Lisheng Fu


pdf bib
Distantly Supervised Attribute Detection from Reviews
Lisheng Fu | Pablo Barrio
Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text

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. We then use review-level attention to pay more attention to those reviews related to the attributes. The experimental results show that our attention-based model predicts attributes for places from reviews with over 98% accuracy. The attention weights assigned to each review provide explanation of capturing relevant reviews.

pdf bib
A Case Study on Learning a Unified Encoder of Relations
Lisheng Fu | Bonan Min | Thien Huu Nguyen | Ralph Grishman
Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text

Typical relation extraction models are trained on a single corpus annotated with a pre-defined relation schema. An individual corpus is often small, and the models may often be biased or overfitted to the corpus. We hypothesize that we can learn a better representation by combining multiple relation datasets. We attempt to use a shared encoder to learn the unified feature representation and to augment it with regularization by adversarial training. The additional corpora feeding the encoder can help to learn a better feature representation layer even though the relation schemas are different. We use ACE05 and ERE datasets as our case study for experiments. The multi-task model obtains significant improvement on both datasets.


pdf bib
Domain Adaptation for Relation Extraction with Domain Adversarial Neural Network
Lisheng Fu | Thien Huu Nguyen | Bonan Min | Ralph Grishman
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

Relations are expressed in many domains such as newswire, weblogs and phone conversations. Trained on a source domain, a relation extractor’s performance degrades when applied to target domains other than the source. A common yet labor-intensive method for domain adaptation is to construct a target-domain-specific labeled dataset for adapting the extractor. In response, we present an unsupervised domain adaptation method which only requires labels from the source domain. Our method is a joint model consisting of a CNN-based relation classifier and a domain-adversarial classifier. The two components are optimized jointly to learn a domain-independent representation for prediction on the target domain. Our model outperforms the state-of-the-art on all three test domains of ACE 2005.


pdf bib
A Two-stage Approach for Extending Event Detection to New Types via Neural Networks
Thien Huu Nguyen | Lisheng Fu | Kyunghyun Cho | Ralph Grishman
Proceedings of the 1st Workshop on Representation Learning for NLP


pdf bib
An Efficient Active Learning Framework for New Relation Types
Lisheng Fu | Ralph Grishman
Proceedings of the Sixth International Joint Conference on Natural Language Processing