GATech at AbjadGenEval Shared Task: Multilingual Embeddings for Arabic Machine-Generated Text Classification
We present our approach to the AbjadGenEval shared task on detecting AI-generated Arabic text. We fine-tuned the multilingual E5-large encoder for binary classification, and we explored several pooling strategies to pool token representations, including weighted layer pooling, multi-head attention pooling, and gated fusion. Interestingly, none of these outperformed simple mean pooling, which achieved an F1 of 0.75 on the test set. We believe this is because complex pooling methods introduce additional parameters that need more data to train properly, whereas mean pooling offers a stable baseline that generalizes well even with limited examples. We also observe a clear pattern in the data: human-written texts tend to be significantly longer than machine-generated ones.
Code (0)
등록된 구현이 없습니다.
Tasks
Binary ClassificationText ClassificationSimilar Papers 제목 키워드 기반
Domain Adaptive Pretraining for Multilingual Acronym Extraction
This paper presents our findings from participating in the multilingual acronym extraction shared task SDU@AAAI-22. The task consists of acronym extraction from documents in 6 languages within scientific and legal domain…
CUNI Submission to the BUCC 2022 Shared Task on Bilingual Term Alignment
We present our submission to the BUCC Shared Task on bilingual term alignment in comparable specialized corpora. We devised three approaches using static embeddings with post-hoc alignment, the Monoses pipeline for unsup…
Machine TranslationTranslationMultilingual Named Entity Recognition Using Pretrained Embeddings, Attention Mechanism and NCRF
In this paper we tackle multilingual named entity recognition task. We use the BERT Language Model as embeddings with bidirectional recurrent network, attention, and NCRF on the top. We apply multilingual BERT only as em…
Joint NER and ClassificationLanguage ModelingLanguage ModellingMultilingual Named Entity Recognition+4TRAVIS at PARSEME Shared Task 2020: How good is (m)BERT at seeing the unseen?
This paper describes the TRAVIS system built for the PARSEME Shared Task 2020 on semi-supervised identification of verbal multiword expressions. TRAVIS is a fully feature-independent model, relying only on the contextual…
A Simple Approach to Learning Unsupervised Multilingual Embeddings
Recent progress on unsupervised learning of cross-lingual embeddings in bilingual setting has given impetus to learning a shared embedding space for several languages without any supervision. A popular framework to solve…
Bilingual Lexicon InductionDependency ParsingDocument ClassificationWord Alignment+1