Abstract
Ordering events with temporal relations in texts remains a challenge in natural language processing. In this paper, we introduce a new combined neural network architecture that is capable of classifying temporal relations between events in an Arabic sentence. Our model consists of two branches: the first one extracts the syntactic information and identifies the orientation of the relation between the two given events based on a Shortest Dependency Path (SDP) layer with Long and Short Memory (LSTM), and the second one encourages the model to focus on the important local information when learning sentence representations based on a Bidirectional-LSTM (BiLSTM) attention layer. The experiments suggest that our proposed model outperforms several previous state-of-the-art methods, with an F1-score equal to 86.40%.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
Temporal relations: After, Before, I-before, I-after, Begins, begun-by, Ends, Ends-by, During, During-INV, Includes, IS-Included, Simultaneous, Overlaps, overlapped by, Identity.
- 2.
udpipe tool: http://lindat.mff.cuni.cz/services/udpipe/.
- 3.
Similar events list:( , Perished), ( , Perished), ( , killed), ( , burned), ( , martyred), ( , died), ( , Perished), ( , died), ( , died), ( , died), ( , died), ( , Perished).
- 4.
The enriched corpus can be found at: https://github.com/nafaa5/Enriched-Arabic-TimeML-Corpus.
References
Allen, J.F.: Maintaining knowledge about temporal intervals. Commun. ACM 26, 832–843 (1983)
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: ICLR (2015)
Bethard, S.: Cleartk-timeml: a minimalist approach to tempeval 2013. In: SemEval@NAACL-HLT, vol. 2, pp. 10–14 (2013)
Bsir, B., Zrigui, M.: Document model with attention bidirectional recurrent network for gender identification. In: Rojas, I., Joya, G., Catala, A. (eds.) IWANN 2019. LNCS, vol. 11506, pp. 621–631. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20521-8_51
Bunescu, R.C., Mooney, R.J.: A shortest path dependency kernel for relation extraction. In: HLT/EMNLP, pp. 724–731 (2005)
Chambers, N.: Navytime: event and time ordering from raw text. In: SemEval@NAACL-HLT, vol. 2, pp. 73–77 (2013)
Chambers, N., Cassidy, T., McDowell, B., Bethard, S.: Dense event ordering with a multi-pass architecture. Trans. ACL 2, 273–284 (2014)
Chambers, N., Wang, S., Jurafsky, D.: Classifying temporal relations between events. In: ACL (2007)
Dligach, D., Miller, T., Lin, C., Bethard, S., Savova, G.: Neural temporal relation extraction. In: EACL, vol. 2 (2017)
Do, H.W., Jeong, Y.S.: Temporal relation classification with deep neural network. In: BigComp, pp. 454–457 (2016)
D’Souza, J., Ng, V.: Classifying temporal relations with rich linguistic knowledge. In: HLT-NAACL (2013)
Glavas, G., Šnajder, J.: Construction and evaluation of event graphs. Nat. Lang. Eng. 21(4), 607–652 (2015)
Haffar, N., Hkiri, E., Zrigui, M.: Arabic linguistic resource and specifications for event annotation. In: IBIMA, pp. 4316–4327 (2019)
Haffar, N., Hkiri, E., Zrigui, M.: TimeML annotation of events and temporal expressions in Arabic texts. In: Nguyen, N.T., Chbeir, R., Exposito, E., Aniorté, P., Trawiński, B. (eds.) ICCCI 2019. LNCS (LNAI), vol. 11683, pp. 207–218. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-28377-3_17
Haffar, N., Hkiri, E., Zrigui, M.: Enrichment of Arabic TimeML corpus. In: Nguyen, N.T., Hoang, B.H., Huynh, C.P., Hwang, D., Trawiński, B., Vossen, G. (eds.) ICCCI 2020. LNCS (LNAI), vol. 12496, pp. 655–667. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-63007-2_51
Haffar, N., Hkiri, E., Zrigui, M.: Using bidirectional LSTM and shortest dependency path for classifying Arabic temporal relations. KES. Procedia Comput. Sci. 176, 370–379 (2020)
Hkiri, E., Mallat, S., Zrigui, M.: Events automatic extraction from Arabic texts. Int. J. Inf. Retr. Res. 6(1), 36–51 (2016)
Hkiri, E., Mallat, S., Zrigui, M.: Integrating bilingual named entities lexicon with conditional random fields model for Arabic named entities recognition. In: ICDAR, pp. 609–614. IEEE (2017)
Hkiri, E., Mallat, S., Zrigui, M., Mars, M.: Constructing a lexicon of Arabic-English named entity using SMT and semantic linked data. Int. Arab J. Inf. Technol. 14(6), 820–825 (2017)
