1 |
Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge
|
|
|
|
In: arXiv (2019)
|
|
BASE
|
|
Show details
|
|
2 |
Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning
|
|
|
|
In: Narasimhan (2016)
|
|
BASE
|
|
Show details
|
|
3 |
Language Understanding for Text-based Games using Deep Reinforcement Learning
|
|
|
|
In: Narasimhan (2015)
|
|
Abstract:
In this paper, we consider the task of learning control policies for text-based games. In these games, all interactions in the virtual world are through text and the underlying state is not observed. The resulting language barrier makes such environments challenging for automatic game players. We employ a deep reinforcement learning framework to jointly learn state representations and action policies using game rewards as feedback. This framework enables us to map text descriptions into vector representations that capture the semantics of the game states. We evaluate our approach on two game worlds, comparing against baselines using bag-of-words and bag-of-bigrams for state representations. Our algorithm outperforms the baselines on both worlds demonstrating the importance of learning expressive representations. ; Leventhal Fellowship ; MIT Center for Brains, Minds and Machines
|
|
URL: http://hdl.handle.net/1721.1/98900
|
|
BASE
|
|
Hide details
|
|
4 |
Morphological segmentation : an unsupervised method and application to Keyword Spotting ; Unsupervised method and application to KWS
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Morphological Segmentation for Keyword Spotting
|
|
|
|
In: MIT web domain (2014)
|
|
BASE
|
|
Show details
|
|
6 |
An unsupervised method for uncovering morphological chains
|
|
|
|
In: Association for Computational Linguistics (2014)
|
|
BASE
|
|
Show details
|
|
|
|