# Topic Detection and Tracking with Time-Aware Document Embeddings

arXiv: https://arxiv.org/abs/2112.06166 · HTML: https://mlsanity.com/paper/2112.06166/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 58 references that are in the map.
- First posted on arXiv 12 Dec 2021.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [Time2Vec: Learning a Vector Representation of Time](https://mlsanity.com/paper/1907.05321/) (2019)
- [What Do Position Embeddings Learn? An Empirical Study of Pre-Trained Language Model Positional Encoding](https://mlsanity.com/paper/2010.04903/) (2020)
- [Multilingual Clustering of Streaming News](https://mlsanity.com/paper/1809.00540/) (2018)
- [Event-Driven News Stream Clustering using Entity-Aware Contextual Embeddings](https://mlsanity.com/paper/2101.11059/) (2021)
- [Batch Clustering for Multilingual News Streaming](https://mlsanity.com/paper/2004.08123/) (2020)
- [Offline versus Online Triplet Mining based on Extreme Distances of Histopathology Patches](https://mlsanity.com/paper/2007.02200/) (2020)

## Abstract (arXiv)

The time at which a message is communicated is a vital piece of metadata in many real-world natural language processing tasks such as Topic Detection and Tracking (TDT). TDT systems aim to cluster a corpus of news articles by event, and in that context, stories that describe the same event are likely to have been written at around the same time. Prior work on time modeling for TDT takes this into account, but does not well capture how time interacts with the semantic nature of the event. For example, stories about a tropical storm are likely to be written within a short time interval, while stories about a movie release may appear over weeks or months. In our work, we design a neural method that fuses temporal and textual information into a single representation of news documents for event detection. We fine-tune these time-aware document embeddings with a triplet loss architecture, integrate the model into downstream TDT systems, and evaluate the systems on two benchmark TDT data sets in English. In the retrospective setting, we apply clustering algorithms to the time-aware embeddings and show substantial improvements over baselines on the News2013 data set. In the online streaming setting, we add our document encoder to an existing state-of-the-art TDT pipeline and demonstrate that it can benefit the overall performance. We conduct ablation studies on the time representation and fusion algorithm strategies, showing that our proposed model outperforms alternative strategies. Finally, we probe the model to examine how it handles recurring events more effectively than previous TDT systems.