Papers with hybrid models
The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation (P18-1)
Copied to clipboard
Mia Xu Chen, Orhan Firat, Ankur Bapna, Melvin Johnson, Wolfgang Macherey, George Foster, Llion Jones, Mike Schuster, Noam Shazeer, Niki Parmar, Ashish Vaswani, Jakob Uszkoreit, Lukasz Kaiser, Zhifeng Chen, Yonghui Wu, Macduff Hughes
| Challenge: | In recent years, the emergence of seq2seq models has revolutionized the field of machine translation by replacing traditional phrase-based approaches with neural machine translation (NMT) systems based on the encoder-decoder paradigm. |
| Approach: | They propose to use a convolutional seq2seq model to combine the strengths of the two approaches. |
| Outcome: | The proposed architectures outperform the existing models on the WMT’14 benchmark dataset. |
Hybrid Models for Aspects Extraction without Labelled Dataset (D19-66)
Copied to clipboard
| Challenge: | Existing methods to extract aspects from opinions focus on explicit aspects, but sentences do not state them explicitly. |
| Approach: | They propose to use a dictionary-based approach to identify and extract aspects from opinions . they propose to combine topic modelling and dictionary--based method . |
| Outcome: | The proposed models outperform baseline topic model and dictionary-based approach in 58.70% of the evaluations. |
Abstractive Summarizers are Excellent Extractive Summarizers (2023.acl-short)
Copied to clipboard
| Challenge: | Abstractive summarization systems have traditionally been fragmented, limiting the benefits of compatible models. |
| Approach: | They propose three new inference algorithms using sequence-to-sequence architectures to model extractive summarization with an abstractive summmarization system. |
| Outcome: | The proposed algorithms outperform existing models on CNN and Dailymail and show that they are more efficient than existing models. |
Context Generation Improves Open Domain Question Answering (2023.findings-eacl)
Copied to clipboard
Dan Su, Mostofa Patwary, Shrimai Prabhumoye, Peng Xu, Ryan Prenger, Mohammad Shoeybi, Pascale Fung, Anima Anandkumar, Bryan Catanzaro
| Challenge: | Existing closed-book question answering methods do not fully exploit the parameterized knowledge. |
| Approach: | They propose a closed-book QA framework which uses a coarse-to-fine approach to extract the relevant knowledge and answer a question. |
| Outcome: | The proposed method outperforms open-book QA methods on three QA benchmarks. |
How much do contextualized representations encode long-range context? (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing studies of contextualized representations focus on short sequences of tens to hundreds of tokens, whereas modern language models handle hundreds of thousands of token in a single context window. |
| Approach: | They use a perturbation setup and a metric to capture contextualization of long-range patterns from the perspective of representation geometry. |
| Outcome: | The proposed model can encode long-range contexts, but it's not fully recurrent, the authors say . their results suggest improvements in existing language models . |
LAMB: A Training-Free Method to Enhance the Long-Context Understanding of SSMs via Attention-Guided Token Filtering (2025.acl-short)
Copied to clipboard
Zhifan Ye, Zheng Wang, Kejing Xia, Jihoon Hong, Leshu Li, Lexington Whalen, Cheng Wan, Yonggan Fu, Yingyan Celine Lin, Souvik Kundu
| Challenge: | Recent work attributes performance degradation to an exponential decay in hidden-state memory. |
| Approach: | They propose a token filtering strategy that is training-free and attention-guided . they propose 'LAMB' to preserve critical tokens during inference . |
| Outcome: | The proposed token filtering improves long-context performance by 30.35% over state-of-the-art methods on benchmarks. |
Towards Better Modeling Hierarchical Structure for Self-Attention with Ordered Neurons (D19-1)
Copied to clipboard
| Challenge: | Recent studies have shown that a hybrid of self-attention networks (SANs) and recurrent neural networks (RNNs) outperforms both individual architectures, while not much is known about why the hybrid models work. |
| Approach: | They propose to use an advanced variant of self-attention networks (SANs) to enhance the strength of hybrid models by introducing a syntax-oriented inductive bias to perform tree-like composition. |
| Outcome: | The proposed model outperforms both individual models and a standard hybrid model on a machine translation task. |
Testing the limits of logical reasoning in neural and hybrid models (2024.findings-naacl)
Copied to clipboard
| Challenge: | despite the successes of deep learning models, we still need to know more about how and what they learn. |
| Approach: | They create tests to analyze logical reasoning patterns in neural and hybrid models . they find that models can generalize logical thinking only to a limited degree . |
| Outcome: | The proposed models can capture elementary aspects of meaning but only to limited extent . authors say they need to understand how and what they learn . |
On the Role of Bidirectionality in Language Model Pre-Training (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Prior work on language model pre-training explored different architectures and learning objectives, but differences in data, hyperparameters and evaluation make a principled comparison difficult. |
| Approach: | They propose a framework that generalizes prior approaches to pre-training language models by focusing on bidirectionality and controlling each of them separately. |
| Outcome: | The proposed framework generalizes prior approaches including fully unidirectional models like GPT, fully bidirectional models and hybrid models like CM3 and prefix LM. |
Augmenting word2vec with latent Dirichlet allocation within a clinical application (N19-1)
Copied to clipboard
| Challenge: | Existing models that combine latent Dirichlet allocation and word embedding for distinguishing between speakers with and without Alzheimer’s disease from transcripts of picture descriptions are not suitable for clinical binary text classification tasks. |
| Approach: | They propose three models that combine latent Dirichlet allocation and word embedding for distinguishing between speakers with and without Alzheimer’s disease from transcripts of picture descriptions. |
| Outcome: | The proposed models outperform word2vec and LDA models on a clinical binary text classification task. |
Towards Neural Speaker Modeling in Multi-Party Conversation: The Task, Dataset, and Models (L18-1)
Copied to clipboard
| Challenge: | Existing methods for speaker modeling are based on hand-crafted statistics and ad hoc to a certain application. |
| Approach: | They propose to use speaker classification as a surrogate task for general speaker modeling and collect massive data to facilitate research in this direction. |
| Outcome: | The proposed models outperform the existing models and are feasible with speaker identity information. |
Pushing on Text Readability Assessment: A Transformer Meets Handcrafted Linguistic Features (2021.emnlp-main)
Copied to clipboard
| Challenge: | ML models with handcrafted features are linguistically explainable, expandable, and competent against the modern neural models. |
| Approach: | They propose to combine traditional ML models with ML transformers to improve readability assessment by 99% accuracy. |
| Outcome: | The proposed model achieves state-of-the-art (SOTA) accuracy on popular datasets. |
Post-decoder Biasing for End-to-End Speech Recognition of Multi-turn Medical Interview (2024.lrec-main)
Copied to clipboard
| Challenge: | End-to-end (E2E) models are replacing hybrid models for automatic speech recognition tasks. |
| Approach: | They propose a method to optimize E2E models for automatic speech recognition . they propose MED-IT, a multi-turn consultation speech dataset . |
| Outcome: | The proposed method improves on subsets of rare words appearing in training speech. |