Journal of Soft Computing and Information Technology

Journal of Soft Computing and Information Technology

Integrated Semantic Representation (ISR-Model): Syntax-Independent Model for Natural Language

Document Type : Persian Original Article

Authors
Artificial Engineering Department, Faculty of Computer Engineering, K. N. Toosi University of Technology, Tehran, Iran
Abstract
Today, one of the most widely used natural language representation methods is meaning representation for text processing in different systems. Meaning representation methods have had many applications in the field of natural language processing in recent years, including automatic text summarization systems and question and answer systems, etc. Many text expressions may be different in terms of grammatical structure, but they are the same in terms of meaning, so how to apply a single and uniform meaning to them is one of the challenges of text processing. The main goal of this paper is to design an Integrated Semantic Representation (ISR) model for natural language. The proposed model, while maintaining its simplicity in annotation and understanding, does not depend on specific natural language features or on syntactic and lexical structure. In this regard, several examples in both English and Persian language, which have different in terms of written and grammatical structure, are presented in this paper. Moreover, by using the proposed model, the same representation is provided for texts with the same meaning and different grammatical structure. The proposed model is designed in graph and list format is recommended to annotate its corpuses. One of the main features of this model is that it can represent semantic relations at both sentence-level and document-level and is able to represent complex and important linguistic phenomena such as aspect, tense, and quantification. The simplicity of the proposed model helps to avoid making language processing slow or complicated in various applications, and the preparation of structures based on this model for different natural languages will not be too complicated, so that it can be used both for natural languages with low resources and for those with various resources. Further, features of the proposed model are compared with one of the most important related works.
Keywords

