# Neural Semantic Encoders

arXiv: https://arxiv.org/abs/1607.04315 · HTML: https://mlsanity.com/paper/1607.04315/

## Key facts

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

## Built on by (most cited first, 14 of 14)

- [Titans: Learning to Memorize at Test Time](https://mlsanity.com/paper/2501.00663/) (2024)
- [Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention](https://mlsanity.com/paper/2404.07143/) (2024)
- [Nested Learning: The Illusion of Deep Learning Architectures](https://mlsanity.com/paper/2512.24695/) (2025)
- [ATLAS: Learning to Optimally Memorize the Context at Test Time](https://mlsanity.com/paper/2505.23735/) (2025)
- [It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization](https://mlsanity.com/paper/2504.13173/) (2025)
- [Evaluation of BERT and ALBERT Sentence Embedding Performance on Downstream NLP Tasks](https://mlsanity.com/paper/2101.10642/) (2021)
- [Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognition](https://mlsanity.com/paper/2110.02220/) (2021)
- [Comba: Improving Bilinear RNNs with Closed-loop Control](https://mlsanity.com/paper/2506.02475/) (2025)
- [Memory Caching: RNNs with Growing Memory](https://mlsanity.com/paper/2602.24281/) (2026)
- [Can Transformer Language Models Predict Psychometric Properties?](https://mlsanity.com/paper/2106.06849/) (2021)
- [TNT: Improving Chunkwise Training for Test-Time Memorization](https://mlsanity.com/paper/2511.07343/) (2025)
- [Deep Learning-based Sentiment Classification: A Comparative Survey](https://mlsanity.com/paper/2312.17253/) (2023)
- [Bias Beneath the Tone: Empirical Characterisation of Tone Bias in LLM-Driven UX Systems](https://mlsanity.com/paper/2512.19950/) (2025)
- [Proteus: Incremental Memory Activation for Long-Context Sequence Modeling](https://mlsanity.com/paper/2608.16844/) (2026)

## Abstract (arXiv)

We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders. NSE is equipped with a novel memory update rule and has a variable sized encoding memory that evolves over time and maintains the understanding of input sequences through read}, compose and write operations. NSE can also access multiple and shared memories. In this paper, we demonstrated the effectiveness and the flexibility of NSE on five different natural language tasks: natural language inference, question answering, sentence classification, document sentiment analysis and machine translation where NSE achieved state-of-the-art performance when evaluated on publically available benchmarks. For example, our shared-memory model showed an encouraging result on neural machine translation, improving an attention-based baseline by approximately 1.0 BLEU.