Papers with context-aware representations

6 papers
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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations