Çizge Tabanlı WordNet Ağı Üzerinde Anlamsal İlişki Ağırlıklarının Tespiti

Birçok doğal dil işleme uygulamasında metinsel iki öğenin anlamsal ilişkisinin tespit edilmesi çok önemli bir aşamadır. Bu çalışmada WordNet 3.0 ve Men’s veri seti kullanarak sözlük tabanlı anlamsal ilişki belirleme metodları için yeni bir yaklaşım sunulmaktadır. Anlamsal ağırlıkların hesaplanmasında Men’s veriseti kullanılmış ve bulunan değerler anlamsal ağırlık hesaplanmasında kullanılmıştır. Önerilen metodun doğruluğunu ölçmek için RG65 benzerlik veriseti kullanılmış, kayıslama sonucunda 0.81 Spearman korelasyon değeri elde edilmiştir. Büyük boyutlu bir verisetinin geliştirme ve test için kullanılıp, diğer önemli bir verisetinin de kıyaslama amaçlı olarak anlamsal ilişki tiplerinin ağırlıklarının belirlenmesi ve anlamsal ilişkinin hesaplanmasında kullanılması anlamsal benzerlik ve anlamsal ilişki hesaplanmasına farklı bir bakış açısı getirmektedir.

Anahtar Kelimeler:

Doğal dil işleme, Anlamsal ilişki, WordNet

Semantic Relation’s Weight Determination on a Graph Based WordNet

Determination of semantic relatedness between two textual items is one of the crucial phases in many Natural Language Processing applications. In this study, a new approach to lexicon based semantic relation determination methods was experienced using WordNet 3.0 and Men’s real-life similarity dataset. Men’s test collection was used for the determination of the relation weights and determined weights were used in semantic relatedness computation. RG65 similarity dataset was used for a benchmark of the proposed method and Spearman correlation 0.81 was gained, taking into account that retrieving the relations weight using a large scale dataset and testing them with another real-life dataset promises new perspectives to the determination of the relations weight and to the relatedness computation.

Keywords:

Natural language processing, Semantic relation, WordNet,

PDF

___

Aguirre, E. and Soroa, A., 2009. Personalizing PageRank for Word Sense Disambiguation. Proceedings of the 12th conference of the European chapter of the Association for Computational Linguistics, March 2009, Athens, Greece, p. 34-41.
Ahsan, M.G., Naghibzadeh, M. and Naeini, S.E.Y., 2014. Semantic similarity assessment of words using weighted WordNet, Int. J. Mach. Learn. & Cyber, 5 (3), 479-490, https://doi.org/10.1007/s13042-012-0135-3.
Brin, S. and Page, L., 1998. The anatomy of a large-scale hypertextual web search engine. Computer Networks and ISDN Systems 30, 107-117.
Bruni, E., Tran, N. K. and Baroni, M., 2014. Multimodal Distributional Semantics. Journal of Artificial Intelligence Research, 49, 1-47, https://doi.org/10.1613/jair.413.
Fellbaum, C., 1998. WordNet: An Electronic Lexical Database. Cambridge, MA: MIT Press, 422p.
Finkelstein, L., Gabrilovich, E., Matia,S., Y., Rivlin, E., Solan, Z., Wolfman, G. and Ruppin, E., 2001. Placing search in context: The concept revisited. In WWW ’01: Proceedings of the 10th international conference on World Wide Web, May 2001, Hong Hong, p. 406–414.
Hirst, G. and St-Onge, D, 1998, Lexical chains as representations of context for the detection and correction of malapropisms, in WordNet: An Electronic Lexical Database, MITP, p. 305–332.
Hughes, T. and Ramage, D., 2007. Lexical semantic relatedness with random graph walks. Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP–CoNLL, June 2007, Prague, Czech Republic, p.581–589.
Kartsaklis D., Pilehvar M.T. and Collier N., 2018. Mapping Text to Knowledge Graph Entities using Multi-Sense LSTMs. EMNLP, Oct. 2018, Brussels, Belgium.
Li, Y., Zuhair, A. B. and McLean, D., 2003. An approach for measuring semantic similarity between words using multiple information sources, IEEE Trans. Knowledge and Data Eng., 15 (4), 871-882.
Meng, L., Gu, J. and Zhou, Z., 2012. A New Hybrid Semantic Similarity Measure Based on WordNet. In: Lei J., Wang F.L., Li M., Luo Y. (eds) Network Computing and Information Security. Communications in Computer and Information Science. 345, 739-744. https://doi.org/10.1007/978-3-642-35211-9_93.
Miller, G. A. and Charles, W. G., 1991. Contextual Correlates of Semantic Similarity. Language and Cognitive Processes, 6 (1), 1-28.
Mikolov T., Chen K., Corrado G. and Dean J., 2013. Efficient estimation of word representations in vector space. CoRR, abs/1301.3781.
Navigli R. and Ponzetto S., 2012. BabelNet: The Automatic Construction, Evaluation, and Application of a Wide-Coverage Multilingual Semantic Network. Artificial Intelligence, 193, P. 217-250.
Pennington J., Socher R. and Christopher D.M., 2014. GloVe: Global vectors for word representation. Proceedings of the Empiricial Methods in Natural Language Processing (EMNLP 2014), October 2014, Doha, Qatar, 12, 1532–1543.
Pilehvar, M. T. and Navigli, R., 2015. From Senses to Texts: An All-in-one Graph-based Approach for Measuring Semantic Similarity. Artificial Intelligence, 228, 95-128.
Rubenstein, H. and Goodenough, J.B., 1965. Contextual correlates of synonymy, Communications of the ACM, 8 (10), 627–633
Siblini, R. And Kosseim, L., 2013. Using a Weighted Semantic Network for Lexical Semantic Relatedness. Proceedings of Recent Advances in Natural Language Processing, Sept 2013, Hissar, Bulgaria, p.610-618
Speer R. and Chin J., 2016. An ensemble method to produce high-quality word embeddings. arXiv preprint arXiv:1604.01692
Speer, R. and Havasi C., 2012. Representing General Relational Knowledge in ConceptNet 5,. Proc. of LREC, May 2012, Istanbul Turkey, p. 3679-3686.
Sultan, A.M., Bethard, S. and Sumner, T., 2014. Back to basics for monolingual alignment: exploiting word similarity and contextual evidence, Trans. Assoc. Comput. Linguist., 2 (1), 219–230.
Wu, Z. and Palmer, M., 1994. Verb semantics and lexical selection. the 32nd Annual Meeting of the Association for Computational Linguistics, June 1994, New Mexico USA, p.133–138.
Yang, D. and Powers, M.V., 2005. Measuring semantic similarity in the taxonomy of WordNet. Proceeding of the 28th Australasian Computer Science Conference, Jan 2005, Newcastle, Australia, p. 315-332.