A Joint Neural Model for Information Extraction with Global Features

By Ying Lin, Heng Ji, Fei Huang, Lingfei Wu. Annual Meeting of the Association for Computational Linguistics, 2020

466 citations recorded by the source corpus.

Most existing joint neural models for Information Extraction (IE) use local task-specific classifiers to predict labels for individual instances (e.g., trigger, relation) regardless of their interactions. For example, a victim of a die event is likely to be a victim of an attack event in the same sentence. In order to capture such cross-subtask and cross-instance inter-dependencies, we propose a joint neural framework, OneIE, that aims to extract the globally optimal IE result as a graph from an input sentence. OneIE performs end-to-end IE in four stages: (1) Encoding a given sentence as contextualized word representations; (2) Identifying entity mentions and event triggers as nodes; (3) Computing label scores for all nodes and their pairwise links using local classifiers; (4) Searching for the globally optimal graph with a beam decoder. At the decoding stage, we incorporate global features to capture the cross-subtask and cross-instance interactions. Experiments show that adding global features improves the performance of our model and achieves new state of-the-art on all subtasks. In addition, as OneIE does not use any language-specific feature, we prove it can be easily applied to new languages or trained in a multilingual manner.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/222dcbf5ee19fdfc9cfbd9c75af168a5c2122a4a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

Citations in the corpus

Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction (2021, methodology): “…cross-sentence context (Wadden et al., 2019); GAIL is an inverse reinforcement learning-based joint entity and event extraction model (Zhang et al., 2019b); OneIE is an end-to-end IE system which employs global feature and beam search to extract globally optimal event structures (Lin et al., 2020).”
Joint Constrained Learning for Event-Event Relation Extraction (2020, background): “Moreover, while it is a common strategy to combine multiple training data in multi-task learning (Lin et al., 2020), our work is distinguished by enhancing the learning process by pushing the model towards a coherent output that satisﬁes logical constraints across separate tasks.”
Paired Representation Learning for Event and Entity Coreference (2020, methodology): “We use the preprocessed data split by Lin et al. (2020). Event Clusters includes singletons.”
Prefix-to-SQL: Text-to-SQL Generation from Incomplete User Questions (2021, background): “…community, mapping natural language utterances to SQL queries for databases, also known as SQLbased semantic parsing, has attracted increasing attention (Yin and Neubig, 2017; Dong and Lapata, 2018b; Guo et al., 2019; Wang et al., 2020; Bogin et al., 2019; Lin et al., 2020; Yin and Neubig, 2019).”
Lifelong Event Detection with Knowledge Transfer (2021, methodology): “Other methods on joint information extraction (Li et al., 2013; Wadden et al., 2019; Lin et al., 2020) also include event detection as a subtask.”
KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction (2021, methodology): “2019), applying LMs as the backbone of RE systems (Lin et al. 2020; Wang et al. 2020; Li et al. 2020; Zhang et al. 2021b; Zheng et al. 2021; Ye et al. 2021; Zhang et al. 2021a) has become a standard procedure.”
Unified Structure Generation for Universal Information Extraction (2022, methodology): “Event For ACE05-Evt, we follow the same types, data splits, and pre-processing steps as Lin et al. (2020).”
Event Extraction by Answering (Almost) Natural Questions (2020, methodology): “Although joint models (Yang and Mitchell, 2016; Nguyen and Nguyen, 2019; Zhang et al., 2019a; Lin et al., 2020) have been proposed to mitigate this issue, error propagation (Li et al.”
The Art of Prompting: Event Detection based on Type Specific Prompts (2022, methodology): “…Liao and Grishman, 2010; McClosky et al., 2011; Li et al., 2013; Chen et al., 2015; Cao et al., 2015; Feng et al., 2016; Yang and Mitchell, 2016; Nguyen et al., 2016; Zhang et al., 2017; Lin et al., 2020; Wang et al., 2021b), however, they cannot be directly applied to detect new types of events.”
A Frustratingly Easy Approach for Entity and Relation Extraction (2021, methodology): “more recent work Lin et al. (2020) further extends DYGIE++ by incorporating global features based on cross-substask and cross-instance constraints.”
BARTScore: Evaluating Generated Text as Text Generation (2021, background): “By learning to predict the words or sentences in natural text, these models simultaneously learn to extract features that not only benefit mainstream NLP tasks such as information extraction [18, 31], question answering [1,21], text summarization [33,65] but also have proven effective in development”
Extracting Temporal Event Relation with Syntactic-Guided Temporal Graph Transformer (2021, background): “Progress in natu-ral language processing, especially information extraction (Lin et al., 2020; Huang and Ji, 2020), has helped automate the identiﬁcation of each single S1: Israel's prime minister has ( e 1 : apologised ) to Turkey for " any errors that could have led to loss of life " during the…”
The Case for Translation-Invariant Self-Attention in Transformer-Based Language Models (2021, background): “, 2020), and information extraction (Wadden et al., 2019; Lin et al., 2020).”
Efficient Attentions for Long Document Summarization (2021, methodology): “On PubMed, we re-train OneIE on Genia 2011 (BioNLP, 2011) and 2013 (BioNLP, 2013), and PubMed (Wei et al., 2019) datasets to extract domain-speciﬁc entities and events, such as entities of Gene and Disease .”
Code4Struct: Code Generation for Few-Shot Structured Prediction from Natural Language (2022, unknown): “We follow Wadden et al. (2019); Lin et al. (2020) for dataset processing.”