The AI2 system at SemEval-2017 Task 10 (ScienceIE): semi-supervised end-to-end entity and relation extraction

@inproceedings{Ammar2017TheAS,
  title={The AI2 system at SemEval-2017 Task 10 (ScienceIE): semi-supervised end-to-end entity and relation extraction},
  author={Waleed Ammar and Matthew E. Peters and Chandra Bhagavatula and Russell Power},
  booktitle={*SEMEVAL},
  year={2017}
}
This paper describes our submission for the ScienceIE shared task (SemEval- 2017 Task 10) on entity and relation extraction from scientific papers. Our model is based on the end-to-end relation extraction model of Miwa and Bansal (2016) with several enhancements such as semi-supervised learning via neural language models, character-level encoding, gazetteers extracted from existing knowledge bases, and model ensembles. Our official submission ranked first in end-to-end entity and relation… 

Figures and Tables from this paper

GU IRLAB at SemEval-2018 Task 7: Tree-LSTMs for Scientific Relation Classification

TLDR
This work presents the tree-based LSTM network for SemEval 2018 Task 7, and provides an ablation study of features included as input to the network.

SemEval 2017 Task 10: ScienceIE - Extracting Keyphrases and Relations from Scientific Publications

We describe the SemEval task of extracting keyphrases and relations between them from scientific documents, which is crucial for understanding which publications describe which processes, tasks and

A Richer-but-Smarter Shortest Dependency Path with Attentive Augmentation for Relation Extraction

TLDR
A combined deep neural model with a LSTM network on word sequences and a CNN on RbSP, which is based on the basic information in the SDP enhanced with information selected by several attention mechanisms with kernel filters, namely R bSP (Richer-but-Smarter SDP).

Duluth at SemEval-2021 Task 11: Applying DeBERTa to Contributing Sentence Selection and Dependency Parsing for Entity Extraction

TLDR
The Duluth system that participated in SemEval-2021 Task 11, NLP Contribution Graph uses deBERTa for multi-class sentence classification to extract the contributing sentences and their type, and dependency parsing to outline each sentence and extract subject-predicate-object triples.

Deep neural model with self-training for scientific keyphrase extraction

TLDR
A neural network based approach for scientific keyphrase extraction, which employs the bidirectional long short-memory (LSTM) to represent the sentences in the article and efficiently incorporates the unlabeled data and achieve competitive performance compared with previous state-of-the-art systems.

End-to-End NLP Knowledge Graph Construction

TLDR
This paper applies the SciNLP-KG framework to 30,000 NLP papers from ACL Anthology to build a large-scale KG, which can facilitate automatically constructing scientific leaderboards for the NLP community and indicates that the resulting KG contains high-quality information.

A Bag-of-concepts Model Improves Relation Extraction in a Narrow Knowledge Domain with Limited Data

TLDR
This paper explores a traditional relation extraction task in the context of limited annotated data and a narrow knowledge domain with a clinical corpus consisting of 200 breast cancer follow-up treatment letters in which 16 distinct types of relations are annotated and introduces a new bag-of-concepts (BoC) approach to feature engineering based on the state of the art word embeddings and word synonyms.

Semi-supervised sequence tagging with bidirectional language models

TLDR
A general semi-supervised approach for adding pretrained context embeddings from bidirectional language models to NLP systems and apply it to sequence labeling tasks, surpassing previous systems that use other forms of transfer or joint learning with additional labeled data and task specific gazetteers.

Dataset Mention Extraction and Classification

TLDR
This work proposes various neural baselines and evaluates these model on one-plus and zero-shot classification scenarios and further explores various joint learning approaches - exploring the synergy between the tasks - and reports the issues with such techniques.

Simultaneously Self-Attending to All Mentions for Full-Abstract Biological Relation Extraction

TLDR
A model which simultaneously predicts relationships between all mention pairs in a document and a new dataset an order of magnitude larger than existing human-annotated biological information extraction datasets and more accurate than distantly supervised alternatives is proposed.
...

References

SHOWING 1-10 OF 10 REFERENCES

SemEval 2017 Task 10: ScienceIE - Extracting Keyphrases and Relations from Scientific Publications

We describe the SemEval task of extracting keyphrases and relations between them from scientific documents, which is crucial for understanding which publications describe which processes, tasks and

End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures

TLDR
A novel end-to-end neural model to extract entities and relations between them and compares favorably to the state-of-the-art CNN based model (in F1-score) on nominal relation classification (SemEval-2010 Task 8).

Natural Language Processing (Almost) from Scratch

We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including part-of-speech tagging, chunking, named entity

Exploring the Limits of Language Modeling

TLDR
This work explores recent advances in Recurrent Neural Networks for large scale Language Modeling, and extends current models to deal with two key challenges present in this task: corpora and vocabulary sizes, and complex, long term structure of language.

One billion word benchmark for measuring progress in statistical language modeling

TLDR
A new benchmark corpus to be used for measuring progress in statistical language modeling, with almost one billion words of training data, is proposed, which is useful to quickly evaluate novel language modeling techniques, and to compare their contribution when combined with other advanced techniques.

GloVe: Global Vectors for Word Representation

TLDR
A new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods and produces a vector space with meaningful substructure.

Adam: A Method for Stochastic Optimization

TLDR
This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.

Long Short-Term Memory

TLDR
A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.

Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

TLDR
This work presents iterative parameter estimation algorithms for conditional random fields and compares the performance of the resulting models to HMMs and MEMMs on synthetic and natural-language data.

Natural language processing ( almost ) from scratch . In JMLR . Sepp Hochreiter and Jürgen Schmidhuber . 1997 . Long short - term memory

  • Neural Computation
  • 2011