# Ask the GRU: Multi-Task Learning for Deep Text Recommendations

arXiv: https://arxiv.org/abs/1609.02116 · HTML: https://mlsanity.com/paper/1609.02116/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Sep 2016.

## Built on by (most cited first, 24 of 24)

- [A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation](https://mlsanity.com/paper/2104.13030/) (2021)
- [Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation](https://mlsanity.com/paper/2502.05151/) (2025)
- [Fair Resource Allocation in Multi-Task Learning](https://mlsanity.com/paper/2402.15638/) (2024)
- [Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learning](https://mlsanity.com/paper/2106.02705/) (2021)
- [MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks](https://mlsanity.com/paper/2203.06801/) (2022)
- [Editable User Profiles for Controllable Text Recommendation](https://mlsanity.com/paper/2304.04250/) (2023)
- [HoME: Hierarchy of Multi-Gate Experts for Multi-Task Learning at Kuaishou](https://mlsanity.com/paper/2408.05430/) (2024)
- [SmartSAGE: Training Large-scale Graph Neural Networks using In-Storage Processing Architectures](https://mlsanity.com/paper/2205.04711/) (2022)
- [Synthetic Dataset Generation of Driver Telematics](https://mlsanity.com/paper/2102.00252/) (2021)
- [TLSAN: Time-aware Long- and Short-term Attention Network for Next-item Recommendation](https://mlsanity.com/paper/2103.08971/) (2021)
- [Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications](https://mlsanity.com/paper/2103.15330/) (2021)
- [Polarity and Subjectivity Detection with Multitask Learning and BERT Embedding](https://mlsanity.com/paper/2201.05363/) (2022)
- [FedComm: Federated Learning as a Medium for Covert Communication](https://mlsanity.com/paper/2201.08786/) (2022)
- [TATTOOED: A Robust Deep Neural Network Watermarking Scheme based on Spread-Spectrum Channel Coding](https://mlsanity.com/paper/2202.06091/) (2022)
- [ESMC: Entire Space Multi-Task Model for Post-Click Conversion Rate via Parameter Constraint](https://mlsanity.com/paper/2307.09193/) (2023)
- [DenseRec: Revisiting Dense Content Embeddings for Sequential Transformer-based Recommendation](https://mlsanity.com/paper/2508.18442/) (2025)
- [Deep Latent Emotion Network for Multi-Task Learning](https://mlsanity.com/paper/2104.08716/) (2021)
- [Multi-Faceted Hierarchical Multi-Task Learning for a Large Number of Tasks with Multi-dimensional Relations](https://mlsanity.com/paper/2110.13365/) (2021)
- [Tag-Aware Document Representation for Research Paper Recommendation](https://mlsanity.com/paper/2209.03660/) (2022)
- [Graphing else matters: exploiting aspect opinions and ratings in explainable graph-based recommendations](https://mlsanity.com/paper/2107.03226/) (2021)
- [Photos Are All You Need for Reciprocal Recommendation in Online Dating](https://mlsanity.com/paper/2108.11714/) (2021)
- [Multi-task recommendation system for scientific papers with high-way networks](https://mlsanity.com/paper/2204.09930/) (2022)
- [OliVaR: Improving Olive Variety Recognition using Deep Neural Networks](https://mlsanity.com/paper/2303.00431/) (2023)
- [MIARec: Mutual-influence-aware Heterogeneous Network Embedding for Scientific Paper Recommendation](https://mlsanity.com/paper/2510.12054/) (2025)

## Abstract (arXiv)

In a variety of application domains the content to be recommended to users is associated with text. This includes research papers, movies with associated plot summaries, news articles, blog posts, etc. Recommendation approaches based on latent factor models can be extended naturally to leverage text by employing an explicit mapping from text to factors. This enables recommendations for new, unseen content, and may generalize better, since the factors for all items are produced by a compactly-parametrized model. Previous work has used topic models or averages of word embeddings for this mapping. In this paper we present a method leveraging deep recurrent neural networks to encode the text sequence into a latent vector, specifically gated recurrent units (GRUs) trained end-to-end on the collaborative filtering task. For the task of scientific paper recommendation, this yields models with significantly higher accuracy. In cold-start scenarios, we beat the previous state-of-the-art, all of which ignore word order. Performance is further improved by multi-task learning, where the text encoder network is trained for a combination of content recommendation and item metadata prediction. This regularizes the collaborative filtering model, ameliorating the problem of sparsity of the observed rating matrix.