[1] Tohidi, Nasim; Hasheminejad, Seyed Mohammad Hossein;, "MOQAS: Multi-objective question answering system," Journal of Intelligent & Fuzzy Systems, vol. 36, no. 4, pp. 3495-3512, 2019.
[2] Peng, Xiaochang; Gildea, Daniel, "UofR at SemEval-2016 task 8: Learning synchronous hyperedge replacement grammar for AMR parsing," in In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), San Diego, California, 2016.
[3] Peng, Xiaochang; Song, Linfeng; Gildea, Daniel, "A synchronous hyperedge replacement grammar based approach for AMR parsing," in In Proceedings of the Nineteenth Conference on Computational Natural Language Learning, Beijing, China, 2015.
[4] Flanigan, Jeffrey; Thomson, Sam; Carbonell, Jaime; Dyer, Chris; Smith. Noah A., "A Discriminative Graph-Based Parser for the Abstract Meaning Representation," in Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, Baltimore, Maryland, 2014.
[5] C. Wang, "Abstract Meaning Representation Parsing," PhD thesis, Brandeis University, 2018.
[6] Damonte, Marco; Cohen, Shay B.; Satta, Giorgio, "An Incremental Parser for Abstract Meaning Representation," in Proceedings of EACL, Valencia, Spain, 2017.
[7] Gu, Min; Gu, Yanhui; Luo, Weilan; Xu, Guandong; Yang, Zhenglu; Zhou, Junsheng; Qu, Weiguang, "From text to graph: a general transition-based AMR parsing using neural network," Neural Computing and Applications, 2020.
[8] Barzdins, Guntis; Gosko, Didzis, "RIGA at SemEval- 2016 Task 8: Impact of Smatch Extensions and Character-Level Neural Translation on AMR Parsing Accuracy," in In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), San Diego, California, 2016.
[9] W. C. Mann, "An overview of the Penman text generation system," in In Proceedings of the Third AAAI Conference on Artificial Intelligence, 1983.
[10] Konstas, Ioannis; Iyer, Srinivasan; Yatskar, Mark; Choi, Yejin; Zettlemoyer, Luke, "Neural AMR: Sequence-to-Sequence Models for Parsing and Generation," in In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, Vancouver, Canada, 2017.
[11] Pust, Michael; Hermjakob, Ulf; Knight, Kevin; Marcu, Daniel; May, Jonathan, "Parsing English into Abstract Meaning Representation Using Syntax-Based Machine Translation," in In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, Lisbon, Portugal, 2015.
[12] Tohidi, Nasim; Dadkhah, Chitra, "A Study on Abstract Meaning Representation Applications," in The first Conference on Artificial Intelligence and Smart Computing, Online, 2022.
[13] Jahanbakhsh-Nagadeh, Zoleikha; Feizi-Derakhshi, Mohammad-Reza; Sharifi, Arash;, "A Speech Act Classifier for Persian Texts and its Application in Identifying Rumors," Journal of Soft Computing and Information Technology, vol. 9, no. 1, pp. 18-27, 2020.
[14] Miri; Ali; Razavi, Seyyed Mohammad; Miri, Ismail;, "Ensemble Recognition of Persian Typed Sub-word in limited Space Using Smart weighted voting," Journal of Soft Computing and Information Technology (JSCIT), vol. 10, no. 3, pp. 60-72, 2021.
[15] Farahani, Mehrdad; Gharachorloo, Mohammad; Farahani, Marzieh; Manthouri, Mohammad, "ParsBERT: Transformer-based Model for Persian Language Understanding," Neural Processing Letters, vol. 53, p. 3831–3847, 2021.
[16] Tohidi, Nasim; Dadkhah, Chitra; Rustamov, Rustam B., "Optimizing Persian Multi-objective Question Answering System," International Journal on Technical and Physical Problems of Engineering (IJTPE), vol. 13, no. 46, pp. 62-69, 2021.
[17] Kazemi, Arefeh; Mozafari, Jamshid; Nematbakhsh, Mohammad Ali, "PersianQuAD: The Native Question Answering Dataset for the Persian Language," IEEE Access, vol. 10, pp. 26045-26057, 2022.
[18] Tohidi, Nasim; Hasheminejad, Seyed Mohammad Hossein, "A Practice of Human-Machine Collaboration for Persian Text Summarization," in The 27th International Computer Conference, the Computer Society of Iran, Online, 2022.
[19] Poon, Hoifung; Domingos, Pedro, "Unsupervised Semantic Parsing," in Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, Singapore, 2009.
[20] Chen, Desai; Schneider, Nathan; Das, Dipanjan; Smith, Noah A., "SEMAFOR: Frame Argument Resolution with Log-Linear Models," in Proceedings of the 5th International Workshop on Semantic Evaluation, Uppsala, Sweden, 2010.
[21] Banarescu, Laura; Bonial, Claire; Cai, Shu; Georgescu, Madalina; Griffitt, Kira; Hermjakob, Ulf; Knight, Kevin; Koehn, Philipp; Palmer, Martha; Schneider, Nathan, "Abstract Meaning Representation for Sembanking," in In proceedings of the 7th Linguistic Annotation Workshop & Interoperability with Discourse, Sofia, Bulgaria, 2013.
[22] Kingsbury, Paul; Palmer, Martha, "From TreeBank to PropBank," in Proceedings of the Third International Conference on Language Resources and Evaluation (LREC’02), Las Palmas, Canary Islands - Spain, 2002.
[23] K. Cao, "Learning meaning representations for text generation with deep generative models," PhD thesis, University of Cambridge, 2019.
