Exposing Shallow Heuristics of Relation Extraction Models with Challenge Data

By Shachar Rosenman, Alon Jacovi, Yoav Goldberg. 2020

30 citations recorded by the source corpus.

The process of collecting and annotating training data may introduce distribution artifacts which may limit the ability of models to learn correct generalization behavior. We identify failure modes of SOTA relation extraction (RE) models trained on TACRED, which we attribute to limitations in the data annotation process. We collect and annotate a challenge-set we call Challenging RE (CRE), based on naturally occurring corpus examples, to benchmark this behavior. Our experiments with four state-of-the-art RE models show that they have indeed adopted shallow heuristics that do not generalize to the challenge-set data. Further, we find that alternative question answering modeling performs significantly better than the SOTA models on the challenge-set, despite worse overall TACRED performance. By adding some of the challenge data as training examples, the performance of the model improves. Finally, we provide concrete suggestion on how to improve RE data collection to alleviate this behavior.

Subfields: Artificial Intelligence, Evaluation & Benchmarks, Information Extraction

Citations in the corpus

• Are NLP Models really able to Solve Simple Math Word Problems? (2021, neutral): “A wide variety of methods and datasets have been proposed to solve MWPs; e.g. statistical machine learning (Roy and Roth, 2018), semantic parsing (Huang et al., 2017) and most recently deep learning (Wang et al., 2017; Xie and Sun, 2019; Zhang et al., 2020); see (Zhang et al., 2020) for an…”