# AD3: Attentive Deep Document Dater

## TL;DR

This paper introduces AD3, an attention-based neural system that predicts document creation dates from content, improving over existing methods by effectively leveraging context and temporal cues.

## Contribution

The paper presents a novel neural model, AD3, that uses attention mechanisms to accurately estimate document dates from content, addressing missing or unreliable timestamp metadata.

## Key findings

- AD3 outperforms baseline models on multiple datasets.
- Attention mechanisms improve date prediction accuracy.
- The system effectively utilizes contextual and temporal information.

## Abstract

Knowledge of the creation date of documents facilitates several tasks such as summarization, event extraction, temporally focused information extraction etc. Unfortunately, for most of the documents on the Web, the time-stamp metadata is either missing or can't be trusted. Thus, predicting creation time from document content itself is an important task. In this paper, we propose Attentive Deep Document Dater (AD3), an attention-based neural document dating system which utilizes both context and temporal information in documents in a flexible and principled manner. We perform extensive experimentation on multiple real-world datasets to demonstrate the effectiveness of AD3 over neural and non-neural baselines.