Papers with relation classifiers
What Causes the Failure of Explicit to Implicit Discourse Relation Recognition? (2024.naacl-long)
Copied to clipboard
| Challenge: | Prior work claimed that explicit classifiers perform poorly in implicit scenarios . a label shift occurs after connectives are removed, but no empirical evidence supports this claim . |
| Approach: | They propose to prove that the discourse relations expressed by some explicit instances will change when connectives disappear. |
| Outcome: | The proposed methods outperform strong baselines on PDTB 2.0, PDTT 3.0, and the GUM dataset. |
Misleading Relation Classifiers by Substituting Words in Texts (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to generate adversarial examples for relation classification are vulnerable to adversarials. |
| Approach: | They propose a method that uses most important parts of speech to substitute words with synonyms or hyponyms to generate adversarial texts of high quality. |
| Outcome: | The proposed method can generate adversarial texts of high quality and most relationships can be correctly identified in the process of human evaluation. |
HyperNetwork-based Decoupling to Improve Model Generalization for Few-Shot Relation Extraction (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies cannot generalize well to unseen relations using Prototypical Networks . current approaches are dependent on large amount of labeled data and cannot deal with unseense relations well. |
| Approach: | They propose a HyperNetwork-based Decoupling approach to improve FSRE generalization . they propose FSre models with an encoder, network generator and refined classifiers . |
| Outcome: | The proposed method improves the generalization of few-shot relation extraction models. |
Cross-modal Coherence Modeling for Caption Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for image captioning do not guarantee consistent image-text relations . current models do not provide enough data for training robust captioning models . |
| Approach: | They use an annotation protocol specifically devised for capturing image–caption coherence relations to study image captioning. |
| Outcome: | The proposed protocol improves image captioning models with coherence relations . the dataset is large enough to alleviate content hallucinations, the authors show . |
Next Sentence Prediction helps Implicit Discourse Relation Classification within and across Domains (D19-1)
Copied to clipboard
| Challenge: | Discourse relation classification is one of the most difficult tasks in discourse parsing. |
| Approach: | They propose a bidirectional encoder representation from transformer model that encodes a representation of likely next sentences. |
| Outcome: | The proposed model outperforms the state-of-the-art system in 11-way classification by 8% points on the standard PDTB dataset. |
Model-Agnostic Meta-Learning for Relation Classification with Limited Supervision (P19-1)
Copied to clipboard
| Challenge: | Existing methods for relation classification are based on labelled training data, which can be expensive to obtain and available only in limited quantities. |
| Approach: | They propose a model-agnostic meta-learning protocol for training relation classifiers to achieve enhanced predictive performance in limited supervision settings. |
| Outcome: | The proposed protocol improves the performance of two state-of-the-art supervised relation classification models on two relation classification datasets. |