Papers with context-aware representations
Joint Detection and Coreference Resolution of Entities and Events with Document-level Context Aggregation (2021.acl-srw)
Copied to clipboard
| Challenge: | Recent work on extracting information from sentences or paragraphs has a difficulty analyzing longer contexts. |
| Approach: | They propose a jointly trained model that can be used for various information extraction tasks at the document level. |
| Outcome: | The proposed model improves entity and event typing and typing on documents from the ACE05-E+ dataset. |
Neural Token Representations and Negation and Speculation Scope Detection in Biomedical and General Domain Text (D19-62)
Copied to clipboard
| Challenge: | Existing evidence for improved performance on natural language tasks is unclear to what degree the learned token representations capture and encode highlevel morphological/syntactic knowledge about the usage of a given token in a sentence. |
| Approach: | They propose to use context-aware token representations to capture morphological/syntactic knowledge about the usage of a given word/token in a sentence. |
| Outcome: | The proposed representations capture and encode high-level morphological/syntactic knowledge about the usage of a given token in a sentence. |
Revisiting and Advancing Chinese Natural Language Understanding with Accelerated Heterogeneous Knowledge Pre-training (2022.emnlp-industry)
Copied to clipboard
Taolin Zhang, Junwei Dong, Jianing Wang, Chengyu Wang, Ang Wang, Yinghui Liu, Jun Huang, Yong Li, Xiaofeng He
| Challenge: | Existing knowledge-enhanced pre-trained language models (KEPLMs) can capture internal knowledge, but can't understand external background knowledge. |
| Approach: | They propose to use Chinese knowledge-enhanced pre-trained language models to improve context-aware representations via learning from structured relations in knowledge bases. |
| Outcome: | Experiments show that Chinese knowledge-enhanced pre-trained language models outperform strong baselines over various benchmark NLP tasks and in different model sizes. |
ASTRA: Automatic Schema Matching using Machine Translation (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Currently, eCommerce platforms use schema matching to structure product information from disparate sources. |
| Approach: | They propose to model the schema matching problem as a neural machine translation task . they propose to use open-source seq2seq models fine-tuned on product attribute mappings to build a framework . |
| Outcome: | The proposed model achieves a significant performance boost (15% precision and 7% recall uplift) it can support new attributes with precision 95% using only five labeled samples per attribute. |
Relation Extraction using Explicit Context Conditioning (N19-1)
Copied to clipboard
| Challenge: | Existing methods for relation extraction fail to capture complex and long dependencies . end-to-end models that learn both NER and RE can solve this problem . |
| Approach: | They propose to use second-order relations to compute relation scores for relation extraction (RE) . they propose to combine second- and first-order relation scores to obtain final relation scores . |
| Outcome: | The proposed method leads to state-of-the-art performance over two biomedical datasets. |
Beyond the Scientific Document: A Citation-Aware Multi-Granular Summarization Approach with Heterogeneous Graphs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results demonstrate that our model outperforms existing approaches for summarizing documents. |
| Approach: | proposed model constructs a heterogeneous graph to represent a document and its relevant external citations. |
| Outcome: | The proposed model outperforms existing models in three different scenarios. |