Deniz Yuret's Homepage
I am an assistant professor in Computer Engineering
at Koç University in
Istanbul working at the Artificial Intelligence Laboratory
. Previously I was at the MIT AI Lab
and later co-founded Inquira, Inc.
My research is in natural language processing
and machine learning. This year I am helping organize SemEval-2012
, *SEM
, CMN
and LREC
. For prospective students here are
some research topics
, papers
, classes
, blog posts
and past students
.
Koç Üniversitesi Bilgisayar
Mühendisliği Bölümü 'nde öğretim üyesiyim ve
Yapay Zeka Laboratuarı 'nda çalışıyorum. Bundan
önce MIT Yapay Zeka Laboratuarı 'nda çalıştım
ve Inquira, Inc. şirketini kurdum. Araştırma
konularım doğal dil işleme ve yapay öğrenmedir. Bu yıl SemEval-2012
, *SEM
, CMN
ve LREC
'te görev alıyorum. İlgilenen
öğrenciler için araştırma konuları
, makaleler
, verdiğim
dersler , Türkçe
yazılarım
, ve
mezunlarımız .
July 15, 2012
ACL-EMNLP 2012 Highlights
We demonstrated 80% unsupervised part-of-speech induction accuracy in
our EMNLP-2012 paper
using paradigmatic representations of word context and co-occurrence
modeling. Here are some interesting talks I attended at ACL-EMNLP this year.
Check out this tutorial:
Inderjeet Mani; James Pustejovsky
Qualitative Modeling of Spatial Prepositions and Motion Expressions
http://aclweb.org/supplementals/P/P12/P12-4001.Presentation.pdf
And this paper from today on learning language from navigation
instructions and user behavior was interesting:
David Chen
Fast Online Lexicon Learning for Grounded Language Acquisition
http://aclweb.org/anthology-new/P/P12/P12-1045.pdf
All papers can be found on the ACL Anthology page:
http://aclweb.org/anthology-new/P/P12/
Here is a work that builds on CCM for unsupervised parsing that works
better on longer sentences:
P12-2004 [bib]: Dave Golland; John DeNero; Jakob Uszkoreit
A Feature-Rich Constituent Context Model for Grammar Induction
http://aclweb.org/anthology-new/P/P12/P12-2004.pdf
Here is another interesting talk about grounded language acquisition,
computer learning to follow instructions in a virtual world. They have
collected nice corpora of instructions and behaviors of people following
those instructions.
P12-2036 [bib]: Luciana Benotti; Martin Villalba; Tessa Lau; Julian Cerruti
Corpus-based Interpretation of Instructions in Virtual Environments
http://aclweb.org/anthology-new/P/P12/P12-2036.pdf
And here is another similar work on grounded language acquisition:
P12-1045 [bib]: David Chen
Fast Online Lexicon Learning for Grounded Language Acquisition
http://aclweb.org/anthology-new/P/P12/P12-1045.pdf
I nominate this as the best paper on computer humor generation of ACL
2012. Note the resources ConceptNet and SentiNet mentioned in this work
which may be independently useful.
P12-2030 [bib]: Igor Labutov; Hod Lipson
Humor as Circuits in Semantic Networks
http://aclweb.org/anthology-new/P/P12/P12-2030.pdf
We have been working on reordering for SMT. Here is a paper that
modifies distortion matrices instead to allow more flexible reorderings.
P12-1050 [bib]: Arianna Bisazza; Marcello Federico
Modified Distortion Matrices for Phrase-Based Statistical Machine
Translation
http://aclweb.org/anthology-new/P12-1050.pdf
Interesting tree transformation operations.
Transforming Trees to Improve Syntactic Convergence
D. Burkett and D. Klein .
http://aclweb.org/anthology-new/D/D12/D12-1079.pdf
The following paper utilizes n-gram language models in unsupervised
dependency parsing:
D12-1028 [bib]: David Mareček; Zdeněk Žabokrtský
Exploiting Reducibility in Unsupervised Dependency Parsing
http://aclweb.org/anthology-new/D/D12/D12-1028.pdf
Another reordering paper from EMNLP. Mentions a string to tree version
of Moses that is publicly available.
