... cas-
caded finite- state parser (Abney, 1997).
For the tagging approach, the effects of
choosing different representations of de-
pendency tuples are investigated. Per-
formance of the finite- state ... representations by distinguishing lower
bound performance (random choice of a parse)
ADJ
165
A Cascaded Finite- State Parser for German
Michael Schiehlen
Institute for Computational Linguistics, University ... (10,400 tokens) which was not
annotated independently.
5 Conclusion
The paper presents a cascaded finite- state parser
incorporating some degree of underspecification.
The idea is that such syntactically...
...
Roche, E. 1996. Parsing with Finite- State Trans-
ducers, http://www.merl-com/reports/TR96-
30. Visited 12/03/99.
Roche, E. and Schabes, Y., editors, 1997. Finite-
State Language Processing, ...
The regular expressions
are translated into
finite- state automata,
and the
union of the automata yields a single, determin-
istic, finite- state, level recognizer, (Abney, 1996).
Moreover, ...
tions of the models presented. It seems to us
that Swedish language researchers are satisfied
with the description and, apparently, the imple-
mentation on a small scale of finite- state meth-...
... rescoring models that depend on sequential con-
text include distance-based reordering models or Markov fea-
tures in tagging models.
ing models need not be explicitly represented as
FSTs—the state ... language
words. For SCFG models and sequential tag-
ging models, a node also corresponds to a source
span and non-terminal type, but for word-based
and phrase-based models, the relationship to ... been
generated, any non-coaccessible states (i.e., states
that are not reachable from the goal node) are re-
moved and the resulting structure is rescored with
language models using a user-specified intersec-
tion/pruning...
... observations that finite state machines
might accurately account for psycholinguistic re-
sults to some degree. The current study provides
more concrete answers to what finite state machine
is relevant ... our
study that it is worthwhile, for the sake of clarity
and explicit testability, to consider models that are
simpler and more precisely specified than those
assumed by dominant theories of human ... garden-path
52
Acknowledgments
This project was supported by the Cognitive Sci-
ence Summer 2004 Research Award at the Ohio
State University. We acknowledge support from
NSF grant IIS 0347799.
References
S. Bangalore and...
... (Brown et al., 1993), three alignment models
are described that include fertility models, these
are IBM Models 3, 4, and 5. The fertility-based
alignment models have a more complicated struc-
ture ... engine.
In this paper, we study the incorporation
of MT models and ASR models using
finite -state automata. We also propose
some transducers based on MT models for
rescoring the ASR word graphs.
1 Introduction
A ... (MT) models are employed to take into
account the source text for increasing the accuracy
of automatic speech recognition (ASR) models.
Related Work
The idea of incorporating ASR and MT models
was...
... Markov models with finite state
supervision. In A. Kornai, ed., Extended Finite State
Models of Language. Cambridge University Press.
Emmanuel Roche and Yves Schabes, editors. 1997.
Finite- State ... Probabilistic Finite- State Transducers
∗
Jason Eisner
Department of Computer Science
Johns Hopkins University
Baltimore, MD, USA 21218-2691
jason@cs.jhu.edu
Abstract
Weighted finite -state transducers ... noisy-channel
decoding,
1
including classic models for speech
recognition (Pereira and Riley, 1997) and machine
translation (Knight and Al-Onaizan, 1998). More-
over, once the models are expressed in the finite-
state framework,...
... ed-
it distance from state 0 to state j, and the cost(i,j) is
the cost of insertion, deletion or substitution from s-
tate j to state i. The equation means the minED of
state i can be computed ... of
state i can be computed by the accumulated minED-
cost of state j in the phase p. The state j belongs to
the have-been-calculated state set {X
0
,. . . ,X
p−1
} in
phase p. In phrase p, we compute ... transcription for all the to-
be-calculated states which is the X
p
shown in Fig-
ure 4. After computing all the phrases, the best path
and its edit distances of the end states are obtained.
Then the final...
... awra.
As the figure depicts, 0 is the start state and 4 is
the final state. Each transition is a 4-tuple <c, n,
i, o> where c is current state, n is the next state,
i is the input symbol and o is ... FST transition table
do
3: if next state is a final state then
4: for all rules where I is the last character
of first word do
5: S = next state from the start state on
encountering X;
6: Y = first ... concatena-
tion. In such cases, if the input string is not ex-
hausted, but the current state is a final state, we go
back to the start state with the remaining string as
the input.
