The development of natural language processing promotes the progress of general linguistic studies. Based on the selected features and the extracted rules for word sense disambiguation (WSD), some valuable knowledge of the relations between linguistic features and word sense classes may be discovered, which may provide theoretical and practical evidence and references for lexical semantic study and natural language processing. However, many available approaches of feature selection for WSD are in the end to end operation, they can only select the optimal features for WSD, but not provide the rules for WSD, which makes knowledge discovery impossible. Therefore, a new Filter-Attribute partial ordered structure diagram (Filter-APOSD) approach is proposed in this article to fulfill both feature selection and knowledge discovery. The new approach is a combination of a Filter approach and an Attribute Partial Ordered Structure Diagram (APOSD) approach. The Filter approach is designed and used for filtering the simplest rules for WSD, and the APOSD approach is used to provide the complementary rules for WSD and visualize the structure of the datasets for knowledge discovery. The features occurring in the final rule set are selected as the optimal features. The proposed approach is verified by the benchmark data set from the SemEval-2007 preposition sense disambiguation corpus with around as the target word for WSD. The test result shows that the accuracy of WSD of around is greatly improved comparing with the one by the state of the art, and 17 out of 22 features are finally selected and ranked according to their contribution to the WSD, and some knowledge on the relations between the word senses and the selected features is discovered.
AlfawarehA. and JusohS., Resolving ambiguous preposition phrase for text mining applications, in: Proceedings of International Conference on Computer Applications Technology, IEEE, 2013, pp. 1–5.
2.
KumarA. and PrasadP., Incremental fuzzy rough sets based featureselection using fuzzy min-max neural network preprocessing, International Journal of Approximate Reasoning139 (2021), 69–87.
3.
TahaA.S., HadiA.S., CosgraveB. and McKeeverS., Amultiple association-based unsupervised feature selection algorithm for mixed data sets, Expert Systems with Applications 2022. doi: https://doi.org/10.1016/j.eswa.2022.118718
4.
SuarezA. and PalomarM., Improving Feature Selection for Maximum Entropy-BasedWord Sense Disambiguation, International Conference for Natural Language Processing, PorTal 2001: Advances in Natural Language Processing, 2001, pp. 15–23.
5.
SuarezA. and PalomarM., Best feature selection for maximumentropy-basedword sense disambiguation, Processing of International Conference on Application of Natural Language to Information Systems, 2002, pp. 213–217.
IlgenB., AdaliE. and TantugA.C., Exploring feature sets for Turkish word sense disambiguation, Turkish Journal of Electrical Engineering and Computer Sciences24 (2016), 4391–4405.
8.
SamieiyanB., MohammadiNasabP., MollaeiM.A., HajizadehF. and KangavariM., Novel optimized crow search algorithm for feature selection, Expert Systems With Applications204 (2022), 117486.
9.
HovyD., TratzS. and HovyE., What’s in a preposition? Dimensions of sense disambiguation for an interesting word class, in: Proceedings of the Twenty Third International Conference on Computational Linguistics, Posters, Beijing, 2010, pp. 454–462.
10.
HovyD., VaswaniA., TratzS., ChiangD. and HovyE., Models and training for unsupervised preposition sense disambiguation, in: Proceedings of the Forty Ninth Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, 2011, 2, pp. 323–328.
11.
VillanuevaD., Cuevas-RasgadoA., JuárezO. and Guzmán-ArenasA., Using frames to disambiguate prepositions, Expert Systems with Applications40(2) (2013), 598–610.
12.
YuretD., KU: Word sense disambiguation by substitution, in: Proceedings of the 4th International Workshop on Semantic Evaluations (SemEval-2007), Association for Computational Linguistics, Prague, Czech Republic, 2007, pp. 207–213.
13.
HancerE., Differential evolution for feature selection: a fuzzy wrapper-filter approach, Soft Computing23 (2019), 5233–5248.
14.
YanE., SongJ., RenY., ZhengC., MiB. and HongW., Construction of three-way attribute partial order structure via cognitive science and granular computing, Systems197 (2020), 1–15.
