Weighted Finite-State Transducer Algorithms. An Overview

By Mehryar Mohri. 2004

95 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Molecular Biology, Algorithms & Complexity

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Felix Stahlberg
2. Ankur Bapna
3. Yu Zhang
4. Bill Byrne
5. Alexis Conneau
6. Jason Riesa
7. Vera Axelrod
8. Simran Khanuja

In Computational Theory and Mathematics

1. Yu Zhang
2. Eva Hasler
3. Bill Byrne
4. Felix Stahlberg

In Molecular Biology

1. Yu Zhang
2. Alexis Conneau
3. Eva Hasler
4. Bill Byrne
5. Felix Stahlberg

In Algorithms & Complexity

1. Eva Hasler
2. Bill Byrne
3. Felix Stahlberg

Citations in the corpus

• FLEURS: FEW-Shot Learning Evaluation of Universal Representations of Speech (2022, background): “We apply NFC (https://en. wikipedia.org/wiki/Unicode_equivalence# Normalization) and then FST [25] normalization to each sentence, lower-case, normalize and remove punctuations.”
• The Edit Distance Transducer in Action: The University of Cambridge English-German System at WMT16 (2016, methodology): “The composition of two weighted transducers T 1 , T 2 (denoted as T 1 ◦ T 2 ) over a semiring ( K , ⊕ , ⊗ ) is defined following (Mohri, 2004) We will make extensive use of this operation as tool for building complex automata which make use of both the NMT and Hiero translation lattices.”