This paper presents an application of finite state transducers weighted with feature structure descriptions, following Amtrup (2003), to the morphology of the Semitic language Tigrinya. It is shown that feature-structure weights provide an efficient way of handling the templatic morphology that characterizes Semitic verb stems as well as the long-distance dependencies characterizing the complex Tigrinya verb morphotactics. A relatively complete computational implementation of Tigrinya verb morphology is described. 1

We propose WIDL-expressions as a flexible formalism that facilitates the integration of a generic sentence realization system within end-to-end language processing applications. WIDL-expressions represent compactly probability distributions over finite sets of candidate realizations, and have optimal algorithms for realization via interpolation with language model probability distributions. We show the effectiveness of a WIDL-based NLG system in two sentence realization tasks: automatic translation and headline generation. 1

We describe the Cambridge University Engineering Department phrase-based statistical machine translation system for Spanish-English and French-English translation in the ACL 2008 Third Workshop on Statistical Machine Translation Shared Task. The CUED system follows a generative model of translation and is implemented by composition of component models realised as Weighted Finite State Transducers, without the use of a special-purpose decoder. Details of system tuning for both Europarl and News translation tasks are provided.

Abstract—This paper describes the technical and system building advances made in IBM’s speech recognition technology over the course of the Defense Advanced Research Projects Agency (DARPA) Effective Affordable Reusable Speech-to-Text (EARS) program. At a technical level, these advances include the development of a new form of feature-based minimum phone error training (fMPE), the use of large-scale discriminatively trained full-covariance Gaussian models, the use of septaphone acoustic context in static decoding graphs, and improvements in basic decoding algorithms. At a system building level, the advances include a system architecture based on cross-adaptation and the incorporation of 2100 h of training data in every system component. We present results on English conversational telephony test data from the 2003 and 2004 NIST evaluations. The combination of technical advances and an order of magnitude more training data in 2004 reduced the error rate on the 2003 test set by approximately 21 % relative—from 20.4 % to 16.1%—over the most accurate system in the 2003 evaluation and produced the most accurate results on the 2004 test sets in every speed category. Index Terms—Discriminative training, Effective Affordable Reusable Speech-to-Text (EARS), finite-state transducer, full

This paper describes an interpretation and decision strategy that minimizes interpretation errors and perform dialogue actions which may not depend on the hypothesized concepts only, but also on confidence of what has been recognized. The concepts introduced here are applied in a system which integrates language and interpretation models into Stochastic Finite State Transducers (SFST). Furthermore, acoustic, linguistic and semantic confidence measures on the hypothesized word sequences are made available to the dialogue strategy. By evaluating predicates related to these confidence measures, a decision tree automatically learn a decision strategy for rescoring a n-best list of candidates representing a user’s utterance. The different actions that can be then performed are chosen according to the confidence scores given by the tree. 1

In order to simultaneously translate speech into multiple languages an extension of stochastic finite-state transducers is proposed. In this approach the speech translation model consists of a single network where acoustic models (in the input) and the multilingual model (in the output) are embedded. The multi-target model has been evaluated in a practical situation, and the results have been compared with those obtained using several mono-target models. Experimental results show that the multi-target one requires less amount of memory. In addition, a single decoding is enough to get the speech translated into multiple languages. 1