--- title: "Discriminative Approach to Predicate-Argument — Imamura 2009" description: "Japanese sentences often leave arguments unexpressed as zero pronouns." authors: ["Kenji Imamura", "Kuniko Saito", "Tomoko Izumi"] year: 2009 venue: "Proceedings of the ACL-IJCNLP 2009 Conference Short Papers" source: "https://aclanthology.org/P09-2022/" 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/imamura-2009-discriminative-approach-predicate-argument-structure/" --- [Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/imamura-2009-discriminative-approach-predicate-argument-structure/) [home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2009](https://md.research.elamur.ai/free/papers/2009/) / Discriminative Approach to Predicate-Argument Structure Analysis with Zero-Anaphora Resolution # Discriminative Approach to Predicate-Argument Structure Analysis with Zero-Anaphora Resolution **Authors:** Kenji Imamura, Kuniko Saito, Tomoko Izumi · **Year:** 2009 · **Venue:** Proceedings of the ACL-IJCNLP 2009 Conference 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/P09-2022/) · [PDF](https://aclanthology.org/P09-2022.pdf) · [OpenAlex](https://openalex.org/W2098132066) **Citations:** 47 citations (openalex-snapshot · 2026-10-14) · [30](#cited-by) in our library, of the 140673 papers whose bibliographies we read ## Summary Japanese sentences often leave arguments unexpressed as zero pronouns. Purely syntactic, sentence-level analysis therefore cannot recover full predicate-argument structures. The authors combine predicate-argument structure analysis and zero-anaphora resolution into a single supervised selection task. For each predicate, the candidate pool contains noun phrases from the predicate's own sentence, selected phrases from earlier sentences, and a special NULL option for exophoric or absent arguments. Separate maximum entropy models for the nominative, accusative and dative cases each choose the best candidate. Because the models are discriminative, new features are easy to add. The authors add three kinds: - dependency-based language model scores trained on newspaper text, - centering-inspired contextual cues, - a context-based filter that shrinks the candidate set. Experiments use the NAIST Text Corpus and the Kyoto Text Corpus with gold parses. Arguments that directly depend on the predicate are identified well. Zero-anaphoric arguments, especially those in other sentences, are rarely recovered because the model tends to prefer NULL. The work shows that a unified, feature-extensible framework can handle both tasks together. ## Key points - **Data:** NAIST Text Corpus v1.4b aligned with Kyoto Text Corpus 4.0 (newspaper articles). The training set has 1,751 articles and 67,145 predicates; the test set has 695 articles and 25,500 predicates. - **Language model features:** Generation probabilities P(n|c,v) were estimated from Mainichi Shinbun articles (1991–2002, about 5.5M sentences), with Good-Turing discounting and backoff smoothing. - **Contextual features and filtering:** - The 'Used' feature marks phrases that served as arguments of earlier predicates. - The 'SRLOrder' feature takes a phrase's rank in the Salience Reference List (Nariyama, 2002). - The candidate filter cuts the average pool from 102.2 to 3.2 phrases while still covering 62.5% of zero-pronoun referents. - **Overall results:** Predicate-argument accuracy was 59.4% (15,140/25,500). Case-level F-scores were 73.2% (nominative), 89.2% (accusative) and 76.6% (dative). Directly dependent arguments exceeded 80% F in every case. - **Main weakness:** Recall on inter-sentential nominative zero anaphora was only 7.6%. The system produced 488 such arguments against 3,063 in the gold standard, reflecting a strong bias toward NULL. *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: [Coreference resolution](https://md.research.elamur.ai/free/topics/coreference-resolution/) · [Semantic role labeling](https://md.research.elamur.ai/free/topics/semantic-role-labeling/) ## Cited by Cited by 30 papers of our library cite it (of the 140673 whose bibliographies we read); 9 of them have a page here, 21 not yet. - [Cross-lingual Zero Pronoun Resolution](https://md.research.elamur.ai/free/papers/aloraini-2020-cross-lingual-zero-pronoun-resolution/) - [Chinese Zero Pronoun Resolution: An Unsupervised Probabilistic Model Rivaling Supervised Resolvers](https://md.research.elamur.ai/free/papers/chen-2014-chinese-zero-pronoun-resolution-unsupervised/) - [Chinese