Papers with encoder layers
Probing Word Translations in the Transformer and Trading Decoder for Encoder Layers (2021.naacl-main)
Copied to clipboard
| Challenge: | Neural Machine Translation (NMT) has attracted wide attention in recent years. |
| Approach: | They propose a probing-based approach to measure word translation accuracy using transformer layers. |
| Outcome: | The proposed model outperforms previous probing-based translation models. |
LayAlign: Enhancing Multilingual Reasoning in Large Language Models via Layer-Wise Adaptive Fusion and Alignment Strategy (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are pretrained on multilingual corpora but exhibit suboptimal performance on low-resource languages. |
| Approach: | They propose a framework that integrates representations from all encoder layers and an adaptive fusion-enhanced attention mechanism to enable layer-wise interaction between the LLM and the multilingual encoder. |
| Outcome: | Experiments on multilingual reasoning tasks show that the proposed framework outperforms baselines. |
Learning to Compose Representations of Different Encoder Layers towards Improving Compositional Generalization (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies show that sequence-to-sequence (seq2sequ) models struggle with compositional generalization (CG) a crucial property of human language learning is its compositional globalization (GC), the algebraic ability to understand and produce a potentially infinite number of novel combinations from known components. |
| Approach: | They propose a sequence-to-sequence (seq2sequ) extension which learns to compose representations of different encoder layers dynamically for different tasks. |
| Outcome: | The proposed model achieves competitive results on two comprehensive and realistic benchmarks, which empirically demonstrates the effectiveness of the proposed model. |
schuBERT: Optimizing Elements of BERT (2020.acl-main)
Copied to clipboard
| Challenge: | Recent Transformer based models have achieved state-of-the-art performance for many natural language processing tasks including machine translation, question-answering tasks and semantic role labeling. |
| Approach: | They propose to reduce the number of parameters of BERT to obtain a much efficient light model. |
| Outcome: | The proposed model achieves 6.6% higher average accuracy on GLUE and SQuAD datasets than the previous model with three encoder layers while having the same number of parameters. |
Layer-Wise Multi-View Learning for Neural Machine Translation (2020.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to neural machine translation are limited to the topmost encoder layer’s context representation and cannot perceive the lower encoder layers. |
| Approach: | They propose a layer-wise multi-view learning approach to solve this problem by incorporating an auxiliary view into the model. |
| Outcome: | The proposed model can achieve stable results over multiple strong baselines and is agnostic to network architectures. |
Embeddings models for Buddhist Sanskrit (2022.lrec-1)
Copied to clipboard
| Challenge: | Despite extensive scholarly endeavors, much uncertainty still surrounds this body of literature, especially regarding matters of chronology, authorship, compositional history. |
| Approach: | They propose a corpus of Buddhist texts, a general corpus and word similarity and word analogy datasets for embeddings models. |
| Outcome: | The proposed models perform better on semantic similarity and word analogy tasks than on contextual models. |
Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented Speech (2021.emnlp-main)
Copied to clipboard
| Challenge: | Automatic Speech Recognition systems perform poorly on atypical speech and heavily accented speech. |
| Approach: | They add a residual adapter to the encoder layer to improve model adaptation . they show that the residual adapters update only a tiny fraction of the model parameters . |
| Outcome: | The proposed model fine-tuning improves performance on atypical and accented speech . the system can update only a tiny fraction of the model parameters . |
SAME: Signer-Aware Mixture-of-Experts for Test-Time Adaptation in Sign Language Translation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for supervised fine-tuning are limited due to labeled data . existing methods require long adaptation times and batch statistics are unavailable in streaming settings . |
| Approach: | They propose a plug-and-play, signer-aware Mixture-of-Experts (MoE) TTA architecture for SLT . they use a combination of lightweight MoE modules and unsupervised regularizers to decouple domain shift . |
| Outcome: | The proposed test-time adaptation outperforms existing TTA methods in sign language translation . the proposed architecture can be used in real-world deployments without labeling . |
BERTwich: Extending BERT’s Capabilities to Model Dialectal and Noisy Text (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained language models like BERT deteriorate in the face of dialect variation or noise. |
| Approach: | They propose to sandwich BERT's encoder stack between additional encoder layers trained to perform masked language modeling on noisy text. |
| Outcome: | The proposed approach promotes zero-shot transfer to dialectal text and reduces embedding space between words and noisy counterparts. |
Investigating Multi-layer Representations for Dense Passage Retrieval (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Dense retrieval models adopt vectors from the last hidden layer of the document encoder to represent a document, which is in contrast to the fact that representations in different layers of a pre-trained language model contain different kinds of linguistic knowledge and behave differently during fine-tuning. |
| Approach: | They propose to utilize representations from multiple encoder layers to make up the representation of a document, which they denote Multi-layer Representations (MLR). |
| Outcome: | The proposed model outperforms dual encoder, ME-BERT and ColBERT in the single-vector retrieval setting and with other advanced training techniques. |