Papers with decoding procedure
Conformal Nucleus Sampling (2023.findings-acl)
Copied to clipboard
| Challenge: | Modern language generation methods employ one of a handful of standard decoding strategies . greedy search and other methods generate dull text or degenerate text . |
| Approach: | They employ a calibration procedure to calibrate the parameter p as a function of the entropy of the next word distribution. |
| Outcome: | The proposed method overconfidently selects the word with the highest probability . the greedy method and its beam search variations tend to return dull text or degenerate text . |
Grammar-Constrained Neural Semantic Parsing with LR Parsers (2021.findings-acl)
Copied to clipboard
| Challenge: | a context-free grammar can be used to enforce syntactical constraints when predicting logical forms. |
| Approach: | They propose a model that uses an LR parser to maintain syntactically valid sequences throughout the decoding procedure. |
| Outcome: | The proposed model is conceptually simpler and adds less overhead during inference compared to other approaches . it is compared with existing grammar-guided decoding frameworks and is cost-effective . |
Accelerating Neural Transformer via an Average Attention Network (P18-1)
Copied to clipboard
| Challenge: | Using parallelizable attention networks, the neural Transformer is slow to train due to auto-regressive architecture and self-attention in the decoder. |
| Approach: | They propose an average attention network to replace the original self-attention model in the decoder of the neural Transformer. |
| Outcome: | The proposed network can decode sentences over four times faster than the original version with almost no loss in training time and translation performance. |
Plug-and-Play Conversational Models (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Large conversational models that generate coherent and fluent responses often require large dialogue datasets. |
| Approach: | They propose and evaluate plug-and-play methods for controllable response generation . they demonstrate a high degree of control over the generated conversational responses . |
| Outcome: | The proposed method does not require further computation at decoding time and does not need fine-tuning of a large language model. |
Competency-Aware Neural Machine Translation: Can Machine Translation Know its Own Translation Quality? (2022.emnlp-main)
Copied to clipboard
| Challenge: | Neural machine translation models are often criticized for failures that happen without competency awareness. |
| Approach: | They propose a method that extends conventional NMT with a self-estimator to translate a source sentence and estimate its competency. |
| Outcome: | The proposed method performs on translation tasks intact and on quality estimation tasks better than existing methods. |
Accelerating Transformer Inference for Translation via Parallel Decoding (2023.acl-long)
Copied to clipboard
Andrea Santilli, Silvio Severino, Emilian Postolache, Valentino Maiorca, Michele Mancusi, Riccardo Marin, Emanuele Rodola
| Challenge: | Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT) Existing methods to solve this problem are expensive and require changes to the model. |
| Approach: | They propose to reframe autoregressive decoding with a parallel formulation . they propose to speed up existing models without training or modifications while retaining translation quality. |
| Outcome: | The proposed model speeds up existing models without training or modifications while retaining translation quality. |
Information Extraction with Differentiable Beam Search on Graph RNNs (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing approaches to information extraction suffer from exposure bias due to discrepancy between training and decoding. |
| Approach: | They propose to cast graph generation as auto-regressive sequence labeling and make it aware of decoding procedure by using differentiable beam search. |
| Outcome: | The proposed model outperforms its non-decoding-aware version on ACE05 and ConLL04 datasets. |