Distant Supervision for Relation Extraction with Ranking-Based Methods

Abstract

Abstract:Relation extraction has benefited from distant supervision in recent years with the development of natural language processing techniques and data explosion. However, distant supervision is still greatly limited by the quality of training data, due to its natural motivation for greatly reducing the heavy cost of data annotation. In this paper, we construct an architecture called MIML-sort (Multi-instance Multi-label Learning with Sorting Strategies), which is built on the famous MIML framework. Based on MIML-sort, we propose three ranking-based methods for sample selection with which we identify relation extractors from a subset of the training data. Experiments are set up on the KBP (Knowledge Base Propagation) corpus, one of the benchmark datasets for distant supervision, which is large and noisy. Compared with previous work, the proposed methods produce considerably better results. Furthermore, the three methods together achieve the best F 1 on the official testing set, with an optimal enhancement of F 1 from 27.3% to 29.98%.

Distant Supervision with Transductive Learning for Adverse Drug Reaction Identification from Electronic Medical Records

“…Lately, Mintz et al [ 21 ] propose an interchangeable paradigm, distant supervision , to extract relation from Freebase. Their assumption relies on “if the two entities participate in a relation, any sentence that contains those two entities might express that relation.” The distant supervision has been applied recently for relation extraction problem [ 41 – 45 ] by mapping relations of any couple entities from knowledge bases (e.g., Freebase, YAGO) to a sentence in a large-scale text corpus (e.g., New York Times). Similarly, in previous works on application for emotion classification from social media (i.e., tweets, microblog text) [ 46 – 48 ], the authors make use of distant supervision to map lexicon emoticons or smilies from knowledge bases (i.e., Wikipedia, Weibo) to large-scale noisy texts.…”

Dual CNN for Relation Extraction with Knowledge-Based Attention and Word Embeddings

“…Recently, many researchers have begun to apply deep learning techniques to RE [22, 23]. Socher et al [6] proposed using RNNs to solve RE problems; the method first parses a sentence and then learns the vector representation for each node on the syntax tree.…”

Ranking-Based Automatic Seed Selection and Noise Reduction for Weakly Supervised Relation Extraction

“…Intxaurrondo et al (2013) filtered out noisy mentions from the distantly supervised dataset using their frequencies, PMI, or the similarity between the centroids of all relation mentions and each individual mention. Xiang et al (2016) introduced ranking-based methods according to different strategies to select effective training groups. Li et al (2017) proposed three novel heuristics that use lexical and syntactic information to remove noise in the biomedical domain.…”