15.
FanF., HongW., SongJ., JingJ. and JiS., A visualization method of Chinese Medicine knowledge discovery base on Formal concept Analysis, ICIC Express Letters, Part B: Applications4(3) (2013), 801–808.
16.
BorboudakisG. and TsamardinosI., Forward-backward selection with early dropping, The Journal of Machine Learning Research20 (2019), 276–314.
17.
LiG., YangS., WuW. and ZhengY., A Continuous Feature Selection Method of Decision Information System, Information and Control48(2) (2019), 224–231.
18.
GongH., MuJ., BhatS. and ViswanathP., Preposition sense disambiguation and representation, in: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing Association for Computational Linguistics, Brussels, Belgium, 2018, pp. 1510–1521.
19.
LiH. and YuJ., Attribute significance analysis of English modal verb in word sense disambiguation, ICIC Express Letters, Part B: Applications6(5) (2015), 1287–1294.
20.
YangH. and ShenS., The feature selection of pattern recognition, Beijing: Publishing House of Electronics Industry, 2016.
21.
ZhiH. and ZhiD., Research on object concepts and attribute concepts in formal concept analysis, Computer Engineering and Applications49(18) (2013), 112–115.
22.
GuyonI. and ElisseeffA., An introduction to variable and feature selection, The Journal of Machine Learning Research3 (2003), 1157–1182.
23.
FuJ., YuJ. and LiuH., Influence of different subjective factors to WSD of English modal verb can, ICIC Express Letters, Part B: Applications6(5) (2015), 1473–1478.
24.
JelonekJ., KrawiecK. and StefanowskiJ., Comparative study of feature subset selection techniques for machine learning tasks, Proceedings of International Symposium Intelligent Information Systems, 1998, pp. 68–77.
25.
LiJ., KumarC.A., MeiC. and WangX., Comparison of reduction in formal decision contexts, International Journal of Approximate Reasoning80 (2017), 100–122.
26.
WanJ., ChenH., YuanZ., LiT., YangX. and SangB., A novel hybrid feature selection method considering feature interaction in neighborhood rough set, Knowledge-Based Systems227 (2021), 1–18.
27.
YuJ., FuJ., BaiT., LiS. and HongW., Data mining of interactive and restrictive relations between modal senses and contextual features by exclusive attribute features, Journal of Yanshan University43(5) (2019), 462–470.
28.
YuJ., FuJ., BaiT. and XuX., Influence of different contextual features upon WSD of English modal verb, Software Guide19(8) (2020), 33–36.
29.
YuJ., HuangL., MeiD., HongW. and LiuH., Determination of the senses of English modal verb will by fuzzy c-means cluster, ICIC Express Letters, Part B: Applications2(1) (2011), 177–182.
30.
YuJ., HongW., LiS., ZhangT. and SongJ., A new approach of word sense disambiguation and knowledge discovery of English modal verbs by formal concept analysis, International Journal of Innovative Computing, Information and Control9(3) (2013), 1189–1200.
31.
YuJ., HongW., QiuC., LiS. and MeiD., A new approach of attribute partial order structure diagram for word sense disambiguation of English preposition, Knowledge-Based Systems95 (2016), 142–152.
32.
YuJ., LiC., HongW., LiS. and MeiD., A new approach of rule extraction for word sense disambiguation by features of attributes, Applied Soft Computing27 (2015), 411–419.
33.
YuJ. and LiH., A framework for word sense disambiguation of English modal verbs by formal concept analysis, ICIC Express Letters, Part B: Applications8(2) (2017), 357–364.
34.
YuJ., LiY., WeiX., YangY., LiS. and HongW., Interactive relations between senses of quasi-modals in different subjectivity restriction gradients and syntactic and semantic features, ICIC Express Letters10(8) (2016), 2051–2058.
35.
YuJ., SunY., SunR., ZhangT. and HongW., Restriction of co-occurred contextual features upon word sense disambiguation of English modal verb, Journal of Jiangsu University of Science and Technology (Natural Science Edition)33(6) (2019), 60–67.
36.
