Abstract
Implicit discourse relation recognition is a challenging task due to the absence of the necessary informative clues from explicit connectives. An implicit discourse relation recognizer has to carefully tackle the semantic similarity of sentence pairs and the severe data sparsity issue. In this article, we learn token embeddings to encode the structure of a sentence from a dependency point of view in their representations and use them to initialize a baseline model to make it really strong. Then, we propose a novel memory component to tackle the data sparsity issue by allowing the model to master the entire training set, which helps in achieving further performance improvement. The memory mechanism adequately memorizes information by pairing representations and discourse relations of all training instances, thus filling the slot of the data-hungry issue in the current implicit discourse relation recognizer. The proposed memory component, if attached with any suitable baseline, can help in performance enhancement. The experiments show that our full model with memorizing the entire training data provides excellent results on PDTB and CDTB datasets, outperforming the baselines by a fair margin.
- . 2018. Deep enhanced representation for implicit discourse relation recognition. In Proceedings of the 27th International Conference on Computational Linguistics (COLING’18). 571–583.Google Scholar
- . 2015. Comparing word representations for implicit discourse relation classification. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’15). 2201–2211.Google Scholar
Cross Ref
- . 2018. A full end-to-end semantic role labeler, syntactic-agnostic over syntactic-aware? In Proceedings of the 27th International Conference on Computational Linguistics (COLING’18). 2753–2765.Google Scholar
- . 2016a. Discourse relations detection via a mixed generative-discriminative framework. In Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI’16). 2921–2927. Google Scholar
Digital Library
- . 2016b. Implicit discourse relation detection via a deep architecture with gated relevance network. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL’16). 1726–1735.Google Scholar
Cross Ref
- . 2018. Improving implicit discourse relation classification by modeling inter-dependencies of discourse units in a paragraph. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL:HLT’18). 141–151.Google Scholar
Cross Ref
- . 2017. Ontology-aware token embeddings for prepositional phrase attachment. In Proceedings of the Association for Computational Linguistics (ACL’17).Google Scholar
Cross Ref
- . 2017. Language modeling with gated convolutional networks. In Proceedings of the International Conference on Machine Learning. PMLR, 933–941. Google Scholar
Digital Library
- . 2017. Deep biaffine attention for neural dependency parsing. In Proceedings of the International Conference on Learning Representations (ICLR’17).Google Scholar
- . 2014. Abstractive summarization of product reviews using discourse structure. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’14). 1602–1613.Google Scholar
Cross Ref
- . 2018. Implicit discourse relation recognition using neural tensor network with interactive attention and sparse learning. In Proceedings of the 27th International Conference on Computational Linguistics (COLING’18). 547–558.Google Scholar
- . 2018. Syntax for semantic role labeling, to be, or not to be. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL’18). 2061–2071.Google Scholar
Cross Ref
- . 2015. An improved non-monotonic transition system for dependency parsing. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’15). 1373–1378.Google Scholar
Cross Ref
- . 2014. Discourse complements lexical semantics for non-factoid answer reranking. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL’14). 977–986.Google Scholar
Cross Ref
- . 2015. One vector is not enough: Entity-augmented distributed semantics for discourse relations. Trans. Assoc. Comput. Linguist. 3 (2015), 329–344.Google Scholar
Cross Ref
- . 2016. A latent variable recurrent neural network for discourse-driven language models. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL:HLT’16). 332–342.Google Scholar
Cross Ref
- . 2018. Modeling discourse cohesion for discourse parsing via memory network. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL’18). 438–443.Google Scholar
Cross Ref
- . 2018. A knowledge-augmented neural network model for implicit discourse relation classification. In Proceedings of the 27th International Conference on Computational Linguistics (COLING’18). 584–595.Google Scholar
- . 2016. Ask me anything: Dynamic memory networks for natural language processing. In Proceedings of the International Conference on Machine Learning (ICML’16). 1378–1387. Google Scholar
Digital Library
