Zhengzhong Liu

Zhengzhong Liu

Hector is a researcher in Natural Language Processing and Computational Linguistics

Publications

You can also find my articles on my Google Scholar profile.

Graph-Based Decoding for Event Sequencing and Coreference Resolution

Published in 7th International Conference on Computational Linguistics(COLING 2018), 2018

We study two types of relation: Event Coreference and Event Sequencing. We show that the popular tree-like decoding structure for automated Event Coreference is not suitable for Event Sequencing. To this end, we propose a graph-based decoding algorithm that is applicable to both tasks.

Download here

JointSem: Combining Query Entity Linking and Entity based Document Ranking

Published in Proceedings of the 26th ACM International Conference on Information and Knowledge Management (CIKM 2017), 2017

This work presents JointSem, a joint semantic ranking system that combines query entity linking and entity-based document ranking. In JointSem, the spooing and linking signals are used to describe the importance of candidate entities in the query, and the linked entities are utilized to provide additional ranking features for the documents.

Download here

De-duping URLs with Sequence-to-Sequence Neural Networks

Published in SIGIR 2017 Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2017

Traditional de-duping methods are usually limited to heavily engineered rule matching strategies. In this work, we propose a novel URL de-duping framework based on sequence-to-sequence (Seq2Seq) neural networks. A

Download here

Harnessing Deep Neural Networks with Logic Rules

Published in Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2016

We propose a general framework capable of enhancing various types of neural networks (e.g., CNNs and RNNs) with declarative first-order logic rules.

Download here

Exploring the steps of Verb Phrase Ellipsis

Published in Proceedings of the Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2016), co-located with NAACL 2016, 2016

Verb Phrase Ellipsis is a well-studied topic in theoretical linguistics but has received little attention as a computational problem. Here we propose a decomposition of the overall resolution problem into three tasks: target detection, antecedent head resolution, and antecedent boundary detection and implement a number of computational approaches for each one.

Download here

Evaluation Algorithms for Event Nugget Detection : A Pilot Study

Published in Proceedings of the 3rd Workshop on EVENTS at the NAACL-HLT, 2015

We analyze the problems of evaluating multiple event mention attributes and discontinuous event mention spans. In addition, we identify a few limitations in the evaluation algorithm used for the pilot task and propose some potential improvements.

Download here

Detecting Subevent Structure for Event Coreference Resolution

Published in LREC 2014, 2014

In the task of event coreference resolution, recent work has shown the need to perform not only full coreference but also partial coreference of events. We show that subevents can form a particular hierarchical event structure. This paper examines a novel two-stage approach to finding and improving subevent structures.

Download here