YuJ., ZhangY. and HongW., Restriction of time, aspect and voice on senses of English modal verbs, International Journal of Innovative Computing, Information and Control12(2) (2016), 491–502.
37.
LindenK., Word sense discovery and disambiguation, Helsinki: Helsinki University Press, 2005.
38.
LitkowskiK., The Preposition Project Corpora, Technical Report 13-01. Damascus, MD: CL Research, 2013a, pp. 1–4.
39.
LitkowskiK., Preposition Disambiguation: Still a Problem, Technical Report 13-02. Damascus, MD: CL Research, 2013b, pp. 1–8.
40.
LitkowskiK. and HargravesO., The Preposition Project, in: ACL-SIGSEMWorkshop on the Linguistic Dimensions of Prepositions and their Use in Computational LinguisticFormalisms and Applications, University of Essex Colchester, United Kingdom, 2005, pp. 171–179.
41.
LitkowskiK. and HargravesO., Coverage and Inheritance in The Preposition Project, In: Proceedings of the Third ACL SIGSEM Workshop on Prepositions, Trento, Italy, 2006, pp. 89–94.
42.
LitkowskiK. and HargravesO., SemEval-2007 Task 06: Word-Sense Disambiguation of Prepositions, in: Proceedings of the 4th International Workshop on Semantic Evaluations (SemEval-2007), Association for Computational Linguistics, Prague, Czech Republic, 2007, pp. 24–29.
43.
AbualigahL. and DulaimiA., A novel feature selection method for data mining tasks using hybrid sine cosine algorithm and genetic algorithm, Cluster Computing24 (2021), 2161–2176.
44.
GanjeiM.A. and BoostaniR., A hybrid feature selection scheme for high-dimensional data, Engineering Applications of Artificial Intelligence113 (2022), 104894.
45.
RezapourM.A., FakhrahmadS.M. and SadreddiniM.H., Applying various distance functions and feature extraction schemes to ambiguity resolution, Intelligent Data Analysis22 (2018), 617–638.
46.
SabzekarM. and AydinZ., A noise-aware feature selection approach for classification, Soft Computing25 (2021), 6391–6400.
47.
PopescuO., TonelliS. and PiantaE., IRST-BP: Preposition Disambiguation based on Chain Clarifying Relationships Contexts, In MELBYB: Preposition Sense Disambiguation Using Rich Semantic Features, in: Proceedings of the 4th International Workshop on Semantic Evaluations (SemEval-2007), Association for Computational Linguistics, Prague, Czech Republic, 2007, pp. 191–194.
48.
TarkhanehO., NguyenT.T. and MazaheriS., A noval wrapper-based feature subset selection method using modified binary differential evolution algorithm, Information Sciences565 (2021), 278–305.
49.
HyeokP.J. and LeeS., Word sense classification using support vector machine, KIPS Transaction on Software and Data Engineering5(11) (2016), 563–568.
50.
LiangP., LeiD., ChinK. and HuJ., Feature selection based on robust fuzzy rough sets using kernel-based similarity and relative classification uncertainty measures, Knowledge-Based Systems255 (2022), 109795.
51.
DhillonP.S. and UngarL.H., Transfer learning, feature selection and word sense disambiguation, Proceedings of the ACL-IJCNLP 2009 Conference Short Papers, Suntec, Singapore, 2009, pp. 257–260.
52.
TamilselviP. and SrivatsaS.K., Optimal word sense disambiguation with minimal feature set using neural network, Procedia Engineering30 (2012), 546–553.
53.
MihalceaR. and MoldovanD.I., Pattern Learning and Active Feature Selection forWord Sense Disambiguation, In Proceedings of the Second InternationalWorkshop on Evaluating Word Sense Disambiguation Systems (Senseval-2), 2001, pp. 127–130.
54.
WilleR., Restructuring lattice theory: an approach based on hierarchies of concepts, I. Rival Ed. Ordered Sets, Dordrecht-Boston: Reidel, 1982, pp. 445–470.
55.
ZhouR., NiuL. and YangH., Unsupervised feature selection for attributed graphs, Expert Systems with Application168 (2021), 1–13.
