Multi-head Span-based Detector for AI-generated Fragments in Scientific Papers

• URL: http://arxiv.org/abs/2411.07343v1
• Date: Mon, 11 Nov 2024 20:05:22 GMT
• Title: Multi-head Span-based Detector for AI-generated Fragments in Scientific Papers
• Authors: German Gritsai, Ildar Khabutdinov, Andrey Grabovoy,
• Abstract summary: This paper describes a system designed to distinguish between AI-generated and human-written scientific excerpts. In this competition the task is to find artificially generated token-level text fragments in documents of a scientific domain.
• Score: 0.0
• License:
• Abstract: This paper describes a system designed to distinguish between AI-generated and human-written scientific excerpts in the DAGPap24 competition hosted within the Fourth Workshop on Scientific Document Processing. In this competition the task is to find artificially generated token-level text fragments in documents of a scientific domain. Our work focuses on the use of a multi-task learning architecture with two heads. The application of this approach is justified by the specificity of the task, where class spans are continuous over several hundred characters. We considered different encoder variations to obtain a state vector for each token in the sequence, as well as a variation in splitting fragments into tokens to further feed into the input of a transform-based encoder. This approach allows us to achieve a 9% quality improvement relative to the baseline solution score on the development set (from 0.86 to 0.95) using the average macro F1-score, as well as a score of 0.96 on a closed test part of the dataset from the competition.

Related papers

• Advacheck at GenAI Detection Task 1: AI Detection Powered by Domain-Aware Multi-Tasking [0.0]
  The paper describes a system designed by Advacheck team to recognise machine-generated and human-written texts in the monolingual subtask of GenAI Detection Task 1 competition. Our developed system is a multi-task architecture with shared Transformer between several classification heads.
  arXiv  Detail & Related papers  (2024-11-18T17:03:30Z)
• GatedLexiconNet: A Comprehensive End-to-End Handwritten Paragraph Text Recognition System [3.9527064697847005]
  We present an end-to-end paragraph recognition system that incorporates internal line segmentation and convolutional layers based encoder. This study reported character error rates of 2.27% on IAM, 0.9% on RIMES, and 2.13% on READ-16, and word error rates of 5.73% on READ-2016 datasets.
  arXiv  Detail & Related papers  (2024-04-22T10:19:16Z)
• LOCR: Location-Guided Transformer for Optical Character Recognition [55.195165959662795]
  We propose LOCR, a model that integrates location guiding into the transformer architecture during autoregression. We train the model on a dataset comprising over 77M text-location pairs from 125K academic document pages, including bounding boxes for words, tables and mathematical symbols. It outperforms all existing methods in our test set constructed from arXiv, as measured by edit distance, BLEU, METEOR and F-measure.
  arXiv  Detail & Related papers  (2024-03-04T15:34:12Z)
• Object Segmentation by Mining Cross-Modal Semantics [68.88086621181628]
  We propose a novel approach by mining the Cross-Modal Semantics to guide the fusion and decoding of multimodal features. Specifically, we propose a novel network, termed XMSNet, consisting of (1) all-round attentive fusion (AF), (2) coarse-to-fine decoder (CFD), and (3) cross-layer self-supervision.
  arXiv  Detail & Related papers  (2023-05-17T14:30:11Z)
• Tuning Traditional Language Processing Approaches for Pashto Text Classification [0.0]
  The main aim of this study is to establish a Pashto automatic text classification system. This study compares several models containing both statistical and neural network machine learning techniques. This research obtained average testing accuracy rate 94% using classification algorithm and TFIDF feature extraction method.
  arXiv  Detail & Related papers  (2023-05-04T22:57:45Z)
• Detecting Handwritten Mathematical Terms with Sensor Based Data [71.84852429039881]
  We propose a solution to the UbiComp 2021 Challenge by Stabilo in which handwritten mathematical terms are supposed to be automatically classified. The input data set contains data of different writers, with label strings constructed from a total of 15 different possible characters.
  arXiv  Detail & Related papers  (2021-09-12T19:33:34Z)
• Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching [60.8427677151492]
  We propose CMatch, a Character-level distribution matching method to perform fine-grained adaptation between each character in two domains. Experiments on the Libri-Adapt dataset show that our proposed approach achieves 14.39% and 16.50% relative Word Error Rate (WER) reduction on both cross-device and cross-environment ASR.
  arXiv  Detail & Related papers  (2021-04-15T14:36:54Z)
• Deep ensembles based on Stochastic Activation Selection for Polyp Segmentation [82.61182037130406]
  This work deals with medical image segmentation and in particular with accurate polyp detection and segmentation during colonoscopy examinations. Basic architecture in image segmentation consists of an encoder and a decoder. We compare some variant of the DeepLab architecture obtained by varying the decoder backbone.
  arXiv  Detail & Related papers  (2021-04-02T02:07:37Z)
• Text Recognition in Real Scenarios with a Few Labeled Samples [55.07859517380136]
  Scene text recognition (STR) is still a hot research topic in computer vision field. This paper proposes a few-shot adversarial sequence domain adaptation (FASDA) approach to build sequence adaptation. Our approach can maximize the character-level confusion between the source domain and the target domain.
  arXiv  Detail & Related papers  (2020-06-22T13:03:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.