Improving Distantly Supervised Relation Extraction with Neural Noise Converter and Conditional Optimal Selector

Wu, Shanchan; Fan, Kai; Zhang, Qiong

doi:10.1609/aaai.v33i01.33017273

Cited by 27 publications

(19 citation statements)

References 12 publications

(23 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wang et al (2018) avoid using noisy relation labels and employs e 2 − e 1 as soft label to train the model. Wu, Fan, and Zhang (2019) propose a linear layer to obtain the connection between true labels and noisy labels. Then, conduct final prediction based on only the true labels.…”

Section: Distant Supervised Relation Extractionmentioning

confidence: 99%

Are Noisy Sentences Useless for Distant Supervised Relation Extraction?

Shang

Huang

Mao

et al. 2020

AAAI

View full text Add to dashboard Cite

The noisy labeling problem has been one of the major obstacles for distant supervised relation extraction. Existing approaches usually consider that the noisy sentences are useless and will harm the model's performance. Therefore, they mainly alleviate this problem by reducing the influence of noisy sentences, such as applying bag-level selective attention or removing noisy sentences from sentence-bags. However, the underlying cause of the noisy labeling problem is not the lack of useful information, but the missing relation labels. Intuitively, if we can allocate credible labels for noisy sentences, they will be transformed into useful training data and benefit the model's performance. Thus, in this paper, we propose a novel method for distant supervised relation extraction, which employs unsupervised deep clustering to generate reliable labels for noisy sentences. Specifically, our model contains three modules: a sentence encoder, a noise detector and a label generator. The sentence encoder is used to obtain feature representations. The noise detector detects noisy sentences from sentence-bags, and the label generator produces high-confidence relation labels for noisy sentences. Extensive experimental results demonstrate that our model outperforms the state-of-the-art baselines on a popular benchmark dataset, and can indeed alleviate the noisy labeling problem.

show abstract

Section: Distant Supervised Relation Extractionmentioning

confidence: 99%

Are Noisy Sentences Useless for Distant Supervised Relation Extraction?

Shang

Huang

Mao

et al. 2020

AAAI

View full text Add to dashboard Cite

show abstract

“…Multi-instance relation extraction is one of the popular methods for noise mitigation. Riedel et al (2010), Hoffmann et al (2011), Surdeanu et al (2012, Lin et al (2016), Yaghoobzadeh et al (2017), Vashishth et al (2018, Wu et al (2019), and Ye and Ling (2019) used this multi-instance learning concept in their proposed relation extraction models. For each entity pair, they used all the sentences that contain these two entities to find the relation between them.…”

Section: Related Workmentioning

confidence: 99%

Improving Distantly Supervised Relation Extraction with Self-Ensemble Noise Filtering

Nayak¹,

Majumder²,

Poria³

2021

Proceedings of the Conference Recent Advances in Natural Language Processing - Deep Learning for Natural Language Processing Me

View full text Add to dashboard Cite

Distantly supervised models are very popular for relation extraction since we can obtain a large amount of training data using the distant supervision method without human annotation. In distant supervision, a sentence is considered as a source of a tuple if the sentence contains both entities of the tuple. However, this condition is too permissive and does not guarantee the presence of relevant relation-specific information in the sentence. As such, distantly supervised training data contains much noise which adversely affects the performance of the models. In this paper, we propose a selfensemble filtering mechanism to filter out the noisy samples during the training process. We evaluate our proposed framework on the New York Times dataset which is obtained via distant supervision. Our experiments with multiple state-of-the-art neural relation extraction models show that our proposed filtering mechanism improves the robustness of the models and increases their F1 scores.

show abstract

“…The distance supervision method [22,23] is used to automatically annotate large-scale datasets by mapping relations in a knowledge base to text; it has been successfully used in relation extraction (RE) tasks. Distance supervision assumes that sentences that contain the same entity pairs express the same relationships.…”

Section: Distantly Supervised Relation Extractionmentioning

confidence: 99%

Entity–Relation Extraction—A Novel and Lightweight Method Based on a Gate Linear Mechanism

Peng

Chen

2020

Electronics

View full text Add to dashboard Cite

Entity–relation extraction has attracted considerable attention in recent years as a fundamental task in natural language processing. The goal of entity–relation extraction is to discover the relation structures of entities from a natural language sentence. Most existing models approach this task using recurrent neural nets (RNNs); however, given the sequential nature of RNNs, the states cannot be computed in parallel, which slows the machine comprehension. In this paper, we propose a new end-to-end model based on dilated convolutional units and the gate linear mechanism as an alternative to those recurrent models. We find that relation extraction becomes more difficult as the sentence length increases. In this paper, we introduce dynamic convolutions based on lightweight convolutions to process long sequences, which thus reduces the number of parameters to a low level. Another challenge in relation extraction is relation spans potentially overlapping in a sentence, representing a bottleneck for the detection of multiple relational triplets. To alleviate this problem, we design an entirely new prediction scheme to extract relational pairs and additionally boost performance. We conduct experiments on two widely used datasets, and the results show that our model outperforms the baselines by a large margin.

show abstract

Improving Distantly Supervised Relation Extraction with Neural Noise Converter and Conditional Optimal Selector

Cited by 27 publications

References 12 publications

Are Noisy Sentences Useless for Distant Supervised Relation Extraction?

Are Noisy Sentences Useless for Distant Supervised Relation Extraction?

Improving Distantly Supervised Relation Extraction with Self-Ensemble Noise Filtering

Entity–Relation Extraction—A Novel and Lightweight Method Based on a Gate Linear Mechanism

Contact Info

Product

Resources

About