56.
BergsmaS., LinD. and GoebelR., Web-scale n-gram models for lexical disambiguation, in: Proceedings of the 21st international joint conference on Artifical intelligence, 2009, pp. 1507–1512.
57.
KwonS., OhD. and KoY., Word sense disambiguation based on context selection using knowledge-based word similarity, Information Processing and Management51 (2021), 16–31.
58.
LiS., YanE., SongJ., ZhengC. and HongW., Computational generation algorithm of partial ordered structure diagram, Journal of Yanshan University28(5) (2014), 403–408.
59.
LallS., SinhaD. and GhoshA., Stable feature selection using copula based mutual information, Pattern Recognition112 (2021), 1–11.
60.
TratzS., Semantically-Enriched Parsing for Natural Language Understanding, Unpublished Ph.D. thesis, Los Angeles: University of Southern California, 2011.
61.
TratzS. and HovyD., Disambiguation of preposition sense using linguistically motivated features, In: Proceedings of the NAACL HLT Student Research Workshop and Doctoral Consortium, Boulder, Colorado, 2009, pp. 96–100
62.
TratzS. and HovyE., A fast, accurate, non-projective, semantically-enriched parser, in: Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, Edinburgh, Scotland, UK, 2011, pp. 1257–1268.
63.
ZhangS. and YuJ., Contributions of different linguistic features to WSD of English modal verb may, ICIC Express Letters, Part B: Applications6(5) (2015), 1431–1436.
64.
ZhaoS., WangM., MaS. and CuiQ., A feature selection method via relevant-redundant weight, Expert Systems With Applications207 (2022), 117923.
SinghV.P. and KumarP., Naive Bayes classifier for word sense disambiguation of Punjabi Language, Malaysian Journal of Computer Science31(3) (2018), 188–199.
67.
HongW., MaoJ., YuJ. and SongJ., The Complete Definitions of Attributes and Abstract Description of Attribute Features of the Formal Concept Analysis, ICIC Express Letters7(3B) (2013), 997–1004.
68.
HongW., LiS., YuJ., SongJ., WangX. and LiuJ., A new approach of generation of structured partial ordered attribute diagram based on covering, ICIC Express Letters, Part B: Applications6(4) (2015), 1055–1060.
69.
LiuX., ZhouY. and ZhaoH., Robust hierarchical feature selection driven by data and knowledge, Information Science551 (2021), 341–357.
70.
XuX., YuJ. and PiaoX., Contribution of governors to word sense disambiguation of English preposition, ICIC Express Letters6(3) (2015), 723–730.
71.
YangX., ChenH., LiT. and LuoC., A noise-aware fuzzy rough set approach for feature selection, Knowledge-Based Systems250 (2022), 109092.
72.
AlamY., Decision trees for sense disambiguation of prepositions: case of over, in: Proceedings of the HLT-NAACL Workshop on Computational Lexical Semantics Association for Computational Linguistics, 2004, pp. 52–59.s
73.
HuangY., JinW., YuZ. and LiB., Supervised feature selection through deep neural networks with pairwise connected structure, Knowledge-Based Systems204 (2020), 106202.
74.
PatrickY. and BaldwinT., MELB-YB: Preposition Sense Disambiguation Using Rich Semantic Features, in: Proceedings of the 4th International Workshop on Semantic Evaluations (SemEval-2007), Association for Computational Linguistics, Prague, Czech Republic, 2007, pp. 241–244.
75.
WangY., WangM. and FujitaH., A comprehensive knowledge exploitation framework, Knowledge-Based Systems190 (2020), 105030.
76.
YangY., YehH., ZhangW., LeeC., MeeseE. and LoweC., Feature extraction, selection, and K-nearest neighbores algorithm for shark behavior classification based on imbalanced dataset, IEEE Sensor Journal21(5) (2021), 6429–6439.
77.
ZhangZ., Speech feature selection and emotion recognition based on weighted binary cuckoo search, Alexandria Engineering Journal60(1) (2021), 1499–1507.
