Title | ||
---|---|---|
TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition |
Abstract | ||
---|---|---|
Training neural models for named entity recognition (NER) in a new domain often requires additional human annotations (e.g., tens of thousands of labeled instances) that are usually expensive and time-consuming to collect. Thus, a crucial research question is how to obtain supervision in a cost-effective way. In this paper, we introduce "entity triggers", an effective proxy of human explanations for facilitating label-efficient learning of NER models. An entity trigger is defined as a group of words in a sentence that helps to explain why humans would recognize an entity in the sentence. We crowd-sourced 14k entity triggers for two well-studied NER datasets. Our proposed model, named Trigger Matching Network, jointly learns trigger representations and soft matching module with self-attention such that can generalize to unseen sentences easily for tagging. Experiments show that the framework is significantly more cost-effective such that using 20% of the trigger-annotated sentences can result in a comparable performance of conventional supervised approaches using 70% training data. We publicly release the collected entity triggers and our code. |
Year | Venue | DocType |
---|---|---|
2020 | ACL | Conference |
Volume | Citations | PageRank |
2020.acl-main | 0 | 0.34 |
References | Authors | |
0 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yu-Chen Lin | 1 | 28 | 11.20 |
Dong-Ho Lee | 2 | 0 | 3.38 |
Shen Ming | 3 | 0 | 0.34 |
Moreno Ryan | 4 | 0 | 0.34 |
Xiao Huang | 5 | 5 | 18.51 |
Prashant Shiralkar | 6 | 79 | 5.94 |
Xiang Ren | 7 | 885 | 60.08 |