D12-1077 [bib]: Graham Neubig; Taro Watanabe; Shinsuke Mori
Inducing a Discriminative Parser to Optimize Machine Translation Reordering
http://aclweb.org/anthology-new/D/D12/D12-1077.pdf
Must read paper from emnlp. Very likely our paradigmatic representation
would do better here.
D12-1130 [bib]: Carina Silberer; Mirella Lapata
Grounded Models of Semantic Representation
Full post...
0 comments
June 10, 2012
KUTalks - Bilgisayarlara neden dil öğretmeye çalışıyoruz
Kaynak: Koç Üniversitesi'nin Youtube kanalı.
Full post...
Labels: Türkçe
0
comments
June 04, 2012
Language visualization
This is a presentation on our ongoing language visualization project by
Emre Unal. We thank the Alice project at CMU for
giving us the platform for 3D visualization. This work is inspired by
the work of Patrick Winston
's Genesis Group
at MIT and Bob Coyne
's WordsEye
project. We are also working
on going from vision to language as demonstrated in this video
.
Full post...
Labels: Notes 0
comments
May 24, 2012
Learning Syntactic Categories Using Paradigmatic Representations
of Word Context
Mehmet Ali Yatbaz, Enis Sert, Deniz Yuret. EMNLP 2012. (Download the
paper , presentation
,
code , fastsubs paper
, lm training data
(250MB), wsj substitute data
(1GB), scode visualization demo
(may take a few minutes to load). More up to date versions of the code
can be found at github .)
*Abstract:* We investigate paradigmatic representations of word context
in the domain of unsupervised syntactic category acquisition.
Paradigmatic representations of word context are based on potential
substitutes of a word in contrast to syntagmatic representations based
on properties of neighboring words. We compare a bigram based baseline
model with several paradigmatic models and demonstrate significant gains
in accuracy. Our best model based on Euclidean co-occurrence embedding
combines the paradigmatic context representation with morphological and
orthographic features and achieves 80% many-to-one accuracy on a 45-tag
1M word corpus.
Full post...
Labels: Publications
0 comments
FASTSUBS: An Efficient Admissible Algorithm for Finding the Most
Likely Lexical Substitutes Using a Statistical Language Model
Deniz Yuret, 2012. (Download the paper
, code
, and data
(1GB). Our EMNLP-2012
paper uses FASTSUBS to get the best published result in part of speech
induction.).
*Abstract:* Lexical substitutes have found use in the context of word
sense disambiguation, unsupervised part-of-speech induction,
paraphrasing, machine translation, and text simplification. Using a
statistical language model to find the most likely substitutes in a
given context is a successful approach, but the cost of a naive
algorithm is proportional to the vocabulary size. This paper presents
the Fastsubs algorithm which can efficiently and correctly identify the
most likely lexical substitutes for a given context based on a
statistical language model without going through most of the vocabulary.
The efficiency of Fastsubs makes large scale experiments based on
lexical substitutes feasible. For example, it is possible to compute the
top 10 substitutes for each one of the 1,173,766 tokens in Penn Treebank
in about 6 hours on a typical workstation. The same task would take
about 6 days with the naive algorithm. An implementation of the
algorithm and a dataset with the top 100 substitutes of each token in
the WSJ section of the Penn Treebank are available from the author's
website at http://goo.gl/jzKH0.
Full post...
Labels: Publications
0 comments
Older Posts
Home
Subscribe to: Posts (Atom)
My Photo
Deniz Yuret
Koç University
İstanbul Turkey
+90-212-338-1724
dyuret@ku.edu.tr
* Home
* AI Lab
* GitHub
* Scholar
* Türkçe
(49)
* Notes (41)
* Publications
(33)
* Books (24)
* Downloads (10)
* Math (10)
* Links (8)
* Students (8)
* Classes (1)
* Projects (1)
*Teaching*
Comp130 Introduction to Programming
*Curriculum Vitae*
2002-curr Koç University
2000-2002 Inquira, Inc.
