Papers › Recurrent Memory Networks for Language Modeling

Recurrent Memory Networks for Language Modeling

6 Jan 2016NAACL 2016 6arXiv:1601.01272archive 2025-07-28

Ke Tran, Arianna Bisazza, Christof Monz

Recurrent Neural Networks (RNN) have obtained excellent result in many natural language processing (NLP) tasks. However, understanding and interpreting the source of this success remains a challenge. In this paper, we propose Recurrent Memory Network (RMN), a novel RNN architecture, that not only amplifies the power of RNN but also facilitates our understanding of its internal functioning and allows us to discover underlying patterns in data. We demonstrate the power of RMN on language modeling and sentence completion tasks. On language modeling, RMN outperforms Long Short-Term Memory (LSTM) network on three large German, Italian, and English dataset. Additionally we perform in-depth analysis of various linguistic dimensions that RMN captures. On Sentence Completion Challenge, for which it is essential to capture sentence coherence, our RMN obtains 69.2% accuracy, surpassing the previous state-of-the-art by a large margin.

PaperPDFConference PDFCode

Code

ketranm/RMN officialmentioned in papertorch report
simonjisu/NMT mentioned on GitHubpytorchMIT report

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

Language ModelingLanguage ModellingSentenceSentence Completion

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Memory Network

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