- . 2017. Multi-task attention-based neural networks for implicit discourse relationship representation and identification. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’17). 1299–1308.Google Scholar
Cross Ref
- . 2017. SWIM: A simple word interaction model for implicit discourse relation recognition. In Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI’17). 4026–4032. Google Scholar
Digital Library
- . 2018. Linguistic properties matter for implicit discourse relation recognition: Combining semantic interaction, topic continuity and attribution. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI’18). 4848–4855. Google Scholar
Digital Library
- . 2020. Memory network for linguistic structure parsing. IEEE/ACM Trans. Audio, Speech, Lang. Process. 28 (2020), 2743–2755.Google Scholar
Digital Library
- . 2019. Dependency or span, end-to-end uniform semantic role labeling. In Proceedings of the 33rd Conference of the Association for the Advancement of Artificial Intelligence (AAAI’19), Vol. 33. 6730–6737. Google Scholar
Digital Library
- . 2009. Recognizing implicit discourse relations in the Penn Discourse Treebank. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’09). 343–351. Google Scholar
Digital Library
- . 2018. Learning domain representation for multi-domain sentiment classification. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL:HLT’18). 541–550.Google Scholar
Cross Ref
- . 2016. Recognizing implicit discourse relations via repeated reading: Neural networks with multi-level attention. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’16). 1224–1233.Google Scholar
Cross Ref
- . 2016. Implicit discourse relation classification via multi-task neural networks. In Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI’16). Google Scholar
Digital Library
- . 2016. Multiplicative representations for unsupervised semantic role induction. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL’16). 118–123.Google Scholar
Cross Ref
- . 2017. Learned in translation: Contextualized word vectors. In Advances in Neural Information Processing Systems. MIT Press, 6294–6305. Google Scholar
Digital Library
- . 2016. Key-Value memory networks for directly reading documents. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’16). 1400–1409.Google Scholar
Cross Ref
- . 2016a. Counter-fitting word vectors to linguistic constraints. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL:HLT’16). 142–148.Google Scholar
- . 2016b. Counter-fitting word vectors to linguistic constraints. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL: HLT’16).Google Scholar
- . 2021. Learning context-aware convolutional filters for implicit discourse relation classification. IEEE/ACM Trans. Audio, Speech, Lang. Process. 29 (2021), 2421–2433.Google Scholar
Cross Ref
- . 2019. DisSent: Learning sentence representations from explicit discourse relations. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL’19). 4497–4510.Google Scholar
Cross Ref
- . 2017. Semi-supervised sequence tagging with bidirectional language models. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL’17). 1756–1765.Google Scholar
Cross Ref
- . 2018. Deep contextualized word representations. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL:HLT’18). 2227–2237.Google Scholar
Cross Ref
- . 2009. Automatic sense prediction for implicit discourse relations in text. In Proceedings of the Joint Conference of the 47th Annual Meeting of he Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing (ACL-IJCNLP’09). 683–691. Google Scholar
Digital Library
- . 2019. Implicit discourse relation classification with syntax-aware contextualized word representations. In Proceedings of the 32nd International Flairs Conference.Google Scholar
- . 2008. The Penn Discourse TreeBank 2.0. In Proceedings of the 6th conference on International Language Resources and Evaluation (LREC’08). 2961–2968.Google Scholar
- . 2016a. Implicit discourse relation recognition with context-aware character-enhanced embeddings. In Proceedings of the 26th International Conference on Computational Linguistics (COLING’16). 1914–1924.Google Scholar
- . 2016b. Shallow discourse parsing using convolutional neural network. In Proceedings of the 20th Conference on Computational Natural Language Learning (CoNLL’16). 70–77.Google Scholar
Cross Ref
- . 2016c. A stacking gated neural architecture for implicit discourse relation classification. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’16). 2263–2270.Google Scholar
Cross Ref
- . 2017. Adversarial connective-exploiting networks for implicit discourse relation classification. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL’17). 1006–1017.Google Scholar
Cross Ref
- . 2017. A recurrent neural model with attention for the recognition of Chinese implicit discourse relations. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL’17). 256–262.Google Scholar
