| Challenge: | Neural encoders have allowed dependency parsers to shift from higher-order structured models to simpler first-order ones, making decoding faster and still achieving better accuracy than non-neural parser. |
| Approach: | They found that neural parsers may benefit from higher-order features when employing a powerful pre-trained encoder, such as BERT. |
| Outcome: | Using a pre-trained encoder, we found that higher-order models are more accurate on full sentence parses and match of modifier lists. |
Similar Papers
Enhancing Structure-aware Encoder with Extremely Limited Data for Graph-based Dependency Parsing (2022.coling-1)
Copied to clipboard
| Challenge: | Dependency parsing is an important natural language processing task which analyzes the syntactic structure of an input sentence. |
| Approach: | They propose a structure-aware encoder pre-trained on auto-parsed data to improve dependency parsing . they propose combining gold dependency trees with existing parsers to improve parser performance . |
| Outcome: | The proposed approach outperforms baselines under different parsers and dependency standards under different parameters and model architectures. |
Graph-based Dependency Parsing with Graph Neural Networks (P19-1)
Copied to clipboard
| Challenge: | In graph-based dependency parsers, learning representations is gaining in importance, and we use graph neural networks to learn the representations. |
| Approach: | They propose to use graph neural networks to learn dependency tree nodes and propose to add a new aggregation function to the system. |
| Outcome: | The proposed model achieves the best UAS and LAS on PTB (96.0%, 94.3%) without using external resources. |
Second-Order Neural Dependency Parsing with Message Passing and End-to-End Training (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing approaches to dependency parsing use exact and approximate inference to find the best parse tree. |
| Approach: | They propose a second-order graph-based neural dependency parsing approach using message passing and end-to-end neural networks. |
| Outcome: | The proposed methods match the state-of-the-art second-order graph-based neural dependency parsers and have significantly faster speed in training and testing. |
Second-Order Unsupervised Neural Dependency Parsing (2020.coling-main)
Copied to clipboard
| Challenge: | supervised dependency parsers can reach a very high accuracy, but they require treebanks for training. |
| Approach: | They propose a second-order extension of unsupervised neural dependency models that incorporate grandparent-child or sibling information. |
| Outcome: | The proposed model achieves 10% improvement over the previous state-of-the-art model on the full WSJ dataset. |
The (Non-)Utility of Structural Features in BiLSTM-based Dependency Parsers (P19-1)
Copied to clipboard
| Challenge: | Existing non-neural dependency parsers benefit from information coming from structural features . however, their successors lack explicit information about the structural context . |
| Approach: | They propose to model the structural context of a biLSTM-based dependency parser with features built from partial subtrees. |
| Outcome: | The proposed models do not use any conventional structural features but capture implicitly the structural context. |
Semantic Dependency Parsing with Edge GNNs (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing semantic dependency parsers use factor graphs to generate a tree structure, but they are ill-suited for a more complex semantic relationship representation. |
| Approach: | They propose a second-order neural CRF parser that uses factor graphs to generate a dependency edge and define neighbors in terms of sibling, co-parent, and grandparent relationships. |
| Outcome: | The proposed model outperforms the first-order biaffine parser on English datasets and shows that it is more efficient than the first order. |
Neural Reranking for Dependency Parsing: An Evaluation (2020.acl-main)
Copied to clipboard
| Challenge: | Recent work shows that neural rerankers can improve dependency parsing results over the top k trees produced by a base parser. |
| Approach: | They propose to use a discriminative reranker to improve dependency parsing results . they propose to incorporate global information into the model to improve parse accuracies . |
| Outcome: | The proposed model outperforms existing models on English and German and Czech, and is the only one to improve on German and Chinese data. |
Efficient Second-Order TreeCRF for Neural Dependency Parsing (2020.acl-main)
Copied to clipboard
| Challenge: | In the deep learning (DL) era, dependency parsing models are extremely simplified with little hurt on performance thanks to the remarkable capability of multi-layer BiLSTMs in context representation. |
| Approach: | They propose to extend the biaffine parser to a second-order TreeCRF extension to reduce the complexity of the inside-outside algorithm. |
| Outcome: | The proposed extension can be used to batchify the inside and Viterbi algorithms and avoid the complex outside algorithm via efficient back-propagation. |
Revealing the Myth of Higher-Order Inference in Coreference Resolution (2020.emnlp-main)
Copied to clipboard
| Challenge: | Adapted coreference resolution models have only marginally improved performance over representation learning. |
| Approach: | They implement an end-to-end coreference system and four HOI approaches to analyze the impact of higher-order inference on coreference resolution. |
| Outcome: | The proposed model shows that the impact of higher-order inference (HOI) on coreference resolution is negative to marginal, providing a new perspective on the task. |
AMR Parsing with Latent Structural Information (2020.acl-main)
Copied to clipboard
| Challenge: | Abstract Meaning Representations (AMRs) capture sentence-level semantics structural representations to broad-coverage natural sentences. |
| Approach: | They investigate parsing AMR with explicit dependency structures and interpretable latent structures. |
| Outcome: | The proposed model achieves best results on both AMR 2.0 and AMR 1.0 . the proposed model has been adopted in downstream NLP tasks, including text summarization and question answering. |