... and lex-
ical information are useful for verb classification.
Although neither SCF nor CO performs well on its
own, a combination of them proves to be the most in-
formative feature for this task. ... 10
verbs. We therefore reduce the number of training
verbs to 9 for each class. For each n = 2, 5, 10, 20,
30, 40, 48, we will perform certain number of n-way
classification tasks. For each n-way ... di-
rectly into subcategorization frames has proved in-
adequate for AVC. Other methods for combining
syntactic information with lexical information have
also been attempted (Merlo and Stevenson, 2001;
Joanis...
... unified framework
for automatic evaluation of NLP applications
using N-gram co-occurrence statistics. The
automatic evaluation metrics proposed to date
for Machine Translation and Automatic
Summarization ... R
2
for the family of metrics AEv(α,N), for correctness scores, second QA evaluation
A Unified Framework forAutomatic Evaluation using
N-gram Co-Occurrence Statistics
Radu SORICUT
Information ... unified framework
for automatic evaluation based on N-gram co-
occurrence statistics, for NLP applications for
which a correct answer is usually an unfeasibly
large set (e.g., Machine Translation,...
... system
performance for a given input is in fact relevant not
only for summarization, but in general for all ap-
plications aimed at facilitating information access.
In question answering for example, ... prove
beneficial for the task. We also find that per-
formance predictions for single-document sum-
marization can be done more accurately than for
multi-document summarization. The best classi-
fier for single-document ... two
classes of expected performance. Poor perfor-
mance was assigned to the inputs for which the
average system coverage score was lower than the
average for all inputs. Good performance was as-
signed...
... improve the performance of the
system by integrating automatic feedback
from the student answers. Overall, our
system significantly and consistently out-
performs other unsupervised methods for
short ... similarity
perform comparably when used for the task of
short answer grading. However, since the corpus-
based measures can be improved by account-
ing for domain and corpus size, the highest per-
formance ... feedback in information
retrieval. Prentice Hall, Ing. Englewood Cliffs, New
Jersey.
G. Salton, A. Wong, and C.S. Yang. 1997. A vec-
tor space model forautomatic indexing. In Read-
ings in Information...
... responsible for this performance
boost over their fully automatic system, thus mak-
ing the case that automatic discourse segmentation is
the primary impediment to high accuracy automatic
sentence-level ... 2007.
c
2007 Association for Computational Linguistics
The utility of parse-derived features forautomatic discourse segmentation
Seeger Fisher and Brian Roark
Center for Spoken Language Understanding, ... boundaries in the RST-DT do
not correspond to a well-formed subtree in the hu-
man annotated discourse parse for that document.
Therefore, to perform accurate and efficient pars-
ing of the RST-DT...
... Technology
foch,zens,neyl@cs.rwth
-
aachen.de
Abstract
The goal of interactive machine transla-
tion is to improve the productivity of hu-
man translators. An interactive machine
translation system operates as follows:
the automatic system proposes ... post-editing
'The author is now affiliated with the Information Science
Institute, University of Southern California, och@isi.edu
.
of the machine translation output is necessary. In
such an environment, ... Pr(ff}ef )}
(3)
For simplicity, we formulated this equation on the
level of whole words, but of course, the same
method can also be applied at the character level.
In an interactive machine translation...
... transcription.
For example, if the ASR output contains the
term sequence “… and farther home run for David
forty says…” and the closed captioning contains
the sequence “…another home run for David ... ability to sup-
port video information retrieval.
4.3 Precision of Information Retrieval
One of the most commonly used applications of
ASR for video is to support information retrieval
(IR). ... and then for all patterns within an
event. The resulting parameter estimates are
smoothed using a simple add N smoothing tech-
nique, where N=1 for the word by topic counts and
N=.01 for the...
... Open
source toolkit for statistical machine translation. In
Proceedings of the ACL-2007 Demo and Poster Ses-
sions.
