Papers › Neural Semantic Encoders
Neural Semantic Encoders
Tsendsuren Munkhdalai, Hong Yu
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Machine Translation | WMT2014 English-German | NSE-NSE | BLEU score | 17.9 | #86 of 91 | Archive leaderboard | report |
| Natural Language Inference | SNLI | 300D MMA-NSE encoders with attention | % Test Accuracy | 85.4 | #72 of 98 | Archive leaderboard | report |
| Natural Language Inference | SNLI | 300D MMA-NSE encoders with attention | % Train Accuracy | 86.9 | #72 of 98 | Archive leaderboard | report |
| Natural Language Inference | SNLI | 300D MMA-NSE encoders with attention | Parameters | 3.2m | #72 of 98 | Archive leaderboard | report |
| Natural Language Inference | SNLI | 300D NSE encoders | % Test Accuracy | 84.6 | #76 of 98 | Archive leaderboard | report |
| Natural Language Inference | SNLI | 300D NSE encoders | % Train Accuracy | 86.2 | #76 of 98 | Archive leaderboard | report |
| Natural Language Inference | SNLI | 300D NSE encoders | Parameters | 3.0m | #76 of 98 | Archive leaderboard | report |
| Question Answering | WikiQA | MMA-NSE attention | MAP | 0.6811 | #18 of 25 | Archive leaderboard | report |
| Question Answering | WikiQA | MMA-NSE attention | MRR | 0.6993 | #18 of 25 | Archive leaderboard | report |
| Sentiment Analysis | SST-2 Binary classification | Neural Semantic Encoder | Accuracy | 89.7 | #63 of 87 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections