Challenge: Existing methods for information extraction (IE) focus on training task-specific models, while common knowledge among different IE tasks is not explicitly modeled.
Approach: They propose a regularization-based transfer learning method for IE via an instructed graph decoder which decodes various complex structures into a graph uniformly based on corresponding instructions.
Outcome: The proposed method can learn common knowledge from existing datasets and transfer it to a new dataset with new labels.

Similar Papers

Graph-Based Decoding for Task Oriented Semantic Parsing (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing paradigms for semantic parsing are sequence-to-sequence and AMR parsers.
Approach: They propose to formulate parsing as a sequence-to-sequence task using graph-based decoding techniques developed for syntactic parsers.
Outcome: The proposed approach is competitive with sequence decoders on the standard setting and offers significant improvements in data efficiency and data availability.
Learning from Noisy Labels for Entity-Centric Information Extraction (2021.emnlp-main)

Copied to clipboard

Challenge: Recent information extraction approaches can easily overfit noisy labels and suffer from performance degradation.
Approach: They propose a co-regularization framework for entity-centric information extraction that optimizes neural models with task-specific losses and regularizes them to generate similar predictions based on agreement loss.
Outcome: The proposed framework is optimized with task-specific losses and generates similar predictions based on agreement loss.
Information Extraction with Differentiable Beam Search on Graph RNNs (2024.lrec-main)

Copied to clipboard

Challenge: Existing approaches to information extraction suffer from exposure bias due to discrepancy between training and decoding.
Approach: They propose to cast graph generation as auto-regressive sequence labeling and make it aware of decoding procedure by using differentiable beam search.
Outcome: The proposed model outperforms its non-decoding-aware version on ACE05 and ConLL04 datasets.
Abstract Meaning Representation Guided Graph Encoding and Decoding for Joint Information Extraction (2021.naacl-main)

Copied to clipboard

Challenge: Abstract Meaning Representation (IE) and Information Extraction (IE), both focus on extracting the main information from natural language texts.
Approach: They propose an AMR-guided framework for joint information extraction using a pre-trained AMR parser.
Outcome: The proposed framework achieves state-of-the-art on all IE subtasks.
Mirror: A Universal Framework for Various Information Extraction Tasks (2023.emnlp-main)

Copied to clipboard

Challenge: Recent studies often formulate IE tasks as a triplet extraction problem, but this paradigm does not support multi-span and n-ary extraction, leading to weak versatility.
Approach: They propose a multi-span cyclic graph extraction problem and a non-autoregressive graph decoding algorithm to extract all spans in a single step.
Outcome: The proposed model outperforms or reaches competitive performance with SOTA systems under few-shot and zero-shot settings and it is compatible with 57 datasets.
A Regularization-based Framework for Bilingual Grammar Induction (D19-1)

Copied to clipboard

Challenge: Existing multilingual grammar induction methods require external resources such as parallel corpora, word alignments or linguistic phylogenetic trees.
Approach: They propose a framework in which the learning process of the grammar model of one language is influenced by knowledge from the model of another language.
Outcome: The proposed method outperforms baselines on transfer grammar induction and bilingual grammar inducing on multiple languages.
Few-Shot Semantic Dependency Parsing via Graph Contrastive Learning (2024.lrec-main)

Copied to clipboard

Challenge: Existing graph neural networks (GNNs) have shown promising performance on semantic dependency parsing (SDP) training a high-performing model requires a large amount of labeled data and it is prone to over-fitting in the absence of sufficient labele .
Approach: They propose a syntax-guided graph contrastive learning framework to train GNNs with unlabeled data and fine-tune pre-trained GNN models with few-shot labeled SDP data.
Outcome: The proposed framework achieves promising results when few-shot training samples are available.
Learning to Order Graph Elements with Application to Multilingual Surface Realization (D19-63)

Copied to clipboard

Challenge: Recent advances in deep learning have shown promises in solving combinatorial optimization problems, such as sorting variable-sized sequences.
Approach: They propose an encoder-decoder framework that learns the representation for each element and predicts the ordering of each local neighborhood of the graph in turn.
Outcome: The proposed framework outperforms previous frameworks on multilingual surface realization tasks while outperforming those below by a large margin.
GraphIE: A Graph-Based Framework for Information Extraction (N19-1)

Copied to clipboard

Challenge: Most modern Information Extraction (IE) systems are implemented as sequential taggers and model local dependencies.
Approach: They propose a framework that operates over a graph representing a broad set of dependencies between textual units.
Outcome: The proposed framework outperforms the state-of-the-art sequence tagging model on three different tasks.
GLiNER2: Schema-Driven Multi-Task Learning for Structured Information Extraction (2025.emnlp-demos)

Copied to clipboard

Challenge: Existing solutions for information extraction (IE) require specialized models for different tasks or require expensive large language models.
Approach: They propose a framework that enhances the original GLiNER architecture to support named entity recognition, text classification, and hierarchical structured data extraction within a single efficient model.
Outcome: The proposed framework improves performance across diverse IE tasks and accessibility compared to LLM-based alternatives.

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