RECORD
Dynamic Global Memory for Document-level Argument Extraction
Computation and Language · Submitted 18 Sep 2022
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Empirical results show that our framework outperforms prior methods substantially and it is more robust to adversarially annotated examples with our constrained decoding design.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Extracting informative arguments of events from news articles is a challenging problem in information extraction, which requires a global contextual understanding of each document. While recent work on document-level extraction has gone beyond single-sentence and increased the cross-sentence inference capability of end-to-end models, they are still restricted by certain input sequence length constraints and usually ignore the global context between events. To tackle this issue, we introduce a new global neural generation-based framework for document-level event argument extraction by constructing a document memory store to record the contextual event information and leveraging it to implicitly and explicitly help with decoding of arguments for later events. Empirical results show that our framework outperforms prior methods substantially and it is more robust to adversarially annotated examples with our constrained decoding design. (Our code and resources are available at https://github.com/xinyadu/memory_docie for research purpose.)
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Extracting informative arguments of events from news articles is a challenging problem in information extraction, which requires a global contextual understanding of each document. | background 1.00 | 0.05 | 0.03 | asserted 1.00 |
| s1 | While recent work on document-level extraction has gone beyond single-sentence and increased the cross-sentence inference capability of end-to-end models, they are still restricted by certain input sequence length constraints and usually ignore the global context between events. | gap 0.91 | 0.05 | 0.03 | asserted 1.00 |
| s2 | To tackle this issue, we introduce a new global neural generation-based framework for document-level event argument extraction by constructing a document memory store to record the contextual event information and leveraging it to implicitly and explicitly help with decoding of arguments for later events. | contribution 0.51 | 0.88 | 0.09 | asserted 0.98 |
| s3 | Empirical results show that our framework outperforms prior methods substantially and it is more robust to adversarially annotated examples with our constrained decoding design. | result 1.00 | 0.96 | 0.82 | asserted 1.00 |
| s4 | (Our code and resources are available at https://github.com/xinyadu/memory_docie for research purpose.) | contribution 0.46 | 0.31 | 0.02 | asserted 0.87 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Extracting informative arguments of events from news articles is a challenging problem in information extraction, which requires a global contextual understanding of each document. While recent work on document-level extraction has gone beyond single-sentence and increased the cross-sentence inference capability of end-to-end models, they are still restricted by certain input sequence length constraints and usually ignore the global context between events. To tackle this issue, we introduce a new global neural generation-based framework for document-level event argument extraction by constructing a document memory store to record the contextual event information and leveraging it to implicitly and explicitly help with decoding of arguments for later events. Empirical results show that our framework outperforms prior methods substantially and it is more robust to adversarially annotated examples with our constrained decoding design. (Our code and resources are available at https://github.com/xinyadu/memory_docie for research purpose.)
Human review
How the literature uses it
2 arXiv papers cite this in 4 sentences
Papers citing it · 3 sentences without a confident label
Cites it as background 1 paper
-
With the successful application of retrieval-augmented generation (RAG) [ref] technology to various NLP tasks [ref] , some works [ref] have incorporated retrieval-augmented techniques into event extraction.
A Compressive Memory-based Retrieval Approach for Event Argument Extraction · Introduction · 0.93
What it cites
Compares with 1 paper
-
[ref] is a popular baseline for semantic role labeling (predicate-argument prediction).
Simple BERT Models for Relation Extraction and Semantic Role Labeling · Results · 0.91
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.