Zhifei Li and Sanjeev Khudanpur. 2008. A scalable
decoder for parsing-based machine translation ... source toolkit for parsing-
based machine translation. In Proceedings of the
Fourth Workshop on Statistical Machine Transla-
tion, pages 135–139, Athens, Greece, March. As-
sociation for Computational ... Variational decoding for statistical machine
translation. In Proceedings of ACL.
Yang Liu, Qun Liu, and Shouxun Lin. 2006. Tree-
to-string alignment templates for statistical machine
translation....
... but we take
it for granted that this is performed by an independent system
based on other knowledge sources, and therefore out of scope
here.
where the second row is the analyzed form in terms
of ... the tuple T and an unseen ˜e, our idea is to
combine both the information of verb forms seen in
training and off-the-shelf knowledge for generation.
A translation memory can be built with all the ... future form):
we will go VB 1P F
we will go VB 1P P
These alternatives can be weighted according to
the times we have seen each case in training. An un-
ambiguous form generator produces the forms...
... performance over all goals
while maintaining a clear performance measure
for in-domain goals. Scores should be calculated
separately based on domain, since this will indi-
cate system performance ... Task-Based Evaluation Methodology
for a Spoken Machine Translation System
Kavita Thomas
Language Technologies Institute
Carnegie Mellon University
5000 Forbes Avenue
Pittsburgh, PA 15213, ... of a task-based evaluation methodology
for a spoken machine translation (MT) sys-
tem processing human to human communica-
tion rather than human to machine communi-
cation. I claim that system...
... has been proposed would
appear to be really beyond the reach of a concerted
effort. For information retrieval, and for social science,
the implications of having a computer program able
to reproduce ... all of
it—becomes transformed into “meaningful” informa-
tion before or as it reaches the person’s action direc-
tion center. We may ask: What is the nature of the
transformation it undergoes ... Computation Center. For further informa-
tion, contact V. H. Yngve, COMIT, Room 20D-102, M.I.T., Cam-
bridge, Massachusetts.
26
This is basically the method here proposed for all
machine translation,...
... the Association for Computational Linguistics, pages 148–156,
Uppsala, Sweden, 11-16 July 2010.
c
2010 Association for Computational Linguistics
Pseudo-word for Phrase-based Machine Translation ... is performed in a way similar to
CKY (Cocke-Kasami-Younger) parser.
Initialization: W
i, i
= Sig
i, i
;
W
i, j
= 0, (i≠j);
1: for d = 2 … n do
2: for all i, j s.t. j-i=d-1 do
3: for k ... Baseline Performance
Our baseline system feeds word into PB-SMT
pipeline. We use GIZA++ model 4 for word
alignment, use Moses for phrase-based decoding.
The setting of language model order for each...
... Classification
The approaches used forautomatic classification
are also varied. Vanderwende (1994) presents one
of the first systems forautomatic classification,
which extracted information from online sources
and ... Association for Computational Linguistics, pages 678–687,
Uppsala, Sweden, 11-16 July 2010.
c
2010 Association for Computational Linguistics
A Taxonomy, Dataset, and Classifier forAutomatic Noun ... Compound
Interpretation
Stephen Tratz and Eduard Hovy
Information Sciences Institute
University of Southern California
Marina del Rey, CA 90292
{stratz,hovy}@isi.edu
Abstract
The automatic interpretation of noun-noun
compounds...
... for system combination, the
source languages for each of our MT systems are
different, which rules out a set of popular methods
for obtaining consensus translations which assume
translation for ... and Wei
jing Zhu. 2002. Bleu: A method forautomatic eval-
uation of machine translation. In ACL ’02: Proceed-
ings of the 41st Annual Meeting on Association for
Computational Linguistics.
Roi Reichart, ... 2: The performance of different sentence selection strategies as the iteration of AL loop goes on for three translation
tasks. Plots show the performance of sentence selection methods for single...