Kang, Y., Wei, H., Zhang, H., Gao, G.: Woodblock-printing Mongolian words recognition by bi-LSTM with attention mechanism. In: The International Conference on Document Analysis and Recognition (ICDAR), pp. 910–915 (2019)
Kolya, A.K., Kundu, A., Gupta, R., Ekbal, A., Bandyopadhyay, S.: JU\(\_\)CSE: a CRF based approach to annotation of temporal expression, event and temporal relations. In: SemEval@NAACL-HLT, vol. 2, pp. 64–72 (2013)
Laokulrat, N., Miwa, M., Tsuruoka, Y., Chikayama, T.: Uttime: temporal relation classification using deep syntactic features. In: SemEval@NAACL-HLT, vol. 2, pp. 88–92 (2013)
Li, Z., Cai, J., He, S., Zhao, H.: Seq2seq dependency parsing. In: The 27th International Conference on Computational Linguistics, pp. 3203–3214 (2018)
Lim, C.G., Choi, H.J.: LSTM-based model for extracting temporal relations from Korean text. In: BigComp, pp. 666–668 (2018)
Mahmoud, A., Zrigui, M.: Sentence embedding and convolutional neural network for semantic textual similarity detection in Arabic language. Arab. J. Sci. Eng. 44(11), 9263–9274 (2019)
Mahmoud, A., Zrigui, M.: BLSTM-API: Bi-LSTM recurrent neural network-based approach for Arabic paraphrase identification. Arab. J. Sci. Eng. 46(4), 4163–4174 (2021)
Mani, I., Verhagen, M., Wellner, B., Lee, C.M., Pustejovsky, J.: Machine learning of temporal relations. In: ACL (2006)
Meng, Y., Rumshisky, A., Romanov, A.: Temporal information extraction for question answering using syntactic dependencies in an LSTM-based architecture. In: EMNLP (2017)
Mirza, P., Tonelli, S.: Classifying temporal relations with simple features. In: EACL, pp. 308–317 (2014)
Pandit, O.A., Denis, P., Ralaivola, L.: Learning rich event representations and interactions for temporal relation classification. In: ESANN (2019)
Plank, B., Moschitti, A.: Embedding semantic similarity in tree kernels for domain adaptation of relation extraction. In: ACL, vol. 1, pp. 1498–1507 (2013)
Shen, Y., Huang, X.: Attention-based convolutional neural network for semantic relation extraction. In: COLING, pp. 2526–2536 (2016)
Soliman, A.B., Eissa, K., El-Beltagy, S.R.: Aravec: a set of Arabic word embedding models for use in Arabic NLP. In: ACLING, vol. 117, pp. 256–265 (2017)
Tourille, J., Ferret, O., Névéol, A., Tannier, X.: Neural architecture for temporal relation extraction: a Bi-LSTM approach for detecting narrative containers. In: ACL, vol. 2, pp. 224–230 (2017)
Tran, V.H., Phi, V.T., Shindo, H., Matsumoto, Y.: Relation classification using segment-level attention-based CNN and dependency-based RNN. In: NAACL-HLT, vol. 1, pp. 2793–2798 (2019)
UzZaman, N., Llorens, H., Derczynski, L., Allen, J., Verhagen, M., Pustejovsky, J.: SemEval-2013 task 1: TempEval-3: evaluating time expressions, events, and temporal relations. In: (SemEval-2013), vol. 1 (2013)
Wang, L., Cao, Z., de Melo, G., Liu, Z.: Relation classification via multi-level attention CNNs. In: ACL, vol. 1, pp. 1298–1307 (2016)
Xiao, M., Liu, C.: Semantic relation classification via hierarchical recurrent neural network with attention. In: COLING, pp. 1254–1263 (2016)
Xu, Y., Mou, L., Li, G., Chen, Y., Peng, H., Jin, Z.: Classifying relations via long short term memory networks along shortest dependency paths. In: EMNLP, pp. 1785–1794 (2015)
Zhang, X., Chen, F., Huang, R.: A combination of RNN and CNN for attention-based relation classification. Procedia Comput. Sci. 131, 911–917 (2018)
Zhou, P., et al.: Attention-based bidirectional long short-term memory networks for relation classification. In: ACL, vol. 2, pp. 207–212 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Haffar, N., Ayadi, R., Hkiri, E., Zrigui, M. (2021). Temporal Ordering of Events via Deep Neural Networks. In: Lladós, J., Lopresti, D., Uchida, S. (eds) Document Analysis and Recognition – ICDAR 2021. ICDAR 2021. Lecture Notes in Computer Science(), vol 12822. Springer, Cham. https://doi.org/10.1007/978-3-030-86331-9_49
Download citation
DOI: https://doi.org/10.1007/978-3-030-86331-9_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86330-2
Online ISBN: 978-3-030-86331-9
eBook Packages: Computer ScienceComputer Science (R0)