skip to main content

Title: How Fragile is Relation Extraction under Entity Replacements?
Relation extraction (RE) aims to extract the relations between entity names from the textual context. In principle, textual context determines the ground-truth relation and the RE models should be able to correctly identify the relations reflected by the textual context. However, existing work has found that the RE models memorize the entity name patterns to make RE predictions while ignoring the textual context. This motivates us to raise the question: are RE models robust to the entity replacements? In this work, we operate the random and type-constrained entity replacements over the RE instances in TACRED and evaluate the state-of-the-art RE models under the entity replacements. We observe the 30% - 50% F1 score drops on the state-of-the-art RE models under entity replacements. These results suggest that we need more efforts to develop effective RE models robust to entity replacements. We release the source code at  more » « less
Award ID(s):
Author(s) / Creator(s):
; ; ; ; ; ; ; ;
Publisher / Repository:
Association for Computational Linguistics
Date Published:
Journal Name:
Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)
Page Range / eLocation ID:
414 to 423
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Recent literature focuses on utilizing the entity information in the sentence-level relation extraction (RE), but this risks leaking superficial and spurious clues of relations. As a result, RE still suffers from unintended entity bias, i.e., the spurious correlation between entity mentions (names) and relations. Entity bias can mislead the RE models to extract the relations that do not exist in the text. To combat this issue, some previous work masks the entity mentions to prevent the RE models from over-fitting entity mentions. However, this strategy degrades the RE performance because it loses the semantic information of entities. In this paper, we propose the CoRE (Counterfactual Analysis based Relation Extraction) debiasing method that guides the RE models to focus on the main effects of textual context without losing the entity information. We first construct a causal graph for RE, which models the dependencies between variables in RE models. Then, we propose to conduct counterfactual analysis on our causal graph to distill and mitigate the entity bias, that captures the causal effects of specific entity mentions in each instance. Note that our CoRE method is model-agnostic to debias existing RE systems during inference without changing their training processes. Extensive experimental results demonstrate that our CoRE yields significant gains on both effectiveness and generalization for RE. The source code is provided at: 
    more » « less
  2. null (Ed.)
    Relation Extraction (RE) is one of the fundamental tasks in Information Extraction. The goal of this task is to find the semantic relations between entity mentions in text. It has been shown in many previous work that the structure of the sentences (i.e., dependency trees) can provide important information/features for the RE models. However, the common limitation of the previous work on RE is the reliance on some external parsers to obtain the syntactic trees for the sentence structures. On the one hand, it is not guaranteed that the independent external parsers can offer the optimal sentence structures for RE and the customized structures for RE might help to further improve the performance. On the other hand, the quality of the external parsers might suffer when applied to different domains, thus also affecting the performance of the RE models on such domains. In order to overcome this issue, we introduce a novel method for RE that simultaneously induces the structures and predicts the relations for the input sentences, thus avoiding the external parsers and potentially leading to better sentence structures for RE. Our general strategy to learn the RE-specific structures is to apply two different methods to infer the structures for the input sentences (i.e., two views). We then introduce several mechanisms to encourage the structure and semantic consistencies between these two views so the effective structure and semantic representations for RE can emerge. We perform extensive experiments on the ACE 2005 and SemEval 2010 datasets to demonstrate the advantages of the proposed method, leading to the state-of-the-art performance on such datasets. 
    more » « less
  3. Abstract

    Natural language processing (NLP) techniques can enhance our ability to interpret plant science literature. Many state-of-the-art algorithms for NLP tasks require high-quality labelled data in the target domain, in which entities like genes and proteins, as well as the relationships between entities, are labelled according to a set of annotation guidelines. While there exist such datasets for other domains, these resources need development in the plant sciences. Here, we present the Plant ScIenCe KnowLedgE Graph (PICKLE) corpus, a collection of 250 plant science abstracts annotated with entities and relations, along with its annotation guidelines. The annotation guidelines were refined by iterative rounds of overlapping annotations, in which inter-annotator agreement was leveraged to improve the guidelines. To demonstrate PICKLE’s utility, we evaluated the performance of pretrained models from other domains and trained a new, PICKLE-based model for entity and relation extraction (RE). The PICKLE-trained models exhibit the second-highest in-domain entity performance of all models evaluated, as well as a RE performance that is on par with other models. Additionally, we found that computer science-domain models outperformed models trained on a biomedical corpus (GENIA) in entity extraction, which was unexpected given the intuition that biomedical literature is more similar to PICKLE than computer science. Upon further exploration, we established that the inclusion of new types on which the models were not trained substantially impacts performance. The PICKLE corpus is, therefore, an important contribution to training resources for entity and RE in the plant sciences.

    more » « less
  4. null (Ed.)
    This paper studies the task of Relation Extraction (RE) that aims to identify the semantic relations between two entity mentions in text. In the deep learning models for RE, it has been beneficial to incorporate the syntactic structures from the dependency trees of the input sentences. In such models, the dependency trees are often used to directly structure the network architectures or to obtain the dependency relations between the word pairs to inject the syntactic information into the models via multi-task learning. The major problem with these approaches is the lack of generalization beyond the syntactic structures in the training data or the failure to capture the syntactic importance of the words for RE. In order to overcome these issues, we propose a novel deep learning model for RE that uses the dependency trees to extract the syntax-based importance scores for the words, serving as a tree representation to introduce syntactic information into the models with greater generalization. In particular, we leverage Ordered-Neuron Long-Short Term Memory Networks (ON-LSTM) to infer the model-based importance scores for RE for every word in the sentences that are then regulated to be consistent with the syntax-based scores to enable syntactic information injection. We perform extensive experiments to demonstrate the effectiveness of the proposed method, leading to the state-of-the-art performance on three RE benchmark datasets. 
    more » « less
  5. This work deals with the challenge of learning and reasoning over language and vision data for the related downstream tasks such as visual question answering (VQA) and natural language for visual reasoning (NLVR). We design a novel cross-modality relevance module that is used in an end-to-end framework to learn the relevance representation between components of various input modalities under the supervision of a target task, which is more generalizable to unobserved data compared to merely reshaping the original representation space. In addition to modeling the relevance between the textual entities and visual entities, we model the higher-order relevance between entity relations in the text and object relations in the image. Our proposed approach shows competitive performance on two different language and vision tasks using public benchmarks and improves the state-of-the-art published results. The learned alignments of input spaces and their relevance representations by NLVR task boost the training efficiency of VQA task. 
    more » « less