Biography
I am currently a final-year PhD candidate advised by Professor
Daniel Gildea in the Computer Science Department at the University of Rochester.
My current research areas are Natural Language Understanding (NLU), Question Answering (QA), Information Extraction (IE) and Machine Translation (MT).
I got my Bachelor's degree from
Northeastern University (China) where I participated in several ACM/ICPC competitions.
After undergraduate study, I started my master degree at the
Institute of Computing Technology, Chinese Academy of Science (ICT,CAS).
I'm very lucky to be advised by Professor Qun Liu, who brings me to this wonderful and exciting area.
During my master program, I laid a solid foundation on Statistical Machine Translation, POS tagging and Parsing.
Here is my Curriculum Vitae, updated on September 17th, 2018.
Recent Event
2018.11 Our paper entitled "Semantic Neural Machine Translation using AMR" has been accepted by Transaction of ACL.
2018.09 One paper has been accepted by INLG 2018 as oral representation.
2018.08 Our paper entitled "N-ary Relation Extraction using Graph State LSTM" has been accepted by EMNLP 2018.
2018.07 I was awarded travel grants from ACL 2018.
2018.04 Three papers has been accepted by ACL 2018, please refer to the publication section for more detail.
2018.02 Part of my 2017 internship work entitled "Leveraging Context Information for Natural Question Generation" has been accepted by NAACL 2018.
2017.10 I gave seminar talks entitled "A unified query-based generative model for question generation and question answering" at ICT/CAS and at the Big Picture Seminar of URCS.
2017.07 I was awarded travel grants from EMNLP 2016 and ACL 2017.
2017.03 Our paper entitled "AMR-to-text Generation with Synchronous Node Replacement Grammar" has been accepted by ACL 2017 as oral representation.
2016.09 Our paper entitled "AMR-to-text generation as a Traveling Salesman Problem" has been accepted by EMNLP 2016.
Publication
Can also be found in Google Scholar via here, and our released codes can be found in my Github.
2019
- Tackling Graphical NLP problems with Graph Recurrent Networks.
Linfeng Song.
PhD Thesis Paper.
- SemBleu: A Robust Metric for AMR Parsing Evaluation.
Linfeng Song and Daniel Gildea.
In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL-19).
- Semantic Neural Machine Translation using AMR.
Linfeng Song, Daniel Gildea, Yue Zhang, Zhiguo Wang and Jinsong Su.
In Transaction of ACL (TACL) 2019.
2018
- Exploring Graph-structured Passage Representation
for Multi-hop Reading Comprehension with Graph Neural Networks.
Linfeng Song, Zhiguo Wang, Mo Yu, Yue Zhang, Radu Florian and Daniel Gildea.
In arXiv preprint arXiv:1809.02040.
- Neural Transition-based Syntactic Linearization.
Linfeng Song, Yue Zhang and Daniel Gildea.
In Proceedings of the 2018 Conference on Natural Language Generation (INLG-18).
Oral acceptance rate is 19.6%. Work was done in the spring of 2017.
- N-ary Relation Extraction using Graph State LSTM.
Linfeng Song, Yue Zhang, Zhiguo Wang and Daniel Gildea.
In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP-18).
- A Graph-to-Sequence Model for AMR-to-Text Generation.
Linfeng Song, Yue Zhang, Zhiguo Wang and Daniel Gildea.
In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL-18).
- Sentence-State LSTM for Text Representation.
Yue Zhang, Qi Liu and Linfeng Song.
In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL-18).
- Sequence-to-sequence Models for Cache Transition Systems.
Xiaochang Peng, Linfeng Song, Daniel Gildea and Giorgio Satta.
In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL-18).
- Leveraging Context Information for Natural Question Generation.
Linfeng Song, Zhiguo Wang, Wael Hamza, Yue Zhang and Daniel Gildea.
In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-18).
2017
- A Unified Query-based Generative Model for Question Generation and Question Answering.
Linfeng Song, Zhiguo Wang and Wael Hamza.
In arXiv preprint arXiv:1709.01058.
- k-Nearest Neighbor Augmented Neural Networks for Text Classification.
Zhiguo Wang, Wael Hamza and Linfeng Song.
In arXiv preprint arXiv:1708.07863.
- AMR-to-text Generation with Synchronous Node Replacement Grammar.
