InProceedings{chang-EtAl:2019:Long,
  author    = {Chang, Ming-Wei and Toutanova, Kristina and Lee, Kenton and Devlin, Jacob},
  title     = {Language Model Pre-training for Hierarchical Document Representations},
  booktitle = {arxiv},
  month     = {Jan},
  year      = {2019},
  url       = {https://arxiv.org/abs/1901.09128}
}
 

 InProceedings{ji-EtAl:2017:Long,
  author    = {Ji, Jianshu  and  Wang, Qinlong  and  Toutanova, Kristina  and  Gong, Yongen  and  Truong, Steven  and  Gao, Jianfeng},
  title     = {A Nested Attention Neural Hybrid Model for Grammatical Error Correction},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month     = {July},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {753--762},
  url       = {http://aclweb.org/anthology/P17-1070}
}
 

Grammatical error correction (GEC) systems strive to correct both global errors
inword order and usage, and local errors inspelling and inflection. Further
developing upon recent work on neural machine translation, we propose a new
hybrid neural model with nested attention layers for GEC.Experiments show that
the new model can effectively correct errors of both types by incorporating
word and character-level information, and that the model significantly
outperforms previous  neural models for GEC as measured on the standard
CoNLL-14 benchmark dataset.Further analysis also shows that the superiority of
the proposed model can be largely attributed to the use of the nested attention
mechanism, which has proven particularly effective incorrecting local errors
that involve small edits in orthography.
 

 InProceedings{poon-EtAl:2017:Tutorials,
  author    = {Poon, Hoifung  and  Quirk, Chris  and  Toutanova, Kristina  and  Yih, Wen-tau},
  title     = {NLP for Precision Medicine},
  booktitle = {Proceedings of ACL 2017, Tutorial Abstracts},
  month     = {July},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {1--2},
  url       = {http://aclweb.org/anthology/P17-5001}
}
 

article{TACL1028,
	author = {Peng, Nanyun  and Poon, Hoifung  and Quirk, Chris  and Toutanova, Kristina  and Yih, Wen-tau },
	title = {Cross-Sentence N-ary Relation Extraction with Graph LSTMs},
	journal = {Transactions of the Association for Computational Linguistics},
	volume = {5},
	year = {2017},
	issn = {2307-387X},
	url = {https://transacl.org/ojs/index.php/tacl/article/view/1028},
	pages = {101--115}
}
 

Past work in relation extraction focuses on binary relations in single sentences. Recent NLP inroads in high-valued domains
have kindled strong interest in the more general setting of extracting n-ary relations that span multiple sentences. In this paper, 
we explore a general relation extraction framework based on graph long short-term memory (graph LSTM), which can be easily extended
to cross-sentence n-ary relation extraction. The graph formulation provides a unifying way to explore different LSTM approaches and
incorporate various intra-sentential and inter-sentential dependencies, such as sequential, syntactic, and discourse relations. 
A robust contextual representation is learned for the entities, which serves as input to the relation classifier, making it easy for scaling
to arbitrary relation arity n, as well as for multi-task learning with related relations. We evaluated this framework in two important domains
in precision medicine and demonstrated its effectiveness with both supervised learning and distant supervision. Cross-sentence extraction produced
far more knowledge, and multi-task learning significantly improved extraction accuracy. A thorough analysis comparing various LSTM approaches yielded
interesting insight on how linguistic analysis impacts the performance.
  

@InProceedings{toutanova-EtAl:2016:EMNLP2016,
  author    = {Toutanova, Kristina  and  Brockett, Chris  and  Tran, Ke M.  and  Amershi, Saleema},
  title     = {A Dataset and Evaluation Metrics for Abstractive Compression of Sentences and Short Paragraphs},
  booktitle = {Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing},
  month     = {November},
  year      = {2016},
  address   = {Austin, Texas},
  publisher = {Association for Computational Linguistics},
  pages     = {340--350},
  url       = {https://aclweb.org/anthology/D16-1033}
}
 

  We introduce a manually-created, multi-reference dataset for abstractive sentence and short paragraph compression. First, we examine
  the impact of single- and multi-sentence level editing operations on human compression quality as found in this corpus. We observe that
  substitution and rephrasing operations are more meaning preserving than other operations, and that compressing in context improves quality. 
  Second, we systematically explore the correlations between automatic evaluation metrics and human judgments of meaning preservation
  and grammaticality in the compression task, and analyze the impact of the linguistic units used and precision versus recall measures on
  the quality of the metrics. Multi-reference evaluation metrics are shown to offer significant advantage over single reference-based metrics.
  

 @InProceedings{toutanova-EtAl:2016:P16-1,
  author    = {Toutanova, Kristina  and  Lin, Victoria  and  Yih, Wen-tau  and  Poon, Hoifung  and  Quirk, Chris},
  title     = {Compositional Learning of Embeddings for Relation Paths in Knowledge Base and Text},
  booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month     = {August},
  year      = {2016},
  address   = {Berlin, Germany},
  publisher = {Association for Computational Linguistics},
  pages     = {1434--1444},
  url       = {http://www.aclweb.org/anthology/P16-1136}
}
 

Modeling relation paths has offered significant gains in embedding models for knowledge base (KB) completion. However,
enumerating paths between two entities is very expensive, and existing approaches typically resort to approximation
with a sampled subset. This problem is particularly acute when text is jointly modeled with KB relations and used to
provide direct evidence for facts mentioned in it. In this paper, we propose the first exact dynamic programming algorithm
which enables efficient incorporation of all relation paths of bounded length, while modeling both relation types
and intermediate nodes in the compositional path representations. We conduct a theoretical analysis of the efficiency gain
from the approach. Experiments on two datasets show that it addresses representational limitations in prior approaches and
improves accuracy in KB completion.