Extracting Relations between Non-Standard Entities using Distant Supervision and Imitation Learning

Abstract

Distantly supervised approaches have become popular in recent years as they allow training relation extractors without textbound annotation, using instead known relations from a knowledge base and a large textual corpus from an appropriate domain. While state of the art distant supervision approaches use off-theshelf named entity recognition and classification (NERC) systems to identify relation arguments, discrepancies in domain or genre between the data used for NERC training and the intended domain for the relation extractor can lead to low performance. This is particularly problematic for "non-standard" named entities such as album which would fall into the MISC category. We propose to ameliorate this issue by jointly training the named entity classifier and the relation extractor using imitation learning which reduces structured prediction learning to classification learning. We further experiment with Web features different features and compare against using two off-the-shelf supervised NERC systems, Stanford NER and FIGER, for named entity classification. Our experiments show that imitation learning improves average precision by 4 points over an one-stage classification model, while removing Web features results in a 6 points reduction. Compared to using FIGER and Stanford NER, average precision is 10 points and 19 points higher with our imitation learning approach.

Noise Mitigation for Neural Entity Typing and Relation Extraction

“…Entity types for relation extraction. Several studies have integrated entity type information into relation extraction -either coarse-grained (Hoffmann et al, 2011;Zhou et al, 2005) or finegrained (Liu et al, 2014;Du et al, 2015;Augenstein et al, 2015;Vlachos and Clark, 2014;Ling and Weld, 2012) entity types. In contrast to most of this work, but similar to , we do not incorporate binary entity type values, but probabilistic outputs.…”

CoType

“…However, such a "pipeline" diagram ignores the dependencies between different sub tasks and may suffer from error propagation between the tasks. Recent studies try to integrate entity extraction with relation extraction by performing global sequence labeling for both entities and relations [24,32,1], incorporating type constraints between relations and their arguments [44], or modeling factor graphs [47]. However, these methods require human-annotated corpora (cleaned and general) for model training and rely on existing entity detectors to provide entity mentions.…”

“…This assumes seeds are unambiguous and sufficiently frequent in the corpus, which requires careful seed se-arXiv:1610.08763v2 [cs.CL] 2 Jun 2017 Dataset NYT [43] Wiki-KBP [12], BioInfer [39] # of entity Table 1: A study of type label noise. (1): %entity mentions with multiple sibling entity types (e.g., actor, singer) in the given entity type hierarchy; (2): %relation mentions with multiple relation types, for the three experiment datasets. lection by human [2].…”

Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017)

“…Imitation learning (Schaal, 1999;Abbeel and Ng, 2004;Ross et al, 2011) is a popular instance of learning from demonstration where the algorithm observes a human expert perform a series of actions to accomplish the task and learns a policy that "imitates" the expert with the purpose of generalizing to unseen data. Imitation learning is increasingly being used in NLP (Vlachos and Clark, 2014;Augenstein et al, 2015;Beck et al, 2016;Goodman et al, 2016a,b). However, all these models focus on learning respective NLP models from the final supervision e.g.…”