UTFPR at WMT 2018: Minimalistic Supervised Corpora Filtering for Machine Translation
We present the UTFPR systems at the WMT 2018 parallel corpus filtering task. Our supervised approach discerns between good and bad translations by training classic binary classification models over an artificially produced binary classification dataset derived from a high-quality translation set, and a minimalistic set of 6 semantic distance features that rely only on easy-to-gather resources. We rank translations by their probability for the {``}good{''} label. Our results show that logistic regression pairs best with our approach, yielding more consistent results throughout the different settings evaluated.
Code (0)
등록된 구현이 없습니다.
Tasks
Binary ClassificationClassificationGeneral ClassificationLanguage ModelingLanguage ModellingMachine TranslationregressionTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
UTFPR at SemEval-2020 Task 7: Using Co-occurrence Frequencies to Capture Unexpectedness
We describe the UTFPR system for SemEval-2020{'}s Task 7: Assessing Humor in Edited News Headlines. Ours is a minimalist unsupervised system that uses word co-occurrence frequencies from large corpora to capture unexpect…
Task 2UTFPR at SemEval-2019 Task 5: Hate Speech Identification with Recurrent Neural Networks
In this paper we revisit the problem of automatically identifying hate speech in posts from social media. We approach the task using a system based on minimalistic compositional Recurrent Neural Networks (RNN). We tested…
UTFPR at SemEval-2021 Task 1: Complexity Prediction by Combining BERT Vectors and Classic Features
We describe the UTFPR systems submitted to the Lexical Complexity Prediction shared task of SemEval 2021. They perform complexity prediction by combining classic features, such as word frequency, n-gram frequency, word l…
Lexical Complexity PredictionPredictionUTFPR at SemEval-2019 Task 6: Relying on Compositionality to Find Offense
We present the UTFPR system for the OffensEval shared task of SemEval 2019: A character-to-word-to-sentence compositional RNN model trained exclusively over the training data provided by the organizers. We find that, alt…
SentenceUTFPR at IEST 2018: Exploring Character-to-Word Composition for Emotion Analysis
We introduce the UTFPR system for the Implicit Emotions Shared Task of 2018: A compositional character-to-word recurrent neural network that does not exploit heavy and/or hard-to-obtain resources. We find that our approa…
Emotion Recognition