1988-2000 B.S. M.S.
Ph.D. MIT
1985-1988 İzmir Fen Lisesi
*Bibliography*
*Dissertation*
Deniz Yuret's Homepage
Showing posts with label *Publications*. Show all posts
Showing posts with label *Publications*. Show all posts
May 24, 2012
Learning Syntactic Categories Using Paradigmatic Representations
of Word Context
Mehmet Ali Yatbaz, Enis Sert, Deniz Yuret. EMNLP 2012. (Download the
paper , presentation
,
code , fastsubs paper
, lm training data
(250MB), wsj substitute data
(1GB), scode visualization demo
(may take a few minutes to load). More up to date versions of the code
can be found at github .)
*Abstract:* We investigate paradigmatic representations of word context
in the domain of unsupervised syntactic category acquisition.
Paradigmatic representations of word context are based on potential
substitutes of a word in contrast to syntagmatic representations based
on properties of neighboring words. We compare a bigram based baseline
model with several paradigmatic models and demonstrate significant gains
in accuracy. Our best model based on Euclidean co-occurrence embedding
combines the paradigmatic context representation with morphological and
orthographic features and achieves 80% many-to-one accuracy on a 45-tag
1M word corpus.
Full post...
Labels: Publications
0 comments
FASTSUBS: An Efficient Admissible Algorithm for Finding the Most
Likely Lexical Substitutes Using a Statistical Language Model
Deniz Yuret, 2012. (Download the paper
, code
, and data
(1GB). Our EMNLP-2012
paper uses FASTSUBS to get the best published result in part of speech
induction.).
*Abstract:* Lexical substitutes have found use in the context of word
sense disambiguation, unsupervised part-of-speech induction,
paraphrasing, machine translation, and text simplification. Using a
statistical language model to find the most likely substitutes in a
given context is a successful approach, but the cost of a naive
algorithm is proportional to the vocabulary size. This paper presents
the Fastsubs algorithm which can efficiently and correctly identify the
most likely lexical substitutes for a given context based on a
statistical language model without going through most of the vocabulary.
The efficiency of Fastsubs makes large scale experiments based on
lexical substitutes feasible. For example, it is possible to compute the
top 10 substitutes for each one of the 1,173,766 tokens in Penn Treebank
in about 6 hours on a typical workstation. The same task would take
about 6 days with the naive algorithm. An implementation of the
algorithm and a dataset with the top 100 substitutes of each token in
the WSJ section of the Penn Treebank are available from the author's
website at http://goo.gl/jzKH0.
Full post...
Labels: Publications
0 comments
July 30, 2011
RegMT System for Machine Translation, System Combination, and
Evaluation
Ergun Bicici; Deniz Yuret. /Proceedings of the Sixth Workshop on
Statistical Machine Translation./ pp. 323-329. Edinburgh, Scotland.
July, 2011. (PDF ,
BIB , Proceedings
, Poster
)
*Abstract:* We present the results we obtain using our RegMT system,
which uses transductive regression techniques to learn mappings between
source and target features of given parallel corpora and use these
mappings to generate machine translation outputs. Our training instance
selection methods perform feature decay for proper selection of training
instances, which plays an important role to learn correct feature
mappings. RegMT uses L2 regularized regression as well as L1 regularized
regression for sparse regression estimation of target features. We
present translation results using our training instance selection
methods, translation results using graph decoding, system combination
results with RegMT, and performance evaluation with the
F1 measure over target features as a metric for evaluating translation
quality.
Full post...
Related link
Labels: Publications
0 comments
Instance Selection for Machine Translation using Feature Decay
Algorithms
Ergun Bicici; Deniz Yuret. /Proceedings of the Sixth Workshop on
Statistical Machine Translation./ pp. 272-283. Edinburgh, Scotland.