88
5.1.1 Results
The performance...
...
quence of a start state, reading states, a crossover
state, prefinal states, and a final state. The excep-
tion to this is a path accepting the empty string,
which has a start state, possibly ...
reading
states), states with e-transitions
entering and leaving them
(prefinal
states), and
states with terminal transitions entering them and
e-transitions leaving them (cr0ssover states). ... sequence of G-transitions leading to the final
state [$' * S.]. Hence ~" has the following kinds of
states: the start state, the final state, states with
terminal transitions entering...
... q0, R) where (1) Q is a finite set of
states,
(2) ~ is an
input ranked alphabet,
(3) A is
an
output alphabet,
(4) q0 E Q is the
initial state,
and (5) R is a finite set of
rules
of ... 1969) takes a tree
as an input, starts from the initial state with its
head scanning the root node of an input. Ac-
cording to the current state and the label of the
scanned node, it transforms ... of the
scanned node, it transforms an input tree into
an output tree in a top-down way. A
finite state
translation system (fts)
is a tree transducer with
its input domain being the set of...
... have chosen to represent rules as
subse-
quential finitestate transducers.
Subsequential finite
state transducers are a subtype of finitestate transduc-
ers with the following properties: ... destination state
After the process of merging states terminates, a deci-
sion tree is induced at each state to classify the outgoing
arcs. Figure 9 shows a tree induced at the initial state of ... Destination State: 0
2: Output: [ ], Destination State: 1
prim-stress
ix+
1 2
On end of string: Output: nil, Destination State: 0
Figure 9: Decision Tree Before Pruning: The initial state
of...
... languages can be
assigned to them by finite- state parsers that op-
erate by identifying constituents as quickly as
possible. We call this the
Efficient Finite-
State Parser Hypothesis.
The four ... the affixed
strings associated with the expressions of L2 can
still be assigned to them by a finite- state parser.
The added complexity involved in interpreting E2*
results from the fact that ... acceptable sentences of a na-
tural language in a manner which enables them to
be parsed by a finite- state device, and which also
predicts the way in which (at least) certain ex-
pressions with...
... parser for spontaneous
speech that is at once both robust and finite-
state. It is called PROFER, for Predictive, RO-
bust, Finite- state parsER. Currently PROFER
accepts a transcript as input. ... removed. Each
initial state of a sub-net is assumed into its par-
ent state which is equivalent to item-set for-
mation in that parent state (Figure 7 left-side).
Each final state of a sub-net ... begins the FSM always starts
at state 0:0 (i.e., net 0, start state 0) and tra-
verses an arc labeled by the top-level
net name
to the 0:1 state (i.e., net 0, final state 1), as il-
lustrated...
... poorer than that of
Chang et al., yet based on their published examples, our
71
A STOCHASTIC FINITE- STATE WORD-SEGMENTATION ALGORITHM
FOR CHINESE
Richard Sproat
Chilin Shih
William
Gale
AT&T ... University
Cambridge, MA 02138
nchang@das, harvard, edu
Abstract
We present a stochastic finite- state model for segment-
ing Chinese text into dictionary entries and produc-
tively derived ... Foreign Names: ~i~::,,~ bu4-
lang 3-shi4-wei2-ke4 'Brunswick'.
We present a stochastic finite- state model for seg-
menting Chinese text into dictionary entries and words
derived via the...
... Non-
concatenative finite -state morphotactics of Amharic
simple verbs. ELRC Working Papers, 2(3).
Jan Amtrup. 2003. Morphology in machine translation
systems: Efficient integration of finite state trans-
ducers ... Sound
Pattern of English. Harper and Row, New York.
Yael Cohen-Sygal and Shuly Wintner. 2006. Finite-
state registered automata for non-concatenative mor-
phology. Computational Linguistics, 32:49–82.
Ann ... and read from
(Cohen-Sygal and Wintner, 2006). Because it can
remember relevant previous states, a “finite -state
registered transducer” for template morphology
can keep the root and pattern separate...