@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.