July, 2011. (PDF ,
BIB , Proceedings
, Presentation
)
*Abstract:* We present an empirical study of instance selection
techniques for machine translation. In an active learning setting,
instance selection minimizes the human effort by identifying the most
informative sentences for translation. In a transductive learning
setting, selection of training instances relevant to the test set
improves the final translation quality. After reviewing the state of the
art in the field, we generalize the main ideas in a class of instance
selection algorithms that use feature decay. Feature decay algorithms
increase diversity of the training set by devaluing features that are
already included. We show that the feature decay rate has a very strong
effect on the final translation quality whereas the initial feature
values, inclusion of higher order features, or sentence length
normalizations do not. We evaluate the best instance selection methods
using a standard Moses baseline using the whole 1.6 million sentence
English-German section of the Europarl corpus. We show that selecting
the best 3000 training sentences for a specific test sentence is
sufficient to obtain a score within 1 BLEU of the baseline, using 5% of
the training data is sufficient to exceed the baseline, and a ~ 2 BLEU
improvement over the baseline is possible by optimally selected subset
of the training data. In out-of-domain translation, we are able to
reduce the training set size to about 7% and achieve a similar
performance with the baseline.
Full post...
Related link
Labels: Publications
0 comments
October 27, 2010
Anharmonicity, mode-coupling and entropy in a fluctuating native
protein
A. Kabakçıoğlu, D. Yuret, M. Gür, B. Erman. 2010 Phys. Biol. 7 046005
doi: 10.1088/1478-3975/7/4/046005
(PDF
,
PDF
,
HTML , Online
, Hermite code
)
*Abstract:* We develop a general framework for the analysis of residue
fluctuations that simultaneously incorporates anharmonicity and
mode-coupling in a unified formalism. We show that both deviations from
the Gaussian model are important for modeling the multidimensional
energy landscape of the protein Crambin (1EJG) in the vicinity of its
native state. The effect of anharmonicity and mode-coupling on the
fluctuational entropy is in the order of a few percent.
Full post...
Related link
Labels: Publications
0 comments
August 26, 2010
Unsupervised Part of Speech Tagging Using Unambiguous Substitutes
from a Statistical Language Model
Mehmet Ali Yatbaz and Deniz Yuret. Coling 2010. pp. 1391--1398. Beijing,
China. (PDF , Poster
)
*Abstract:* We show that unsupervised part of speech tagging performance
can be significantly improved using likely substitutes for target words
given by a statistical language model. We choose unambiguous substitutes
for each occurrence of an ambiguous target word based on its context.
The part of speech tags for the unambiguous substitutes are then used to
filter the entry for the target word in the word--tag dictionary. A
standard HMM model trained using the filtered dictionary achieves 92.25%
accuracy on a standard 24,000 word corpus.
Full post...
Related link
Labels: Publications
0 comments
July 15, 2010
SemEval-2010 Task 12: Parser Evaluation using Textual Entailments
Deniz Yuret, Aydın Han, Zehra Turgut. /Proceedings of the 5th
International Workshop on Semantic Evaluation. (SemEval-2010
)/ pp. 51--56. July, 2010. Uppsala,
Sweden. (PDF ,
Presentation
, Task
website , Proceedings
, Journal submission
).
*Abstract:* Parser Evaluation using Textual Entailments (PETE) is a
shared task in the SemEval-2010 Evaluation Exercises on Semantic
Evaluation. The task involves recognizing textual entailments based on
syntactic information alone. PETE introduces a new parser evaluation
scheme that is formalism independent, less prone to annotation error,
and focused on semantically relevant distinctions.
Full post...
Related link
Labels: Publications
0 comments
L1 Regularized Regression for Reranking and System Combination in
Machine Translation
Ergun Bicici, Deniz Yuret. /Proceedings of the Joint Fifth Workshop on
Statistical Machine Translation and MetricsMATR./ pp. 282--289. July
2010. Uppsala, Sweden. (PDF
, Slide
,
Poster
)
*Abstract:* We use L1 regularized transductive regression to learn
mappings between source and target features of the training sets derived
for each test sentence and use these mappings to rerank translation
outputs. We compare the effectiveness of L1 regularization techniques
for regression to learn mappings between features given in a sparse
feature matrix. The results show the effectiveness of using L1
regularization versus L2 used in ridge regression. We show that
regression mapping is effective in reranking translation outputs and in
selecting the best system combinations with encouraging results on
different language pairs.
