Noise Mitigation for Neural Entity Typing and Relation Extraction

Levy

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

et al. 2018

175

311

We introduce a new entity typing task: given a sentence with an entity mention, the goal is to predict a set of free-form phrases (e.g. skyscraper, songwriter, or criminal) that describe appropriate types for the target entity. This formulation allows us to use a new type of distant supervision at large scale: head words, which indicate the type of the noun phrases they appear in. We show that these ultra-fine types can be crowd-sourced, and introduce new evaluation sets that are much more diverse and fine-grained than existing benchmarks. We present a model that can predict open types, and is trained using a multitask objective that pools our new head-word supervision with prior supervision from entity linking. Experimental results demonstrate that our model is effective in predicting entity types at varying granularity; it achieves state of the art performance on an existing fine-grained entity typing benchmark, and sets baselines for our newly-introduced datasets. 1

Section: Introductionmentioning

confidence: 99%

Ultra-Fine Entity Typing

Levy

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

et al. 2018

175

311

“…Zeng et al [13] adopted piecewise convolution neural networks (PCNNs), which use the position information of words in a sentence to model the sentence representation. Yaghoobzadeh et al [14] also tried to mitigate the noise in DS by combining entity type and relation extraction models. Vashishth et al [15] used entity type and relation alias information to impose soft constraints when predicting relations.…”

Section: Related Workmentioning

confidence: 99%

Semantic Enhanced Distantly Supervised Relation Extraction via Graph Attention Network

Ouyang

Chen

Wang³

2020

Information

Distantly Supervised relation extraction methods can automatically extract the relation between entity pairs, which are essential for the construction of a knowledge graph. However, the automatically constructed datasets comprise amounts of low-quality sentences and noisy words, and the current Distantly Supervised methods ignore these noisy data, resulting in unacceptable accuracy. To mitigate this problem, we present a novel Distantly Supervised approach SEGRE (Semantic Enhanced Graph attention networks Relation Extraction) for improved relation extraction. Our model first uses word position and entity type information to provide abundant local features and background knowledge. Then it builds the dependency trees to remove noisy words that are irrelevant to relations and employs Graph Attention Networks (GATs) to encode syntactic information, which also captures the important semantic features of relational words in each instance. Furthermore, to make our model more robust against noisy words, the intra-bag attention module is used to weight the bag representation and mitigate noise in the bag. Through extensive experiments on Riedel New York Times (NYT) and Google IISc Distantly Supervised (GIDS) datasets, we demonstrate SEGRE’s effectiveness.

“…The third approach for integrating entity information into a convolutional neural network for relation classification is based on structured prediction, as we originally presented for a table filling evaluation of entity and relation recognition (Adel & Schütze, 2017). While we applied it only to a manually labeled dataset in that previous work, we now adopt it to the slot filling pipeline setting with distantly supervised training data for the first time.…”

Section: Structured Predictionmentioning

confidence: 99%

“…To calculate scores for the possible relations, all three contexts are used. In contrast to the model we proposed earlier (Adel & Schütze, 2017), we again use the flag for the order of the relation arguments for classifying the relation. Also, we do not compute representations for entities for slot filling, as motivated in Section 3.1.…”

Section: Structured Predictionmentioning

confidence: 99%

Type-aware Convolutional Neural Networks for Slot Filling

Adel¹,

Schütze²

2019

jair

Self Cite

The slot filling task aims at extracting answers for queries about entities from text, such as "Who founded Apple". In this paper, we focus on the relation classification component of a slot filling system. We propose type-aware convolutional neural networks to benefit from the mutual dependencies between entity and relation classification. In particular, we explore different ways of integrating the named entity types of the relation arguments into a neural network for relation classification, including a joint training and a structured prediction approach. To the best of our knowledge, this is the first study on type-aware neural networks for slot filling. The type-aware models lead to the best results of our slot filling pipeline. Joint training performs comparable to structured prediction. To understand the impact of the different components of the slot filling pipeline, we perform a recall analysis, a manual error analysis and several ablation studies. Such analyses are of particular importance to other slot filling researchers since the official slot filling evaluations only assess pipeline outputs. The analyses show that especially coreference resolution and our convolutional neural networks have a large positive impact on the final performance of the slot filling pipeline. The presented models, the source code of our system as well as our coreference resource is publicy available.