paper:arxiv-1406-1078Learning phrase representations using RNN encoder-decoder for statistical machine translation
Original abstract (expand)
In this paper, we propose a novel neural network model called RNN Encoder‐ Decoder that consists of two recurrent neural networks (RNN). One RNN encodes a sequence of symbols into a fixedlength vector representation, and the other decodes the representation into another sequence of symbols. The encoder and decoder of the proposed model are jointly trained to maximize the conditional probability of a target sequence given a source sequence. The performance of a statistical machine translation system is empirically found to improve by using the conditional probabilities of phrase pairs computed by the RNN Encoder‐Decoder as an additional feature in the existing log-linear model. Qualitatively, we show that the proposed model learns a semantically and syntactically meaningful representation of linguistic phrases.
Related work— refs + corpus + external arXiv
Cited / in-corpus / arXiv badges show which signals surfaced each row. Multi-source rows weighted higher.
- Statistical Machine Translation for Indic LanguagesDivyajoti Panda, Tapas Kumar Mishra, Bidyut Kr. Patra Sudhansu Bala Das2026≈ 75%
- Survey on reinforcement learning for language processingNicolas Navarro-Guerrero, Anabel Martin-Gonzalez, Cornelius Weber, Stefan Wermter Victor Uc-Cetina2026≈ 74%
- SAE-RNA: A Sparse Autoencoder Model for Interpreting RNA Language Model RepresentationsSangdae Nam Taehan Kim2025≈ 73%
- Improved acoustic word embeddings for zero-resource languages using multilingual transferYevgen Matusevych, Sharon Goldwater Herman Kamper2021≈ 73%
- Pairing Orthographically Variant Literary Words to Standard Equivalents Using Neural Edit Distance ModelsCraig Messner and Tom Lippincott2026≈ 73%
- ≈ 73%
- Improving Normative Modeling for Multi-modal Neuroimaging Data using mixture-of-product-of-experts variational autoencodersPhilip Payne, Aristeidis Sotiras Sayantan Kumar2026≈ 73%
- Transfer Learning for Improving Speech Emotion Classification AccuracyRajib Rana, Shahzad Younis, Junaid Qadir, and Julien Epps Siddique Latif2020≈ 73%
- Representation Learning with Autoencoders for Electronic Health Records: A Comparative StudyMilad Zafar Nezhad, Ratna Babu Chinnam, Dongxiao Zhu Najibesadat Sadati2019≈ 73%
- ≈ 73%
- ≈ 73%
- Probing Task-Oriented Dialogue Representation from Language ModelsChien-Sheng Wu and Caiming Xiong2020≈ 73%
- ≈ 73%
- ≈ 72%
- Representation Learning with Autoencoders for Electronic Health Records: A Comparative StudyMilad Zafar Nezhad, Ratna Babu Chinnam, Dongxiao Zhu Najibesadat Sadati2019≈ 72%
- ≈ 72%
- Model Alignment Searchin corpus2025≈ 69%
- Interpreting Language Model Parametersin corpus2026≈ 69%
- ≈ 68%
- Relating transformers to models and neural representations of the hippocampal formationin corpus2021≈ 68%
- The Platonic Representation Hypothesisin corpus2024≈ 68%
- ≈ 68%
- ≈ 67%
- Simulators — LessWrongin corpus≈ 67%
- The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?in corpus2025≈ 67%
- Mechanistic Knobs in LLMs: Retrieving and Steering High-Order Semantic Features via Sparse Autoencodersin corpus2026≈ 67%
- A Mathematical Framework for Transformer Circuitsin corpus2021≈ 67%
Similar preprints — Semantic Scholar
Cited by (2)
- Model Alignment Search
Model Alignment Search (MAS) establishes bidirectional causal similarity between neural networks by learning a per-model orthogonal rotation matrix that isolates behaviorally relevant subspaces and us
- Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
Manifold steering — intervening on model activations along paths constrained to lie on a learned activation manifold M_h rather than along Euclidean linear directions — produces behavioral trajectorie