--- title: "Using Phrasal Patterns to Identify Discourse — Saito 2006" description: "The paper addresses automatic recognition of the discourse relation linking two adjacent Japanese sentences when no explicit connective is available." authors: ["Manami Saito", "Kazuhide Yamamoto", "Satoshi Sekine"] year: 2006 venue: "Proceedings of the Human Language Technology Conference of the NAACL, Companion Volume: Short Papers" source: "https://aclanthology.org/N06-2034/" licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)" licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/papers/saito-2006-phrasal-patterns-identify-discourse-relations/" --- [Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/saito-2006-phrasal-patterns-identify-discourse-relations/) [home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2006](https://md.research.elamur.ai/free/papers/2006/) / Using Phrasal Patterns to Identify Discourse Relations # Using Phrasal Patterns to Identify Discourse Relations **Authors:** Manami Saito, Kazuhide Yamamoto, Satoshi Sekine · **Year:** 2006 · **Venue:** Proceedings of the Human Language Technology Conference of the NAACL, Companion Volume: Short Papers · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/) **Links:** [Publisher's page](https://aclanthology.org/N06-2034/) · [PDF](https://aclanthology.org/N06-2034.pdf) · [OpenAlex](https://openalex.org/W2034087555) **Citations:** 36 citations (openalex-snapshot · 2026-10-14) · [14](#cited-by) in our library, of the 140673 papers whose bibliographies we read ## Summary The paper addresses automatic recognition of the discourse relation linking two adjacent Japanese sentences when no explicit connective is available. Following Marcu and Echihabi (2002), the authors build training data automatically. They collect sentence pairs whose second sentence opens with an unambiguous cue phrase and treat that cue as the relation label. The cue phrases come from the ChaSen dictionary and are grouped into classes adapted from Ichikawa. The data comes from roughly 20G of Web text and 38 years of newspapers. Two evidence sources are combined: - **Lexical:** cross-sentence word pairs, restricted by part of speech and marked for negation. - **Phrasal patterns:** combinations of bunsetsu fragments in which function words are required and content words are optional. Frequency-based scores, some corrected for class priors, are merged by a simple decision rule. Phrasal patterns raise weighted accuracy from 53% to 65%. That result roughly matches human judges given the same two-sentence context. It shows that grammatical, function-word structure carries discourse signal beyond lexical content. ## Key points - **Relation inventory:** 167 cue phrases from ChaSen (IPADIC, Ver.2.7.0) are mapped to 7 classes. OTHER is dropped, leaving six: ELABORATION (43.0% of the corpus), CONTRAST (32.2%), CAUSE-EFFECT, EQUIVALENCE, CHANGE-TOPIC and EXAMPLE. - **Data:** about 1,300,000 sentence pairs come from the Web and about 150,000 from newspapers. A balanced test set of 300 pairs (50 per relation) is held out. - **Pattern construction:** every pattern must contain a minimum of three subphrases, and both sentences must contribute one or more of them. Patterns seen more than 1000 times are discarded as uninformative. A single example pair yields 348 distinct patterns. - **Results:** unweighted accuracy rises from 57% to 64%, and weighted accuracy from 53% to 65%. The majority baseline is 43%, and Marcu and Echihabi reported 49.7% in a comparable setup. CONTRAST benefits most, rising from 62% to 86%. - **Human comparison:** three annotators scored 63%, 54% and 48%, with 69% average inter-annotator agreement. System accuracy was 71% on items all three humans got right and 47% on items none of them did. *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/shelves/linguistics/) Topics: [Discourse analysis](https://md.research.elamur.ai/free/topics/discourse-analysis/) ## Cited by Cited by 14 papers of our library cite it (of the 140673 whose bibliographies we read); 7 of them have a page here, 7 not yet. - [Leveraging Synthetic Discourse Data via Multi-task Learning for Implicit Discourse Relation Recognition](https://md.research.elamur.ai/free/papers/lan-2013-leveraging-synthetic-discourse-data-multi/) - [Recognizing Implicit Discourse Relations in the Penn Discourse Treebank](https://md.research.elamur.ai/free/papers/lin-2009-recognizing-implicit-discourse-relations-penn/) - [What Causes the Failure of Explicit to Implicit Discourse Relation Recognition?](https://md.research.elamur.ai/free/papers/liu-2024-what-causes-failure-explicit-implicit/) - [Kernel Based Discourse Relation Recognition with Temporal Ordering Information](https://md.research.elamur.ai/free/papers/wang-2010-kernel-based-discourse-relation-recognition/) - [Implicit Discourse Relation Recognition by Selecting Typical Training Examples](https://md.research.elamur.ai/free/papers/wang-2012-implicit-discourse-relation-recognition-selecting/) - [The Effects of Discourse Connectives Prediction on Implicit Discourse Relation Recognition](https://md.research.elamur.ai/free/papers/zhou-2010-effects-discourse-connectives-prediction-implicit/) - [Predicting Discourse Connectives for Implicit Discourse Relation Recognition](https://md.research.elamur.ai/free/papers/zhou-2010-predicting-discourse-connectives-implicit-discourse/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{saito2006using, title = {{Using Phrasal Patterns to Identify Discourse Relations}}, author = {Saito, Manami and Yamamoto, Kazuhide and Sekine, Satoshi}, booktitle = {Proceedings of the Human Language Technology Conference of the NAACL, Companion Volume: Short Papers}, year = {2006}, doi = {10.3115/1614049.1614083}, url = {https://doi.org/10.3115/1614049.1614083} } ``` - [← previous Using Lexical Dependency and Ontological Knowledge to Improve a Detailed Syntactic and Semantic Tagger of English](https://md.research.elamur.ai/free/papers/finch-2006-lexical-dependency-ontological-knowledge-improve/) - [next → Va'yehi as a Discourse Marker in Kings](https://md.research.elamur.ai/free/papers/hbo-2006-li-va-yehi-discourse-marker-kings/) - [↑ back to papers of 2006](https://md.research.elamur.ai/free/papers/2006/) ## References 3 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Daniel Marcu and Abdessamad Echihabi. 2002. An Unsupervised Approach to Recognizing Discourse Relations, Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, 368-375. [find](https://scholar.google.com/scholar?q=Daniel+Marcu+and+Abdessamad+Echihabi%2E+2002%2E+An+Unsupervised+Approach+to+Recognizing+Discourse+Relations%2C+Proceedings+of+the+40th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+368%2D37) [our card](https://md.research.elamur.ai/free/papers/marcu-2002-unsupervised-approach-recognizing-discourse-relations/) 2. Florian Wolf and Edward Gibson. 2005. Representing Discourse Coherence: A Corpus-Based Study, Computational Linguistics, 31(2):249-287. [find](https://scholar.google.com/scholar?q=Florian+Wolf+and+Edward+Gibson%2E+2005%2E+Representing+Discourse+Coherence%3A+A+Corpus%2DBased+Study%2C+Computational+Linguistics%2C+31%282%29%3A249%2D287%2E) [our card](https://md.research.elamur.ai/free/papers/wolf-2005-representing-discourse-coherence-corpus-based/) 3. Takashi Ichikawa. 1978. Syntactic Overview for Japanese Education, Kyo-iku publishing, 65-67 (in Japanese). [find](https://scholar.google.com/scholar?q=Takashi+Ichikawa%2E+1978%2E+Syntactic+Overview+for+Japanese+Education%2C+Kyo%2Diku+publishing%2C+65%2D67+%28in+Japanese%29%2E)