arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.08226cs.CLcs.IR
收藏

TSI:一种基于文本点击率和广告语义相似度的广告文本强度指标

TSI: an Ad Text Strength Indicator using Text-to-CTR and Semantic-Ad-Similarity

Yahoo Research(雅虎研究院)

Shaunak Mishra, Changwei Hu, Manisha Verma, Kevin Yen, Yifan Hu, Maxim Sviridenko

摘要:

提出有效的广告文本是一个耗时的过程,特别是具有有限的广告经验的小企业的挑战。当一个没有经验的广告客户使用写得很差的广告文本进行广告投放时,广告平台有机会检测到表现不佳的广告文本,并提供改进建议。为了实现这个机会,我们提出了一个广告文本强度指标(TSI),它:(i)预测输入广告文本的点击率(CTR),(ii)获取类似的现有广告,以创建一个周围的输入广告,(iii)和比较预测的CTR在附近,以宣布输入广告是强还是弱。此外,作为广告文本改进的建议,TSI在附近显示匿名版本的高级广告(更高的预测CTR)。对于(i),我们提出了一个基于BERT的文本到CTR模型,该模型在与广告文本相关联的印象和点击上进行训练。对于(ii),我们提出了一个基于语义BERT的广告相似性模型,该模型使用来自广告活动设置数据的弱标签进行训练。离线实验表明,我们的基于BERT的文本到CTR模型实现了显着的提升CTR预测AUC冷启动(新)广告客户相比,基于词袋的基线。此外,我们用于相似广告检索的语义-文本-相似性模型达到了0.93的精确度@1(对于从同一产品类别中检索广告);与无监督的TF-IDF,word 2 vec和BERCE-BERT基线相比,这明显更高。最后,我们分享了雅虎(Verizon Media)广告平台上广告商的在线结果,其中TSI的变体实现了亚秒级的端到端延迟。

英文摘要:

Coming up with effective ad text is a time consuming process, and particularly challenging for small businesses with limited advertising experience. When an inexperienced advertiser onboards with a poorly written ad text, the ad platform has the opportunity to detect low performing ad text, and provide improvement suggestions. To realize this opportunity, we propose an ad text strength indicator (TSI) which: (i) predicts the click-through-rate (CTR) for an input ad text, (ii) fetches similar existing ads to create a neighborhood around the input ad, (iii) and compares the predicted CTRs in the neighborhood to declare whether the input ad is strong or weak. In addition, as suggestions for ad text improvement, TSI shows anonymized versions of superior ads (higher predicted CTR) in the neighborhood. For (i), we propose a BERT based text-to-CTR model trained on impressions and clicks associated with an ad text. For (ii), we propose a sentence-BERT based semantic-ad-similarity model trained using weak labels from ad campaign setup data. Offline experiments demonstrate that our BERT based text-to-CTR model achieves a significant lift in CTR prediction AUC for cold start (new) advertisers compared to bag-of-words based baselines. In addition, our semantic-textual-similarity model for similar ads retrieval achieves a precision@1 of 0.93 (for retrieving ads from the same product category); this is significantly higher compared to unsupervised TF-IDF, word2vec, and sentence-BERT baselines. Finally, we share promising online results from advertisers in the Yahoo (Verizon Media) ad platform where a variant of TSI was implemented with sub-second end-to-end latency.

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。

↑