[24] Knight, Kevin; Badarau, Bianca; Baranescu, Laura; Bonial, Claire; Bardocz, Madalina; Griffitt, Kira; Hermjakob, Ulf; Marcu, Daniel; Palmer, Martha; O'Gorman, Tim; Schneider, Nathan, "Abstract Meaning Representation (AMR) Annotation Release 2.0," Linguistic Data Consortium, Philadelphia, 2017.
[25] Van Gysel, Jens E.L.; Vigus, Meagan; Chun, Jayeol; Lai, Kenneth; Moeller, Sarah; Yao, Jiarui; O’Gorman, Tim; Cowell, Andrew; Croft, William; Huang, Chu-Ren; Hajič, Jan; Martin, James H.; Oepen, Stephan; Palmer, Martha; Pustejovsky, James; et al., "Designing a Uniform Meaning Representation for Natural Language Processing," KI - Künstliche Intelligenz, vol. 35, p. 343–360, 2021.
[26] Damonte, Marco; Cohen, Shay B., "Cross-Lingual Abstract Meaning Representation Parsing," in Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, New Orleans, Louisiana, 2018.
[27] Flanigan, Jeffrey; Dyer, Chris; Smith, Noah A.; Carbonell, Jaime, "Generation from abstract meaning representation using tree transducers," in In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego, California, 2016b.
[28] Gruzitis, Normunds; Gosko, Didzis; Barzdins, Guntis, "RIGOTRIO at SemEval-2017 Task 9: Combining Machine Learning and Grammar Engineering for AMR Parsing and Generation.," in In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), Vancouver, Canada, 2017.
[29] Song, Linfeng; Peng, Xiaochang; Zhang, Yue; Wang, Zhiguo; Gildea, Daniel, "AMR-to-text Generation with Synchronous Node Replacement Grammar," in In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Vancouver, Canada, 2017.
[30] Song, Linfeng; Zhang, Yue; Peng, Xiaochang; Wang, Zhiguo; Gildea, Daniel, "AMR-to-text generation as a Traveling Salesman Problem," in In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, Texas, 2016.
[31] Mille, Simon; Carlini, Roberto; Burga, Alicia; Wanner, Leo , "FORGe at SemEval-2017 Task 9: Deep sentence generation based on a sequence of graph transducers," in In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), Vancouver, Canada, 2017.
[32] Lampouras, Gerasimos; Vlachos, Andreas, "Sheffield at SemEval-2017 Task 9: Transition-based language generation from AMR," in In Proceedings of the 11th InternationalWorkshop on Semantic Evaluation (SemEval-2017), Vancouver, Canada, 2017.
[33] T. Schick, "Transition-Based Generation from Abstract Meaning Representations," Master’s thesis, 2017.
[34] Y. H. Gao, "English Semantic Recognition Based on Abstract Meaning Representation and Vector Space Model," Journal of Physics: Conference Series, vol. 1087, no. 5, 2018.
[35] Ribeiro, Leonardo; Gardent, Claire; Gurevych, Iryna, "Enhancing AMR-to-Text Generation with Dual Graph Representations," in Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Hong Kong, China, 2019.
[36] Lai, Kenneth; Donatelli, Lucia; Pustejovsky, James, "A Continuation Semantics for Abstract Meaning Representation," The Second International Workshop on Designing Meaning Representations, Barcelona, Spain, 2020.
[37] Ilmy, Adylan Roaffa; Khodra, Masayu Leylia, "Parsing Indonesian Sentence into Abstract Meaning Representation using Machine Learning Approach," arXiv, 2021.
[38] S. Haddadan and M. Bahrani, "Persian Abstractive Summarization using Graph-based Abstract Meaning Representation," Languages and Linguistics Center, Sharif University of Technology, Tehran, Iran, 2017.
[39] Kakaei, Farokh; Rahimi, Saeed; Bahrani, Mohammad, "Generating Text from Abstract Meaning Representation in Persian," Languages and Linguistics Center, Sharif University of Technology, Tehran, Iran, 2020.
[40] Tohidi, Nasim; Dadkhah, Chitra, "A Short Review of Abstract Meaning Representation Applications," Journal of Modeling & Simulation in Electrical & Electronics Engineering, vol. 2, no. 3, pp. 1-9, 2022.
[41] Palmer, Martha; Gildea, Daniel; Kingsbury, Paul, "The Proposition Bank: An Annotated Corpus of Semantic Roles," Computational Linguistics, vol. 31, no. 1, pp. 71-106, 2005.
[42] Mirzaei, Azadeh; Moloodi, Amirsaeid, "Persian Proposition Bank," in 10th edition of the Language Resources and Evaluation Conference, 2016.
[43] Barhom, Shany; Shwartz, Vered; Eirew, Alon; Bugert, Michael; Reimers, Nils; Dagan, Ido;, "Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolution," in The 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, 2019.
[44] Jurafsky, Daniel; Martin, James H. , Speech and Language Processing, Prentice Hall, 2021.
[45] Guo, Zhijiang; Lu, Wei;, "Better Transition-Based AMR Parsing with a Refined Search Space," in The 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, 2018.
[46] Cai, Shu; Knight, Kevin, "Smatch: an Evaluation Metric for Semantic Feature Structures," in The 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Sofia, Bulgaria, 2013.