Sciweavers

ACL
2015
8 years 23 days ago
Transition-Based Dependency Parsing with Stack Long Short-Term Memory
We propose a technique for learning representations of parser states in transitionbased dependency parsers. Our primary innovation is a new control structure for sequence-to-seque...
Chris Dyer, Miguel Ballesteros, Wang Ling, Austin ...
ACL
2015
8 years 23 days ago
Low Resource Dependency Parsing: Cross-lingual Parameter Sharing in a Neural Network Parser
Training a high-accuracy dependency parser requires a large treebank. However, these are costly and time-consuming to build. We propose a learning method that needs less data, bas...
Long Duong, Trevor Cohn, Steven Bird, Paul Cook
ACL
2015
8 years 23 days ago
The Impact of Listener Gaze on Predicting Reference Resolution
We investigate the impact of listener’s gaze on predicting reference resolution in situated interactions. We extend an existing model that predicts to which entity in the enviro...
Nikolina Koleva, Martin Villalba, Maria Staudte, A...
ACL
2015
8 years 23 days ago
Semantic Role Labeling Improves Incremental Parsing
Incremental parsing is the task of assigning a syntactic structure to an input sentence as it unfolds word by word. Incremental parsing is more difficult than fullsentence parsin...
Ioannis Konstas, Frank Keller
ACL
2015
8 years 23 days ago
Towards Debugging Sentiment Lexicons
Central to many sentiment analysis tasks are sentiment lexicons (SLs). SLs exhibit polarity inconsistencies. Previous work studied the problem of checking the consistency of an SL...
Andrew Schneider, Eduard C. Dragut
ACL
2015
8 years 23 days ago
IWNLP: Inverse Wiktionary for Natural Language Processing
Nowadays, there are a lot of natural language processing pipelines that are based on training data created by a few experts. This paper examines how the proliferation of the inter...
Matthias Liebeck, Stefan Conrad 0001
ACL
2015
8 years 23 days ago
KB-LDA: Jointly Learning a Knowledge Base of Hierarchy, Relations, and Facts
Many existing knowledge bases (KBs), including Freebase, Yago, and NELL, rely on a fixed ontology, given as an input to the system, which defines the data to be cataloged in the...
Dana Movshovitz-Attias, William W. Cohen
ACL
2015
8 years 23 days ago
Non-distributional Word Vector Representations
Data-driven representation learning for words is a technique of central importance in NLP. While indisputably useful as a source of features in downstream tasks, such vectors tend...
Manaal Faruqui, Chris Dyer
ACL
2015
8 years 23 days ago
Learning Representations for Text-level Discourse Parsing
In the proposed doctoral work we will design an end-to-end approach for the challenging NLP task of text-level discourse parsing. Instead of depending on mostly hand-engineered sp...
Gregor Weiss
ACL
2015
8 years 23 days ago
Learning Lexical Embeddings with Syntactic and Lexicographic Knowledge
We propose two improvements on lexical association used in embedding learning: factorizing individual dependency relations and using lexicographic knowledge from monolingual dicti...
Tong Wang, Abdelrahman Mohamed, Graeme Hirst