--- title: "Using Explicit Discourse Connectives in — Shi 2017" description: "Classifying implicit discourse relations, which are relations between text spans that no connective such as \"because\" or \"but\" signals, remains a weak…" authors: ["Wei Shi", "Frances Yung", "Raphael Rubino", "Vera Demberg"] year: 2017 venue: "Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)" source: "https://aclanthology.org/I17-1049/" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/shi-2017-explicit-discourse-connectives-translation-implicit/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/shi-2017-explicit-discourse-connectives-translation-implicit/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2017](https://md.research.elamur.ai/free/en/papers/2017/page/4/) / Using Explicit Discourse Connectives in Translation for Implicit Discourse Relation Classification # Using Explicit Discourse Connectives in Translation for Implicit Discourse Relation Classification **Authors:** [Wei Shi](https://md.research.elamur.ai/free/en/authors/wei-shi/), [Frances Yung](https://md.research.elamur.ai/free/en/authors/frances-yung/), [Raphael Rubino](https://md.research.elamur.ai/free/en/authors/raphael-rubino/), [Vera Demberg](https://md.research.elamur.ai/free/en/authors/vera-demberg/) · **Year:** 2017 · **Venue:** Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/I17-1049/) · [PDF](https://aclanthology.org/I17-1049.pdf) · [OpenAlex](https://openalex.org/W2775220237) **Citations:** 12 citations (openalex-snapshot · 2026-10-14) · [13](#cited-by) in our library, of the 140884 papers whose bibliographies we read ## Summary Classifying implicit discourse relations, which are relations between text spans that no connective such as "because" or "but" signals, remains a weak point of discourse parsing. One main reason is that PDTB offers little labeled data. The authors propose a way to generate extra training examples from English–French parallel text. Human translators sometimes add a connective that the source lacked (explicitation), and this added connective reveals the intended relation. The pipeline works in four steps: 1. A pre-trained MT system translates the French side back into English. 2. An end-to-end English discourse parser runs on both the original and the back-translated text. 3. The method keeps consecutive sentence pairs that the parser marks as implicit in the source but explicit in the back-translation. 4. Each kept source pair receives the label of the explicit relation. This yields a training set several times larger than PDTB's. With this added data, a plain bidirectional LSTM beats prior state-of-the-art systems on the PDTB 2.0 test set and in cross-validation. The approach does not depend on any particular classifier, so other implicit relation models could reuse it. ## Key points - PDTB provides only 12763 implicit training instances and a 761-relation test set. Some second-level senses have about a dozen examples. - Back-translating into English lets the method use an English parser and the PDTB label set instead of a target-language parser. MT quality matters mainly for translating the connectives correctly. - Accuracy rises with more mined intra-sentential samples but levels off around 40,000. That setting gave the best averaged accuracy, 45.87%, which beat using all mined samples. - Training on mined samples alone, without PDTB data, performed worse than using PDTB only. - The mined data contains noise, for example "if" wrongly tagged as a connective, which inflates Contingency.Condition. It also captures relation patterns that PDTB does not annotate, such as temporal readings of gerund constructions. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/) Topics: [Discourse analysis](https://md.research.elamur.ai/free/en/topics/discourse-analysis/) ## Cited by Cited by 13 papers of our library cite it (of the 140884 whose bibliographies we read); 6 of them have a page here, 7 not yet. - [CVAE-based Re-anchoring for Implicit Discourse Relation Classification](https://md.research.elamur.ai/free/en/papers/dou-2021-cvae-based-re-anchoring-implicit/) - [Annotation-Inspired Implicit Discourse Relation Classification with Auxiliary Discourse Connective Generation](https://md.research.elamur.ai/free/en/papers/liu-2023-annotation-inspired-implicit-discourse-relation/) - [Acquiring Annotated Data with Cross-lingual Explicitation for Implicit Discourse Relation Classification](https://md.research.elamur.ai/free/en/papers/shi-2019-acquiring-annotated-data-cross-lingual/) - [Learning to Explicitate Connectives with Seq2Seq Network for Implicit Discourse Relation Classification](https://md.research.elamur.ai/free/en/papers/shi-2019-learning-explicitate-connectives-seq2seq-network/) - [Next Sentence Prediction helps Implicit Discourse Relation Classification within and across Domains](https://md.research.elamur.ai/free/en/papers/shi-2019-next-sentence-prediction-helps-implicit/) - [Topic Tensor Network for Implicit Discourse Relation Recognition in Chinese](https://md.research.elamur.ai/free/en/papers/xu-2019-topic-tensor-network-implicit-discourse/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{shi2017using, title = {{Using Explicit Discourse Connectives in Translation for Implicit Discourse Relation Classification}}, author = {Shi, Wei and Yung, Frances and Rubino, Raphael and Demberg, Vera}, booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)}, year = {2017}, doi = {10.22028/d291-30793}, url = {https://doi.org/10.22028/d291-30793} } ``` - [← previous Using Electronic Dictionaries and NooJ to Generate Sentences Containing English Phrasal Verbs](https://md.research.elamur.ai/free/en/papers/machonis-2017-electronic-dictionaries-nooj-generate-sentences/) - [next → Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm](https://md.research.elamur.ai/free/en/papers/felbo-2017-millions-emoji-occurrences-learn-any/) - [↑ back to papers of 2017](https://md.research.elamur.ai/free/en/papers/2017/page/4/) ## References 4 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Fatemeh Torabi Asr and Vera Demberg. 2012. Implicitness of discourse relations. In Proceedings of COLING 2012. [find](https://scholar.google.com/scholar?q=Fatemeh+Torabi+Asr+and+Vera+Demberg%2E+2012%2E+Implicitness+of+discourse+relations%2E+In+Proceedings+of+COLING+2012%2E) [our card](https://md.research.elamur.ai/free/en/papers/asr-2012-implicitness-discourse-relations/) 2. The COLING 2012 Organizing Committee, Mumbai, India, pages 2669–2684. [find](https://scholar.google.com/scholar?q=The+COLING+2012+Organizing+Committee%2C+Mumbai%2C+India%2C+pages+2669%E2%80%932684%2E) 3. Or Biran and Kathleen McKeown. 2013. Aggregated word pair features for implicit discourse relation disambiguation. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Sofia, Bulgaria, pages 69–73. [find](https://scholar.google.com/scholar?q=Or+Biran+and+Kathleen+McKeown%2E+2013%2E+Aggregated+word+pair+features+for+implicit+discourse+relation+disambiguation%2E+In+Proceedings+of+the+51st+Annual+Meeting+of+the+Association+for+Computational+Lingui) [our card](https://md.research.elamur.ai/free/en/papers/biran-2013-aggregated-word-pair-features-implicit/) 4. Bruno Cartoni, Sandrine Zufferey, and Thomas Meyer. 2013. Annotating the meaning of discourse connectives by looking at their translation: The translation-spotting technique. D&D 4(2):65–86. [find](https://scholar.google.com/scholar?q=Bruno+Cartoni%2C+Sandrine+Zufferey%2C+and+Thomas+Meyer%2E+2013%2E+Annotating+the+meaning+of+discourse+connectives+by+looking+at+their+translation%3A+The+translation%2Dspotting+technique%2E+D%26D+4%282%29%3A65%E2%80%9386%2E) [our card](https://md.research.elamur.ai/free/en/papers/cartoni-2013-annotating-meaning-discourse-connectives-looking/)