81 |
Post-specialisation: Retrofitting vectors of words unseen in lexical resources
|
|
|
|
BASE
|
|
Show details
|
|
82 |
Discriminating between lexico-semantic relations with the specialization tensor model
|
|
|
|
BASE
|
|
Show details
|
|
83 |
Adversarial propagation and zero-shot cross-lingual transfer of word vector specialization
|
|
|
|
BASE
|
|
Show details
|
|
85 |
A resource-light method for cross-lingual semantic textual similarity
|
|
|
|
BASE
|
|
Show details
|
|
90 |
University of Mannheim @ CLSciSumm-17: Citation-Based Summarization of Scientific Articles Using Semantic Textual Similarity
|
|
|
|
BASE
|
|
Show details
|
|
92 |
Improving neural knowledge base completion with cross-lingual projections
|
|
|
|
BASE
|
|
Show details
|
|
93 |
Leveraging event-based semantics for automated text simplification
|
|
|
|
Abstract:
Automated Text Simplification (ATS) aims to transform complex texts into their simpler variants which are easier to understand to wider audiences and easier to process with natural language processing (NLP) tools. While simplification can be applied on lexical, syntactic, and discourse level, all previously proposed ATS systems only operated on the first two levels, thus failing at simplifying texts on the discourse level. We present a semantically-motivated ATS system which is the first system that is applied on the discourse level. By exploiting the state-of-the-art event extraction system, it is the first ATS system able to eliminate large portions of irrelevant information from texts, by maintaining only those parts of the original text that belong to factual event mentions. A few handcrafted rules ensure that the output of the system is syntactically simple, by placing each factual event mention in a separate short sentence, while the state-of-the-art unsupervised lexical simplification module, based on using word embeddings, replaces complex and infrequent words with their simpler variants. We perform a thorough evaluation, both automatic and manual, showing that our system produces more readable and simpler texts than the state-of-the-art ATS systems. Our newly proposed post-editing evaluation further reveals that our system requires less human effort for correcting grammaticality and meaning preservation on news articles than the state-of-the-art ATS system.
|
|
Keyword:
004 Informatik
|
|
URL: https://doi.org/10.1016/j.eswa.2017.04.005 https://madoc.bib.uni-mannheim.de/42829/ http://www.sciencedirect.com/science/article/pii/S0957417417302385
|
|
BASE
|
|
Hide details
|
|
94 |
Two layers of annotation for representing event mentions in news stories
|
|
|
|
BASE
|
|
Show details
|
|
95 |
If sentences could see: Investigating visual information for semantic textual similarity
|
|
|
|
BASE
|
|
Show details
|
|
96 |
Dual tensor model for detecting asymmetric lexico-semantic relations
|
|
|
|
BASE
|
|
Show details
|
|
98 |
Unsupervised text segmentation using semantic relatedness graphs
|
|
|
|
BASE
|
|
Show details
|
|
99 |
Spanish NER with word representations and conditional random fields
|
|
|
|
BASE
|
|
Show details
|
|
|
|