FAQ

Mehryar Mohri

Mehryar Mohri is a professor of computer science at the Courant Institute of Mathematical Sciences at New York University known for his work in… (More)
Wikipedia

Topic mentions per year

Topic mentions per year

1996-2017
024619962017

Related topics

Related topics

10 relations
Automata theoryComputational biologyComputer scienceJournal of Automata, Languages and Combinatorics
(More)

Related mentions per year

Related mentions per year

1936-2018
19401960198020002020
Mehryar Mohri
Machine learning
Computer science
Speech recognition
Automata theory
Natural language processing

Papers overview

Semantic Scholar uses AI to extract papers important to this topic.
2010
2010
Efficient Inference through Cascades of Weighted Tree Transducers
Weighted tree transducers have been proposed as useful formal models for representing syntactic natural language processing… (More)
  • figure 1
  • table 1
  • figure 2
  • table 2
  • table 3
Is this relevant?
2009
2009
Strongly Regular Grammars and Regular Approximation of Context-Free Languages
We consider algorithms for approximating context–free grammars by regular grammars, making use of Chomsky’s characterization of… (More)
  • figure 1
  • figure 2
  • figure 3
Is this relevant?
2008
2008
A Burnside Approach to the Termination of Mohri's Algorithm for Polynomially Ambiguous Min-Plus-Automata
We show that the termination of Mohri’s algorithm is decidable for polynomially ambiguous weighted finite automata over the… (More)
Is this relevant?
2006
2006
Sparse solutions for linear prediction problems
Simplicity is the ultimate sophistication. -Leonardo da Vinci The simplicity of an idea has long been regarded as a sign of… (More)
  • figure 7.1
  • figure 7.2
  • figure 7.3
  • figure 7.4
  • figure 8.1
Is this relevant?
2005
2005
Margin-Based Ranking Meets Boosting in the Middle
We present a margin-based bound for ranking in a general setting, using the L∞ covering number of the hypothesis space as our… (More)
Is this relevant?
Highly Cited
2002
Highly Cited
2002
Parameter Estimation for Probabilistic Finite-State Transducers
Weighted finite-state transducers suffer from the lack of a training algorithm. Training is even harder for transducers that have… (More)
  • figure 1
  • figure 2
Is this relevant?
1999
1999
Network optimizations for large-vocabulary speech recognition
The redundancy and the size of networks in large-vocabulary speech recognition systems can have a critical e€ect on their overall… (More)
  • figure 2
  • figure 1
  • figure 4
  • figure 3
  • figure 5
Is this relevant?
1999
1999
Transducers from Rewrite Rules with Backreferences
Context sensitive rewrite rules have been widely used in several areas of natural language processing, including syntax… (More)
  • table 1
Is this relevant?
1996
1996
An E cient Compiler for Weighted Rewrite Rules
Context-dependent rewrite rules are used in many areas of natural language and speech processing. Work in computational phonology… (More)
Is this relevant?
Review
1996
Review
1996
An Efficient Compiler for Weighted Rewrite Rules
Context-dependent rewrite rules are used in many areas of natural language and speech processing. Work in computational phonology… (More)
Is this relevant?