| Challenge: | Existing approaches to improve the likelihood of sequence prediction models are based on MLE and teacher forcing. |
| Approach: | They propose a Generative Bridging Network (GBN) that extends the point-wise ground truth to a bridge distribution conditioned on it and optimizes their KL-divergence. |
| Outcome: | The proposed bridge module can improve on two recognized sequence prediction tasks and minimize learning burden. |
Similar Papers
Attention Focusing for Neural Machine Translation by Bridging Source and Target Embeddings (P18-1)
Copied to clipboard
| Challenge: | Neural machine translation uses source and target word embeddings to improve translation quality . source and targeted word embeds are at the two ends of a long information processing procedure . |
| Approach: | They propose a method to shorten the distance between source and target words in neural machine translation by bridging source and targeting word embeddings. |
| Outcome: | The proposed method shortens the distance between source and target words in neural machine translation and strengthens their association. |
Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets (N18-1)
Copied to clipboard
| Challenge: | Experimental results show that the proposed model consistently outperforms the traditional RNNSearch and the newly emerged state-of-the-art Transformer on English-German and Chinese-English translation tasks. |
| Approach: | They propose an approach for applying GANs to NMT by building a conditional sequence generative adversarial net with two adversarials. |
| Outcome: | The proposed model outperforms the existing RNNSearch and Transformer on English-German and Chinese-English translation tasks. |
Leveraging WordNet Paths for Neural Hypernym Prediction (2020.coling-main)
Copied to clipboard
| Challenge: | Existing work on lexical relations based on distributed representations has differed widely. |
| Approach: | They propose a model that generates taxonomy paths for hypernym prediction using WordNet sequences. |
| Outcome: | The hypo2path model outperforms the best model by 4.11 points in hit-at-one (H@1) The proposed model outpersforms previous models by a factor of 0.9. |
SpanPredict: Extraction of Predictive Document Spans with Neural Attention (2021.naacl-main)
Copied to clipboard
| Challenge: | identifying predictive text in clinical notes can be as important as the predictions themselves . identifying specific content in clinical note descriptions may illuminate previously unknown risk factors . |
| Approach: | They propose a method for identifying predictive text in clinical notes . they use linear attention to formalize the problem as predictive extraction . |
| Outcome: | The proposed model preserves differentiability and allows scalable inference via stochastic gradient descent. |
A Deep Ensemble Model with Slot Alignment for Sequence-to-Sequence Natural Language Generation (N18-1)
Copied to clipboard
| Challenge: | a recent study has shown that natural language generators produce utterances with humanlike coherence and naturalness for many different kinds of content. |
| Approach: | They propose to use a neural language generator to generate a syntactically and semantically correct utterance from a given MR. |
| Outcome: | The proposed model outperforms state-of-the-art models on restaurant, TV and laptop datasets. |
Single Sequence Prediction over Reasoning Graphs for Multi-hop QA (2023.acl-long)
Copied to clipboard
| Challenge: | Recent generative approaches for multi-hop question answering (QA) use fusion-in-decoder to generate a single sequence output . but, they often have difficulty accurately identifying passages corresponding to key entities in the context . |
| Approach: | They propose a single-sequence prediction method that integrates a graph structure linking key entities in each context passage to relevant subsequent passages for each question. |
| Outcome: | The proposed method improves answer exact-match/F1 scores and faithfulness of grounding on the hotpotQA dataset and achieves state-of-the-art numbers on the Musique dataset. |
Attending to Future Tokens for Bidirectional Sequence Generation (D19-1)
Copied to clipboard
| Challenge: | Neural sequence generation is typically performed token-by-token and left-to-right. |
| Approach: | They propose to use placeholder tokens to make the sequence generation process bidirectional by taking past and future tokens into consideration when generating the actual output token. |
| Outcome: | The proposed approach outperforms baselines on two conversational tasks by a large margin. |
Predicting generalization performance with correctness discriminators (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models estimate accuracy of models on unlabeled test data, but they hide their own uncertainty. |
| Approach: | They propose a model that establishes upper and lower bounds on the accuracy without requiring gold labels for the unseen data. |
| Outcome: | The proposed model establishes upper and lower bounds on accuracy without requiring gold labels for the unseen data. |
Neural Data-to-Text Generation with LM-based Text Augmentation (2021.eacl-main)
Copied to clipboard
| Challenge: | Neural data-to-text generation is a difficult task for many new applications because of a lack of training data. |
| Approach: | They propose a few-shot approach that augments the data available for training by generating new text samples based on replacing specific values by alternative ones from the same category and pairing the new text with data samples. |
| Outcome: | The proposed approach outperforms fully supervised sequence-to-sequence models with less than 10% of the training set on both datasets. |
A Universal Discriminator for Zero-Shot Generalization (2023.acl-long)
Copied to clipboard
| Challenge: | Generative modeling has been the dominant approach for large-scale pretraining and zeroshot generalization. |
| Approach: | They propose a discriminator that predicts whether a text sample comes from the true data distribution and which option has the highest probability of coming from the real data distribution. |
| Outcome: | The proposed discriminative approach outperforms GANs on a number of NLP tasks by 16.0%, 7.8%, and 11.5% respectively. |