1 code implementation • EACL 2021 • Lisheng Fu, Ralph Grishman
We propose to use prototypical examples to represent each relation type and use these examples to augment related types from a different dataset.
no code implementations • WS 2018 • Lisheng Fu, Bonan Min, Thien Huu Nguyen, Ralph Grishman
Typical relation extraction models are trained on a single corpus annotated with a pre-defined relation schema.
no code implementations • WS 2018 • Lisheng Fu, Pablo Barrio
This work aims to detect specific attributes of a place (e. g., if it has a romantic atmosphere, or if it offers outdoor seating) from its user reviews via distant supervision: without direct annotation of the review text, we use the crowdsourced attribute labels of the place as labels of the review text.
no code implementations • IJCNLP 2017 • Lisheng Fu, Thien Huu Nguyen, Bonan Min, Ralph Grishman
Our method is a joint model consisting of a CNN-based relation classifier and a domain-adversarial classifier.