Zero Pronoun Resolution: A Joint Unsupervised Discourse-Aware Model Rivaling State-of-the-Art Resolvers](https://md.research.elamur.ai/free/papers/chen-2015-chinese-zero-pronoun-resolution-joint/) - [Chinese Zero Pronoun Resolution with Deep Neural Networks](https://md.research.elamur.ai/free/papers/chen-2016-chinese-zero-pronoun-resolution-deep/) - [A Cross-Lingual ILP Solution to Zero Anaphora Resolution](https://md.research.elamur.ai/free/papers/iida-2011-cross-lingual-ilp-solution-zero/) - [Intra-sentential Zero Anaphora Resolution using Subject Sharing Recognition](https://md.research.elamur.ai/free/papers/iida-2015-intra-sentential-zero-anaphora-resolution/) - [Intra-Sentential Subject Zero Anaphora Resolution using Multi-Column Convolutional Neural Network](https://md.research.elamur.ai/free/papers/iida-2016-intra-sentential-subject-zero-anaphora/) - [A Discriminative Approach to Japanese Zero Anaphora Resolution with Large-scale Lexicalized Case Frames](https://md.research.elamur.ai/free/papers/sasano-2011-discriminative-approach-japanese-zero-anaphora/) - [Chinese Zero Pronoun Resolution with Deep Memory Network](https://md.research.elamur.ai/free/papers/yin-2017-chinese-zero-pronoun-resolution-deep/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{imamura2009discriminative, title = {{Discriminative Approach to Predicate-Argument Structure Analysis with Zero-Anaphora Resolution}}, author = {Imamura, Kenji and Saito, Kuniko and Izumi, Tomoko}, booktitle = {Proceedings of the ACL-IJCNLP 2009 Conference Short Papers}, year = {2009}, doi = {10.3115/1667583.1667611}, url = {https://doi.org/10.3115/1667583.1667611} } ``` - [← previous Detecting Compositionality in Multi-Word Expressions](https://md.research.elamur.ai/free/papers/aclbulk-2009-korkontzelos-detecting-compositionality-multi-word-expressions/) - [next → Domain Adaptation for Statistical Machine Translation with Monolingual Resources](https://md.research.elamur.ai/free/papers/bertoldi-2009-domain-adaptation-statistical-machine-translation/) - [↑ back to papers of 2009](https://md.research.elamur.ai/free/papers/2009/) ## References 5 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Ryu Iida, Mamoru Komachi, Kentaro Inui, and Yuji Matsumoto. 2007. Annotating a Japanese text corpus with predicate-argument and coreference relations. In Proceedings of the Linguistic Annotation Workshop in ACL-2007, pages 132–139. [find](https://scholar.google.com/scholar?q=Ryu+Iida%2C+Mamoru+Komachi%2C+Kentaro+Inui%2C+and+Yuji+Matsumoto%2E+2007%2E+Annotating+a+Japanese+text+corpus+with+predicate%2Dargument+and+coreference+relations%2E+In+Proceedings+of+the+Linguistic+Annotation+Works) [our card](https://md.research.elamur.ai/free/papers/iida-2007-annotating-japanese-text-corpus-predicate/) 2. Zheng Ping Jiang and Hwee Tou Ng. 2006. Semantic role labeling of nombank: A maximum entropy approach. In Proceedings of EMNLP-2006, pages 138–145. [find](https://scholar.google.com/scholar?q=Zheng+Ping+Jiang+and+Hwee+Tou+Ng%2E+2006%2E+Semantic+role+labeling+of+nombank%3A+A+maximum+entropy+approach%2E+In+Proceedings+of+EMNLP%2D2006%2C+pages+138%E2%80%93145%2E) 3. Shigeko Nariyama. 2002. Grammar for ellipsis resolution in Japanese. In Proceedings of TMI-2002, pages 135–145. [find](https://scholar.google.com/scholar?q=Shigeko+Nariyama%2E+2002%2E+Grammar+for+ellipsis+resolution+in+Japanese%2E+In+Proceedings+of+TMI%2D2002%2C+pages+135%E2%80%93145%2E) 4. Ryohei Sasano, Daisuke Kawahara, and Sadao Kurohashi. 2008. A fully-lexicalized probabilistic model for Japanese zero anaphora resolution. In Proceedings of COLING-2008, pages 769–776. [find](https://scholar.google.com/scholar?q=Ryohei+Sasano%2C+Daisuke+Kawahara%2C+and+Sadao+Kurohashi%2E+2008%2E+A+fully%2Dlexicalized+probabilistic+model+for+Japanese+zero+anaphora+resolution%2E+In+Proceedings+of+COLING%2D2008%2C+pages+769%E2%80%93776%2E) [our card](https://md.research.elamur.ai/free/papers/sasano-2008-fully-lexicalized-probabilistic-model-japanese/) 5. Hirotoshi Taira, Sanae Fujita, and Masaaki Nagata. 2008. A Japanese predicate argument structure analysis using decision lists. In Proceedings of EMNLP-2008, pages 523–532. [find](https://scholar.google.com/scholar?q=Hirotoshi+Taira%2C+Sanae+Fujita%2C+and+Masaaki+Nagata%2E+2008%2E+A+Japanese+predicate+argument+structure+analysis+using+decision+lists%2E+In+Proceedings+of+EMNLP%2D2008%2C+pages+523%E2%80%93532%2E)