Linfeng Song, Xiaochang Peng, Yue Zhang, Zhiguo Wang and Daniel Gildea.
In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL-17).
2016
- Word Embedding, Sense Embedding and their Application to Word Sense Induction.
Linfeng Song.
Area Paper. slides
- AMR-to-text generation as a Traveling Salesman Problem.
Linfeng Song, Yue Zhang, Xiaochang Peng, Zhiguo Wang and Daniel Gildea.
In Proceeddings of EMNLP 2016. Austin, Texas, USA.
- Sense Embedding for Word Sense Induction.
Linfeng Song, Zhiguo Wang, Haitao Mi and Daniel Gildea.
In Proceedings of *SEM (ACL Workshop) 2016, Berlin, Germany.
2015
- A Synchronous Hyperedge Replacement Grammar based approach for AMR parsing.
Xiaochang Peng, Linfeng Song and Daniel Gildea.
In Proceedings of CoNLL 2015, Beijing, China.
2014 and before
- Joint Morphological Generation and Syntactic Linearization.
Linfeng Song, Yue Zhang, Kai Song and Qun Liu.
In Proceedings of AAAI 2014, Quebec City, Canada.
- Syntactic SMT Using a Discriminative Text Generation Model.
Yue Zhang, Kai Song, Linfeng Song, Jingbo Zhu and Qun Liu.
In Proceedings of EMNLP 2014, Doha, Qatar.
- Translation with Source Constituency and Dependency Trees.
Fandong Meng, Jun Xie, Linfeng Song, Yajuan Lv and Qun Liu.
In Proceedings of EMNLP 2013, Seattle, America.
- Bagging-based System Combination for Domain Adaptation.
Linfeng Song, Haitao Mi, Yajuan Lv and Qun Liu.
In Proceedings of MT-Summit XIII, Xiamen, China.
Professional Service
- Program Committee of ACL (2019), AAAI (2019), IJCAI (2013)
- Reviewer of EMNLP (2014--2018), NAACL (2015, 2018--2019), Coling (2018 outstanding reviewer), EACL (2017)
- Reviewer of journals: TASLP (2016), TALLIP (2019)
- Reviewer of other revenues: WMT (2013--2016, 2018), *SEM (2019), S$^2$MT (2015), EAMT (2017), CWMT (2018)
Internships
-
IBM Thomas J. Watson Research Center, summer of 2018, worked with
Zhiguo Wang,
Mo Yu and
Radu Florian
-
IBM Thomas J. Watson Research Center, summer of 2017, worked with
Zhiguo Wang and
Wael Hamza
-
Bosch American Research Center, summer of 2016, worked with
Lin Zhao
-
IBM Thomas J. Watson Research Center, summer of 2015, worked with
Zhiguo Wang,
Haitao Mi
and Abe Ittycheriah
Teaching Assistants
2017 Fall
CSC 248/448 Statistical Speech and Language Processing Instructor: Daniel Gildea
Office hours: Tu/Th 10am-11am, 2403 Wegmans Hall
2017 Spring
CSC 246/446 Machine Learning Instructor: Daniel Gildea
Office hours: M/W 10:30am-11:30am, CSB 631
2016 Fall
CSC 262/462 COMPUTATIONAL INTRO TO STATISTICS Instructor: ANTHONY ALMUDEVAR
Office hours: W/Th 10:30am-11:30am, CSB 631
2016 Spring
CSC 246/446 Machine Learning Instructor: Daniel Gildea
Office hours: Tu/Th 10:30am-11:30am, CSB 631
Courses
2016 Spring
CSC 280 Computer Models and Limitations Instructor: Muthu Venkitasubramaniam
CSC 455 Software Analysis and Improvement Instructor: Ding Chen
2015 Fall
CSC 448 Statistical Speech and Language Processing Instructor: Daniel Gildea
CSC 453 Dynamic Languages and Software Development Instructor: Ding Chen
CSC 576 Big Data Analytics Instructor: Ji Liu
2015 Spring
CSC 446 Machine Learning Instructor: Daniel Gildea
CSC 484 Advanced Algorithm Instructor: Daniel Stefankovic
2014 Fall
CSC 577 Convex Optimization Instructor: Daniel Gildea
CSC 456 Operating System Instructor: John Criswell
CSC 486 Computational Complexity Instructor: Joel Seiferas
CSC 400 Problem Seminar Instructor: Randal C. Nelson
|