Peng Xu, Hamidreza Saghir, Jin Sung Kang, Teng Long, Avishek Joey Bose, Yanshuai Cao, Jackie Chi Kit Cheung
| Challenge: | Existing coherence models do not generalize to unseen categories of text . previous work advocates for generative models for cross-domain generalization . |
| Approach: | They propose a local discriminative neural model with a smaller negative sampling space that can discriminate against incorrect orderings. |
| Outcome: | The proposed model outperforms state-of-the-art methods on a standard benchmark dataset on the Wall Street Journal corpus and multiple challenging settings on Wikipedia articles. |
Similar Papers
A Unified Neural Coherence Model (D19-1)
Copied to clipboard
| Challenge: | Existing models for coherence modeling fail on harder tasks with more realistic application scenarios. |
| Approach: | They propose a unified coherence model that incorporates sentence grammar, inter-sentence coherent relations, and global coherency patterns into a common neural framework. |
| Outcome: | The proposed model outperforms existing models on local and global discrimination tasks and outperformed existing models by a good margin. |
A Neural Local Coherence Model for Text Quality Assessment (D18-1)
Copied to clipboard
| Challenge: | Existing approaches to local coherence modeling capture text relatedness at the level of sentence-to-sentence transitions. |
| Approach: | They propose a local coherence model that captures the flow of what connects adjacent sentences . they represent the semantics of a sentence by a vector and capture its state at each word . |
| Outcome: | The proposed model is beneficial for readability assessment and essay scoring tasks. |
Multi-Task Learning for Coherence Modeling (P19-1)
Copied to clipboard
| Challenge: | Existing models for assessing discourse coherence have been developed for summarization and language assessment. |
| Approach: | They propose a hierarchical neural network that learns to predict a document-level coherence score along with word-level grammatical roles, taking advantage of inductive transfer between the two tasks. |
| Outcome: | The proposed framework can predict document-level coherence score and word-level grammatical roles using inductive transfer between the two tasks. |
Rethinking Self-Supervision Objectives for Generalizable Coherence Modeling (2022.acl-long)
Copied to clipboard
| Challenge: | Prior work on text generation models focused on new architectures for permuted document tasks. |
| Approach: | They propose to use a basic model architecture to improve coherence evaluation of machine generated text. |
| Outcome: | The proposed model improves on a task-independent test set and shows significant improvements in coherence evaluations of downstream tasks. |
Entity-based Neural Local Coherence Modeling (2022.acl-long)
Copied to clipboard
| Challenge: | Recent neural coherence models encode the input document using large-scale pretrained language models. |
| Approach: | They propose an entity-based neural local coherence model which is linguistically more sound than previous models. |
| Outcome: | The proposed model outperforms existing models on three downstream tasks. |
A Novel Computational Modeling Foundation for Automatic Coherence Assessment (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing models for text coherence assessment rely on a proxy task . however, this approach does not capture the full range of factors contributing to coherency. |
| Approach: | They propose a formal linguistic definition of what makes a discourse coherent and formalize these conditions as respective computational tasks that are jointly trained. |
| Outcome: | The proposed model improves on two human-rated coherence benchmarks. |
How coherent are neural models of coherence? (2020.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to model coherence are limited to small newswire corpora . evaluators need to be trained on lexical and document levels to perform evaluations . |
| Approach: | They propose four generic evaluation tasks that capture coherence-specific properties . they aim at capturing correct use of discourse connectives and lexical cohesion . |
| Outcome: | The proposed tasks capture coherence-specific properties, including correct use of discourse connectives, lexical cohesion, temporal consistency among events and participants in a story. |
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 . |
Centering-based Neural Coherence Modeling with Hierarchical Discourse Segments (2020.emnlp-main)
Copied to clipboard
| Challenge: | Prior studies of coherence focused on identifying semantic relations between adjacent sentences. |
| Approach: | They propose a coherence model which takes discourse structural information into account without relying on human annotations. |
| Outcome: | The proposed model performs state-of-the-art on automated essay scoring and assessing writing quality tasks. |
Diversity-Aware Coherence Loss for Improving Neural Topic Models (2023.acl-short)
Copied to clipboard
| Challenge: | Experimental results show that our method significantly improves the performance of neural topic models without requiring any pretraining or additional parameters. |
| Approach: | They propose a variational autoencoder framework that minimizes the posterior and prior divergence and a diversity-aware coherence loss that encourages the model to learn corpus-level coherency scores while maintaining high diversity between topics. |
| Outcome: | The proposed approach significantly improves the performance of neural topic models without pretraining or additional parameters. |