conference on research and development in information retrieval, New Orleans, LA, 9–13 September 2001, pp. 120–127. New York: ACM.
40.
CrimpRTrotmanA.Refining query expansion terms using query context. In: Proceedings of the 23rd Australasian document computing symposium, Dunedin, New Zealand, December 2018, p. 12. New York: ACM.
41.
CroftWMetzlerDStrohmanT. Search engines – information retrieval in practice, vol. 520. Reading, MA: Addison-Wesley Reading, 2010.
42.
XueBFuCShaobinZ. A study on sentiment computing and classification of Sina Weibo with Word2vec. In: 2014 IEEE international congress on big data (big data congress), Anchorage, AK, 27 June–2 July 2014, pp. 358–363. New York: IEEE.
43.
TaiKSSocherRManningCD. Improved semantic representations from tree-structured long short-term memory networks. In: Proceedings of the 53rd annual meeting of the Association for Computational Linguistics and the 7th international joint conference on natural language processing, Beijing, China, 26–31 July 2015, pp. 1556–1566. Stroudsburg, PA: Association for Computational Linguistics.
VaidyanathanRDasSSrivastavaN. A study on retrieval models and query expansion using PRF. Int J Sci Eng Res2015; 6: 13–18.
46.
DarwishKAliAM.Arabic retrieval revisited: morphological hole filling. In: Proceedings of the 50th annual meeting of the Association for Computational Linguistics: short papers-volume 2, Jeju, Korea, 8–14 July 2012, pp. 218–222. Stroudsburg, PA: Association for Computational Linguistics.
47.
AhmedAAlonGZaidatBet al. Brown University at TREC precision medicine 2019. In: Proceedings of the twenty-eighth text retrieval conference, TREC 2019, Gaithersburg, MD, 13–15 November 2019.
