مجله علمی  رایانش نرم و فناوری اطلاعات

مجله علمی رایانش نرم و فناوری اطلاعات

ISR-Model: مدل بازنمایی معنای یکپارچه زبان طبیعی مستقل از ساختار نحوی

نوع مقاله : مقاله پژوهشی فارسی

نویسندگان
1 گروه هوش‌مصنوعی، دانشکده مهندسی کامپیوتر، دانشگاه صنعتی خواجه نصیرالدین طوسی، تهران، ایران
2 گروه هوش مصنوعی دانشکده مهندسی کامپیوتر دانشگاه خواجه نصیرالدین طوسی، تهران، ایران.
چکیده
امروزه یکی از پرکاربردترین روش‌های بازنمایی زبان طبیعی، بازنمایی معنا جهت پردازش متون در سامانه‌های مختلف است. روش‌های بازنمایی معنا در سال‌های اخیر کاربردهای متعددی در حوزه پردازش زبان طبیعی از جمله سامانه‌های خلاصه‌سازی خودکار متن و سامانه‌های پرسش و پاسخ و غیره داشته‌اند. بسیاری از عبارات متنی ممکن است از لحاظ ساختار گرامری متفاوت، اما از نظر معنایی یکسانی باشند، لذا چگونگی اطلاق یک معنای یکسان و واحد به آن‌ها یکی از چالش‌های پردازش متن است. هدف اصلی این مقاله طراحی مدلی برای بازنمایی معنایی یکپارچه و مستقل از ساختار نحوی برای زبان طبیعی است. مدل پیشنهاد شده با حفظ سادگی خود در حاشیه‌نویسی و درک، عدم وابستگی به ویژگی‌های زبان طبیعی خاص و همچنین عدم وابستگی به ساختار نحوی و لغوی را دارد. در این راستا، مثال‌های از جملات زبان فارسی و انگلیسی که از نظر ساختار گرامری وتفاوت‌ هایی با یکدیگر دارند، در مقاله با روش بازنمایی پیشنهادی ارائه شده‌اند. به علاوه، با استفاده از مدل پیشنهادی، بازنمایی یکسانی برای متون با معنای یکسان و در عین حال ساختار گرامری متفاوت ارائه می‌گردد. مدل پیشنهادی در قالب گراف و لیست جهت تفسیر در پیکره طراحی شده است. یکی از ویژگی‌های اصلی مدل پیشنهادی، قابلیت بازنمایی روابط معنایی در سطح جمله و در سطح سند جهت بازنمایی پدیده‌های پیچیده و مهم زبانی مانند جنبه، زمان و سورها است. سادگی مدل پیشنهادی سبب می‌گردد که پردازش‌های زبانی در کاربردهای مختلف کند ویا پیچیده نشود، و تهیه پیکره‌های مبتنی بر این مدل در آینده برای زبان‌های طبیعی مختلف پیچیدگی زیادی نداشته باشد، تا هم برای زبان‌های طبیعی با منابع محدود و هم برای زبان‌های طبیعی با امکانات کامل قابل بهره‌برداری باشد. همچنین، ویژگی‌های مدل پیشنهادی با یکی از مهم‌ترین کارهای مرتبط پیشین مقایسه شده است.
کلیدواژه‌ها

[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.