paper-with-me

Papers

Quantifying Discourse Support for Omitted Pronouns

2022-09-16 · COLING (CRAC) 2022 10 · Shulin Zhang, Jixing Li, John Hale

Pro-drop is commonly seen in many languages, but its discourse motivations have not been well characterized. Inspired by the topic chain theory in Chinese, this study shows how character-verb usage continuity distinguishes dropped pronouns from overt references to story characters. We model the choice to drop vs. not drop as a function of character-verb continuity. The results show that omitted subjects have higher character history-current verb continuity salience than non-omitted subjects. This is consistent with the idea that discourse coherence with a particular topic, such as a story character, indeed facilitates the omission of pronouns in languages and contexts where they are optional.

📄 PDF Abstract BibTeX arXiv:2209.07961

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

One Model to Learn Both: Zero Pronoun Prediction and Translation

2019-09-01 · IJCNLP 2019 11 · Long-Yue Wang, Zhaopeng Tu, Xing Wang, Shuming Shi

Zero pronouns (ZPs) are frequently omitted in pro-drop languages, but should be recalled in non-pro-drop languages. This discourse phenomenon poses a significant challenge for machine translation (MT) when translating te…

Machine TranslationPredictionTranslation

Discourse-level Annotation over Europarl for Machine Translation: Connectives and Pronouns

2012-05-01 · LREC 2012 5 · Andrei Popescu-Belis, Thomas Meyer, Jeevanthi Liyanapathirana, Bruno Cartoni 외

This paper describes methods and results for the annotation of two discourse-level phenomena, connectives and pronouns, over a multilingual parallel corpus. Excerpts from Europarl in English and French have been annotate…

Machine TranslationTranslation

A Test Set for Discourse Translation from Japanese to English

2020-05-01 · LREC 2020 5 · Masaaki Nagata, Makoto Morishita

We made a test set for Japanese-to-English discourse translation to evaluate the power of context-aware machine translation. For each discourse phenomenon, we systematically collected examples where the translation of th…

Machine TranslationSentenceTranslation

Resolving Discourse-Deictic Pronouns: A Two-Stage Approach to Do It

2015-06-01 · SEMEVAL 2015 6 · Sujay Kumar Jauhar, Raul Guerra, Edgar Gonz{\`a}lez Pellicer, Marta Recasens
Coreference ResolutionNatural Language InferenceVocal Bursts Valence Prediction

Validation of an Automatic Metric for the Accuracy of Pronoun Translation (APT)

2017-09-01 · WS 2017 9 · Lesly Miculicich Werlen, Andrei Popescu-Belis

In this paper, we define and assess a reference-based metric to evaluate the accuracy of pronoun translation (APT). The metric automatically aligns a candidate and a reference translation using GIZA++ augmented with spec…

Machine TranslationTranslation