Full post...
Related link
Labels: Publications
0 comments
February 21, 2010
Preprocessing with Linear Transformations that Maximize the
Nearest Neighbor Classification Accuracy
Mehmet Ali Yatbaz and Deniz Yuret. /1st CSE Student Workshop (CSW’10)/,
21 February 2010, Koc Istinye Campus, Istanbul. (PDF
,
PPT )
*Abstract*
We introduce a preprocessing technique for classification problems based
on linear transformations. The algorithm incrementally constructs a
linear transformation that maximizes the nearest neighbor classification
accuracy on the training set. At each iteration the algorithm picks a
point in the dataset, and computes a transformation
that moves the point closer to points in its own class and/or away from
points in other classes. The composition of the resulting linear
transformations lead to statistically significant improvements in
instance based learning algorithms.
Full post...
Related link
Labels: Publications
0 comments
L1 Regularization for Learning Word Alignments in Sparse Feature
Matrices
Ergun Bicici and Deniz Yuret. /1st CSE Student Workshop (CSW’10)/, 21
February 2010, Koc Istinye Campus, Istanbul. (PDF
,
Poster
)
*Abstract*
Sparse feature representations can be used in various domains. We
compare the effectiveness of regularization techniques for regression to
learn mappings between features given in a sparse feature matrix. We
apply these techniques for learning word alignments commonly used for
machine translation. The performance of the learned mappings are
measured using the phrase table generated on a larger corpus by a state
of the art word aligner. The results show the effectiveness of using
regularization versus used in ridge regression.
Full post...
Related link
Labels: Publications
0 comments
February 19, 2010
The Noisy Channel Model for Unsupervised Word Sense Disambiguation
Deniz Yuret and Mehmet Ali Yatbaz. /Computational Linguistics, Volume
36, Number 1 , March 2010./
(Abstract
,
PDF )
*Abstract:* We introduce a generative probabilistic model, the noisy
channel model, for unsupervised word sense disambiguation. In our model,
each context C is modeled as a distinct channel through which the
speaker intends to transmit a particular meaning S using a possibly
ambiguous word W. To reconstruct the intended meaning the hearer uses
the distribution of possible meanings in the given context P(S|C) and
possible words that can express each meaning P(W|S). We assume P(W|S) is
independent of the context and estimate it using WordNet sense
frequencies. The main problem of unsupervised WSD is estimating context
dependent P(S|C) without access to any sense tagged text. We show one
way to solve this problem using a statistical language model based on
large amounts of untagged text. Our model uses coarse-grained semantic
classes for S internally and we explore the effect of using different
levels of granularity on WSD performance. The system outputs fine
grained senses for evaluation and its performance on noun disambiguation
is better than most previously reported unsupervised systems and close
to the best supervised systems.
Full post...
Labels: Publications
0 comments
December 11, 2009
Unsupervised morphological disambiguation using statistical
language models
Mehmet Ali Yatbaz and Deniz Yuret. /NIPS 2009 Workshop on Grammar
Induction, Representation of Language and Language Learning./ December
2009. (PDF
,
Poster
)
*Abstract:*
In this paper, we present a probabilistic model for the unsupervised
morphological disambiguation problem. Our model assigns morphological
parses T to the contexts C instead of assigning them to the words W. The
target word determines the possible parse set that can be used in 's
context . To assign the correct morphological parse to , our model finds
the parse that maximizes . 's are estimated using a statistical language
model and the vocabulary of the corpus. The system performs
significantly better than an unsupervised baseline and its performance
is close to a supervised baseline.
Full post...
Labels: Publications
0 comments
August 04, 2009
Modeling Morphologically Rich Languages Using Split Words and
Unstructured Dependencies
Deniz Yuret and Ergun Bicici. In /the Joint conference of the 47th
Annual Meeting of the Association for Computational Linguistics and the
4th International Joint Conference on Natural Language Processing of the
Asian Federation of Natural Language Processing (ACL-IJCNLP 2009)/ (PDF
).
