paper-with-me

홈 › Papers

The AIP-Tohoku System at the BEA-2019 Shared Task

2019-08-01 · WS 2019 8 · Hiroki Asano, Masato Mita, Tomoya Mizumoto, Jun Suzuki

We introduce the AIP-Tohoku grammatical error correction (GEC) system for the BEA-2019 shared task in Track 1 (Restricted Track) and Track 2 (Unrestricted Track) using the same system architecture. Our system comprises two key components: error generation and sentence-level error detection. In particular, GEC with sentence-level grammatical error detection is a novel and versatile approach, and we experimentally demonstrate that it significantly improves the precision of the base model. Our system is ranked 9th in Track 1 and 2nd in Track 2.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Grammatical Error CorrectionGrammatical Error DetectionSentence

Similar Papers 제목 키워드 기반

Tohoku-AIP-NTT at WMT 2020 News Translation Task

2020-11-01 · WMT (EMNLP) 2020 11 · Shun Kiyono, Takumi Ito, Ryuto Konno, Makoto Morishita 외

In this paper, we describe the submission of Tohoku-AIP-NTT to the WMT’20 news translation task. We participated in this task in two language pairs and four language directions: English <–> German and English <–> Japanes…

RerankingTranslation

Tohoku at SemEval-2016 Task 6: Feature-based Model versus Convolutional Neural Network for Stance Detection

2016-06-01 · SEMEVAL 2016 6 · Yuki Igarashi, Hiroya Komatsu, Sosuke Kobayashi, Naoaki Okazaki 외
Stance DetectionText ClassificationWord Embeddings

Fine-grained linguistic evaluation for state-of-the-art Machine Translation

2020-10-13 · WMT (EMNLP) 2020 11 · Eleftherios Avramidis, Vivien Macketanz, Ursula Strohriegel, Aljoscha Burchardt 외

This paper describes a test suite submission providing detailed statistics of linguistic performance for the state-of-the-art German-English systems of the Fifth Conference of Machine Translation (WMT20). The analysis co…

Machine TranslationTranslation

Building Damage Mapping with Self-PositiveUnlabeled Learning

2021-11-04 · Junshi Xia, Naoto Yokoya, Bruno Adriano

Humanitarian organizations must have fast and reliable data to respond to disasters. Deep learning approaches are difficult to implement in real-world disasters because it might be challenging to collect ground truth dat…

Building Damage AssessmentHumanitarian

TimeMachine-bench: A Benchmark for Evaluating Model Capabilities in Repository-Level Migration Tasks

2026-01-30 · Ryo Fujii, Makoto Morishita, Kazuki Yano, Jun Suzuki arxiv

With the advancement of automated software engineering, research focus is increasingly shifting toward practical tasks reflecting the day-to-day work of software engineers. Among these tasks, software migration, a critic…