Cross Ref
- . 2017. A systematic study of neural discourse models for implicit discourse relation. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL’17). 281–291.Google Scholar
Cross Ref
- . 2015. Improving the inference of implicit discourse relations via classifying explicit discourse connectives. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL:HLT’15). 799–808.Google Scholar
Cross Ref
- . 2016. Robust non-explicit neural discourse parser in English and Chinese. In Proceedings of the 20th Conference on Computational Natural Language Learning (CoNLL’16). 55–59.Google Scholar
Cross Ref
- . 2018. Contextualized word representations for reading comprehension. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 554–559.Google Scholar
Cross Ref
- . 2016. Do we really need all those rich linguistic features? A neural network-based approach to implicit sense labeling. In Proceedings of the 20th Conference on Computational Natural Language Learning (CoNLL’16). 41–49.Google Scholar
Cross Ref
- . 2016. Neural machine translation of rare words with subword units. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL’16). 1715–1725.Google Scholar
Cross Ref
- . 2019. Learning to explicitate connectives with Seq2Seq network for implicit discourse relation classification. In Proceedings of the 13th International Conference on Computational Semantics. 188–199.Google Scholar
Cross Ref
- . 2015. Training very deep networks. In Proceedings of the 28th International Conference on Neural Information Processing Systems. MIT Press, Cambridge, MA, 2377–2385. Google Scholar
Digital Library
- . 2015. End-To-End memory networks. In Advances in Neural Information Processing Systems, vol. 28. MIT Press, 2440–2448. Google Scholar
Digital Library
- . 2017. Learning to embed words in context for syntactic tasks. In Proceedings of the 2nd Workshop on Representation Learning for NLP. 26–275.Google Scholar
Cross Ref
- . 2019. Employing the correspondence of relations and connectives to identify implicit discourse relations via label embeddings. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL’19). 4201–4207.Google Scholar
- . 2015. Memory networks. In Proceedings of the International Conference on Learning Representations (ICLR’15).Google Scholar
- . 2016. Dynamic memory networks for visual and textual question answering. In Proceedings of the International Conference on Machine Learning (ICML’16). 2397–2406. Google Scholar
Digital Library
- . 2018. Using active learning to expand training data for implicit discourse relation recognition. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’18). 725–731.Google Scholar
Cross Ref
- . 2015. The CoNLL-2015 shared task on shallow discourse parsing. In Proceedings of the 19th Conference on Computational Natural Language Learning (CoNLL’15). 1–16.Google Scholar
Cross Ref
- . 2016. CoNLL 2016 shared task on multilingual shallow discourse parsing. In Proceedings of the 20th Conference on Computational Natural Language Learning (CoNLL’16). 1–19.Google Scholar
Cross Ref
- . 2015. Shallow convolutional neural network for implicit discourse relation recognition. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’15). 2230–2235.Google Scholar
Cross Ref
- . 2019. Semantic graph convolutional network for implicit discourse relation classification. Retrieved from https://arxiv.org/abs/1910.09183.Google Scholar
- . 2012. PDTB-style discourse annotation of Chinese text. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (ACL’12). 69–77. Google Scholar
Digital Library
Index Terms
Memorizing All for Implicit Discourse Relation Recognition
Recommendations
Learning explicit and implicit Arabic discourse relations
We propose in this paper a supervised learning approach to identify discourse relations in Arabic texts. To our knowledge, this work represents the first attempt to focus on both explicit and implicit relations that link adjacent as well as non adjacent ...
Predicting discourse connectives for implicit discourse relation recognition
COLING '10: Proceedings of the 23rd International Conference on Computational Linguistics: PostersExisting works indicate that the absence of explicit discourse connectives makes it difficult to recognize implicit discourse relations. In this paper we attempt to overcome this difficulty for implicit relation recognition by automatically inserting ...
The Chinese Discourse TreeBank: a Chinese corpus annotated with discourse relations
The paper presents the Chinese Discourse TreeBank, a corpus annotated with Penn Discourse TreeBank style discourse relations that take the form of a predicate taking two arguments. We first characterize the syntactic and statistical distributions of ...






Comments