Task-Oriented Learning of Word Embeddings for Semantic Relation Classification

Hashimoto, Kazuma; Stenetorp, Pontus; Misawa, Miwa; Tsuruoka, Yoshimasa

doi:10.18653/v1/k15-1027

Cited by 43 publications

(45 citation statements)

References 20 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many researchers in the general and medical domains focused on feature-based and kernel-based methods [21,[24][25][26][27][28] CNN with softmax classification [4], factor-based compositional embedding model (FCM) [29], and word embeddingbased models [30]. Many RNN-and CNN-based variants ex-ist.…”

Section: Related Workmentioning

confidence: 99%

Classifying medical relations in clinical text via convolutional neural networks

Guan

Dai

2019

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

Deep learning research on relation classification has achieved solid performance in the general domain. This study proposes a convolutional neural network (CNN) architecture with a multi-pooling operation for medical relation classification on clinical records and explores a loss function with a category-level constraint matrix. Experiments using the 2010 i2b2/VA relation corpus demonstrate these models, which do not depend on any external features, outperform previous single-model methods and our best model is competitive with the existing ensemble-based method.

show abstract

Section: Related Workmentioning

confidence: 99%

Classifying medical relations in clinical text via convolutional neural networks

Guan

Dai

2019

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

show abstract

“…The only exception is the DepNN model, which gets better result than FCM on the same embeddings. The task-specific embeddings from (Hashimoto et al, 2015) leads to the best performance (an improvement of 0.7%). This observa-10 In the task-specific setting, FCM will represent entity words and context words with separate sets of embeddings.…”

Section: Effects Of the Word Embeddingsmentioning

confidence: 99%

“…Model F1 tion suggests that the other compositional models may also benefit from the work of Hashimoto et al (2015).…”

Section: Embeddingsmentioning

confidence: 99%

“…We obtain results on on SemEval-2010 Task 8 competitive with the best reported results. Note that other work has already been published that builds on the FCM, such as Hashimoto et al (2015), , dos Santos 3 In ACE 2005, ART refers to a relation between a person and an artifact; such as a user, owner, inventor, or manufacturer relationship et al (2015), and . Additionally, we have extended FCM to incorporate a low-rank embedding of the features , which focuses on fine-grained relation extraction for ACE and ERE.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improved Relation Extraction with Feature-Rich Compositional Embedding Models

Gormley¹,

Yu²,

Dredze³

2015

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

155

View full text Add to dashboard Cite

Compositional embedding models build a representation (or embedding) for a linguistic structure based on its component word embeddings.We propose a Feature-rich Compositional Embedding Model (FCM) for relation extraction that is expressive, generalizes to new domains, and is easy-to-implement. The key idea is to combine both (unlexicalized) handcrafted features with learned word embeddings. The model is able to directly tackle the difficulties met by traditional compositional embeddings models, such as handling arbitrary types of sentence annotations and utilizing global information for composition. We test the proposed model on two relation extraction tasks, and demonstrate that our model outperforms both previous compositional models and traditional feature rich models on the ACE 2005 relation extraction task, and the SemEval 2010 relation classification task. The combination of our model and a loglinear classifier with hand-crafted features gives state-of-the-art results. We made our implementation available for general use 1 . * * Gormley and Yu contributed equally.

show abstract

“…One possible strategy is to change how the embedding is learned in the first place. For example, some approaches have been proposed to learn word embeddings that are better suited at capturing sentiment Tang et al (2016), or to learn embeddings that are optimized for relation extraction Hashimoto et al (2015). Other approaches, however, start with a pre-trained embedding, which is then modified in a particular way.…”

Section: Related Workmentioning

confidence: 99%

Modelling Salient Features as Directions in Fine-Tuned Semantic Spaces

Ager¹,

Kuželka²,

Schockaert³

2018

Proceedings of the 22nd Conference on Computational Natural Language Learning

View full text Add to dashboard Cite

In this paper we consider semantic spaces consisting of objects from some particular domain (e.g. IMDB movie reviews). Various authors have observed that such semantic spaces often model salient features (e.g. how scary a movie is) as directions. These feature directions allow us to rank objects according to how much they have the corresponding feature, and can thus play an important role in interpretable classifiers, recommendation systems, or entity-oriented search engines, among others. Methods for learning semantic spaces, however, are mostly aimed at modelling similarity. In this paper, we argue that there is an inherent trade-off between capturing similarity and faithfully modelling features as directions. Following this observation, we propose a simple method to fine-tune existing semantic spaces, with the aim of improving the quality of their feature directions. Crucially, our method is fully unsupervised, requiring only a bag-of-words representation of the objects as input.1 https://github.com/ThomasAger/ Modelling-Salient-Features-as-Directions-in-Fine-Tuned-Semantic-Spaces

show abstract

Task-Oriented Learning of Word Embeddings for Semantic Relation Classification

Cited by 43 publications

References 20 publications

Classifying medical relations in clinical text via convolutional neural networks

Classifying medical relations in clinical text via convolutional neural networks

Improved Relation Extraction with Feature-Rich Compositional Embedding Models

Modelling Salient Features as Directions in Fine-Tuned Semantic Spaces

Contact Info

Product

Resources

About