paper-with-me

Papers

Using hyperlinks to improve multilingual partial parsers

2017-09-01 · WS 2017 9 · Anders S{\o}gaard

Syntactic annotation is costly and not available for the vast majority of the world{'}s languages. We show that sometimes we can do away with less labeled data by exploiting more readily available forms of mark-up. Specifically, we revisit an idea from Valentin Spitkovsky{'}s work (2010), namely that hyperlinks typically bracket syntactic constituents or chunks. We strengthen his results by showing that not only can hyperlinks help in low resource scenarios, exemplified here by Quechua, but learning from hyperlinks can also improve state-of-the-art NLP models for English newswire. We also present out-of-domain evaluation on English Ontonotes 4.0.

📄 PDF Abstract BibTeX

Code (1)

https://bitbucket.org/soegaard/hyperlink-iwpt17 공식 구현

Tasks

Machine TranslationSpeech Synthesis

Similar Papers 제목 키워드 기반

WikiBank: Using Wikidata to Improve Multilingual Frame-Semantic Parsing

2020-05-01 · LREC 2020 5 · Cezar Sas, Meriem Beloucif, Anders S{\o}gaard

Frame-semantic annotations exist for a tiny fraction of the world{'}s languages, Wikidata, however, links knowledge base triples to texts in many languages, providing a common, distant supervision signal for semantic par…

Cross-Lingual TransferSemantic Parsing

Efficient Social Network Multilingual Classification using Character, POS n-grams and Dynamic Normalization

2017-02-21 · Carlos-Emiliano González-Gallardo, Juan-Manuel Torres-Moreno, Azucena Montes Rendón, Gerardo Sierra

In this paper we describe a dynamic normalization process applied to social network multilingual documents (Facebook and Twitter) to improve the performance of the Author profiling task for short texts. After the normali…

Author ProfilingGeneral ClassificationPOS

Scalable Cross-lingual Treebank Synthesis for Improved Production Dependency Parsers

2020-12-01 · COLING 2020 8 · Yousef El-Kurdi, Hiroshi Kanayama, Efsun Sarioglu Kayi, Vittorio Castelli 외

We present scalable Universal Dependency (UD) treebank synthesis techniques that exploit advances in language representation modeling which leverage vast amounts of unlabeled general-purpose multilingual text. We introdu…

Data Augmentation

Learning Cross-lingual Distributed Logical Representations for Semantic Parsing

2018-06-14 · ACL 2018 7 · Yanyan Zou, Wei Lu

With the development of several multilingual datasets used for semantic parsing, recent research efforts have looked into the problem of learning semantic parsers in a multilingual setup. However, how to improve the perf…

Semantic Parsing

DMRST: A Joint Framework for Document-Level Multilingual RST Discourse Segmentation and Parsing

2021-10-09 · CODI 2021 11 · Zhengyuan Liu, Ke Shi, Nancy F. Chen

Text discourse parsing weighs importantly in understanding information flow and argumentative structure in natural language, making it beneficial for downstream tasks. While previous work significantly improves the perfo…

Discourse ParsingDiscourse SegmentationEnd-to-End RST ParsingSegmentation+1