arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.02648cs.CLcs.AIcs.LG
收藏

基于Quora问题对的释义识别实验

Experiments on Paraphrase Identification Using Quora Question Pairs Dataset

Jakarta Artificial Intelligence Research(雅加达人工智能研究院)

Andreas Chandra, Ruben Stefanus

摘要:

我们对Quora问题对数据集进行建模,以识别类似的问题。我们使用的数据集由Quora提供。该任务是一个二元分类。我们尝试了几种方法和算法,并从以前的作品不同的方法。对于特征提取,我们使用了包括计数向量化器的词袋,以及XGBoost和CatBoost的具有unigram的词频-逆文档频率。此外,我们还尝试了WordPiece标记器,它显着提高了模型性能。我们达到了97%的准确率。代码和数据集。

英文摘要:

We modeled the Quora question pairs dataset to identify a similar question. The dataset that we use is provided by Quora. The task is a binary classification. We tried several methods and algorithms and different approach from previous works. For feature extraction, we used Bag of Words including Count Vectorizer, and Term Frequency-Inverse Document Frequency with unigram for XGBoost and CatBoost. Furthermore, we also experimented with WordPiece tokenizer which improves the model performance significantly. We achieved up to 97 percent accuracy. Code and Dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