Papers with joint approach
An Empirical Study of Pipeline vs. Joint approaches to Entity and Relation Extraction (2022.aacl-short)
Copied to clipboard
| Challenge: | Entity and Relation Extraction tasks are often compared to pipeline approaches . a recent study shows that joint approaches can produce comparable results . |
| Approach: | They propose to use two approaches to the Entity and Relation Extraction task to compare their performance. |
| Outcome: | The proposed approach outperforms the best pipeline model but improperly designed approaches may have poor performance. |
Joint Learning for Emotion Classification and Emotion Cause Detection (D18-1)
Copied to clipboard
| Challenge: | Using a unified framework, we propose a joint approach for emotion classification and emotion cause detection. |
| Approach: | They propose a neural network-based joint approach for emotion classification and emotion cause detection which captures mutual benefits across the two sub-tasks. |
| Outcome: | The proposed approach can capture mutual benefits across two sub-tasks on Chinese microblogs. |
UniKeyphrase: A Unified Extraction and Generation Framework for Keyphrase Prediction (2021.findings-acl)
Copied to clipboard
| Challenge: | Mainstream methods that ignore the diversity among keyphrases or weakly capture the relation between tasks implicitly ignore keyphrase diversity. |
| Approach: | They propose a novel end-to-end learning framework that jointly learns to extract and generate keyphrases by exploiting latent semantic relation between extraction and generation. |
| Outcome: | The proposed approach outperforms mainstream methods on a benchmarked document on keyphrase prediction. |
Concept Pointer Network for Abstractive Summarization (D19-1)
Copied to clipboard
| Challenge: | Abstractive summarization (ABS) has gained overwhelming success owing to a tremendous development of sequence-to-sequence models and its variants. |
| Approach: | They propose a concept pointer network that leverages knowledge-based, context-aware conceptualizations to derive an extended set of candidate concepts and then points to the most appropriate choice using both the concept set and original source text. |
| Outcome: | The proposed model improves on the DUC-2004 and Gigaword datasets and human evaluation of its abstractive abilities supports the quality of the summaries produced. |
A Dual-Attention Network for Joint Named Entity Recognition and Sentence Classification of Adverse Drug Events (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Adverse drug events (ADEs) are a leading cause of death in the United States and cost around $30 $130 billion every year. |
| Approach: | They propose a multi-grained joint deep network to learn ADE entity recognition and ADE sentence classification tasks. |
| Outcome: | The proposed model improves state-of-art F1 score on the MADE 1.0 benchmark of EHR notes. |
An End-to-end Model for Entity-level Relation Extraction using Multi-instance Learning (2021.eacl-main)
Copied to clipboard
| Challenge: | Using a multi-task approach, we extract facts from documents at entity level. |
| Approach: | They propose a multi-task approach that builds upon coreference resolution and gathers relevant signals via multi-instance learning with multi-level representations combining global entity and local mention information. |
| Outcome: | The proposed model is on par with task-specific learning, though more efficient due to shared parameters and training steps. |
Empowering Active Learning to Jointly Optimize System and User Demands (2020.acl-main)
Copied to clipboard
| Challenge: | Existing approaches to active learning maximize the system performance by sampling unlabeled instances for annotation that yield the most efficient training. |
| Approach: | They propose an active learning approach that integrates active learning with an end-user application to optimize the user's training and receiving useful instances. |
| Outcome: | The proposed approach satisfies both objectives when alternative methods lead to many unsuitable exercises for end users. |
Improving Multilingual Translation by Representation and Gradient Regularization (2021.emnlp-main)
Copied to clipboard
| Challenge: | Multilingual Neural Machine Translation models often produce low quality translations, often failing to produce outputs in the right target language. |
| Approach: | They propose a joint approach to regularize NMT models at both representation-level and gradient-level to reduce off-target translation occurrences and improve zero-shot translation performance. |
| Outcome: | The proposed approach reduces off-target translation occurrences and improves zero-shot translation performance by +5.59 and +10.38 BLEU on WMT and OPUS datasets. |