*Abstract:* We experiment with splitting words into their stem and suffix
components for modeling morphologically rich languages. We show that
using a morphological analyzer and disambiguator results in a significant
perplexity reduction in Turkish. We present flexible n-gram models,
Flex-Grams, which assume that the n−1 tokens that determine the
probability of a given token can be chosen anywhere in the sentence
rather than the preceding n − 1 positions. Our final model achieves 27%
perplexity reduction compared to the standard n-gram model.
Full post...
Related link
Labels: Publications
0 comments
July 22, 2009
Morphological cues vs. number of nominals in learning verb types
in Turkish: The syntactic bootstrapping mechanism revisited
A. Engin Ural; Deniz Yuret; F. Nihan Ketrez; Dilara Koçbaş; Aylin C.
Küntay. /Language and Cognitive Processes, 24(10), pp. 1393-1405,
December 2009/ (PDF
,
PDF
,
HTML
).
Abstract: The syntactic bootstrapping mechanism of verb learning was
evaluated against child-directed speech in Turkish, a language with rich
morphology, nominal ellipsis and free word order. Machine-learning
algorithms were run on transcribed caregiver speech directed to two
Turkish learners (one hour every two weeks between 0;9 to 1;10) of
different socioeconomic backgrounds. We found that the number of
nominals in child-directed utterances plays a small, but significant,
role in classifying transitive and intransitive verbs. Further, we found
that accusative morphology on the noun is a strong cue in clustering
verb types. We also found that verbal morphology (past tense and
bareness of verbs) is useful in distinguishing between different
subtypes of intransitive verbs. These results suggest that syntactic
bootstrapping mechanisms should be extended to include morphological
cues to verb learning in morphologically rich languages.
Keywords: Language development; Turkish; Child-directed speech,
Syntactic bootstrapping; Morphology
Full post...
Related link
Labels: Publications
0 comments
March 03, 2009
Classification of semantic relations between nominals
Roxana Girju, Preslav Nakov, Vivi Nastase, Stan Szpakowicz, Peter Turney
and Deniz Yuret. /Language Resources and Evaluation, 2009, 43(2),
105-121./ (PDF
,
PDF ,
HTML ).
Abstract: The NLP community has shown a renewed interest in deeper
semantic analyses, among them automatic recognition of semantic
relations in text. We present the development and evaluation of a
semantic analysis task: automatic recognition of relations between pairs
of nominals in a sentence. The task was part of SemEval-2007, the fourth
edition of the semantic evaluation event previously known as SensEval.
Apart from the observations we have made, the long-lasting effect of
this task may be a framework for comparing approaches to the task. We
introduce the problem of recognizing relations between nominals, and in
particular the process of drafting and refining the definitions of the
semantic relations. We show how we created the training and test data,
list and briefly describe the 15 participating systems, discuss the
results, and conclude with the lessons learned in the course of this
exercise.
Full post...
Related link
Labels: Publications
0 comments
October 31, 2008
Morphological cues vs. number of nominals in learning verb types
in Turkish: Syntactic bootstrapping mechanism revisited
Deniz Yuret, A. Engin Ural, Nihan Ketrez, Dilara Koçbaş and Aylin C.
Küntay. In /The Boston University Conference on Language Development
(BUCLD)/ (Long abstract
, poster
, PDF
)
Abstract: The syntactic bootstrapping mechanism of verb classification
was evaluated against child-directed speech in Turkish, a language with
rich morphology, nominal ellipsis and free word order. Machine-learning
algorithms were run on transcribed caregiver speech (12,276 and 20,687
utterances) directed to two Turkish learners (one hour every two weeks
between 0,9 to 1;10) of different socioeconomic backgrounds. The corpora
contained 12,276 and 20,687 child-directed utterances. Study 1 found
that the number of nominals in child-directed utterances plays some role
in classifying transitive and intransitive verbs. Study 2 found that
accusative morphology on the noun is a stronger cue in clustering verb
types. Study 3 found that verbal morphology is useful in distinguishing
between different subtypes of intransitive verbs. These results suggest
that syntactic bootstrapping mechanisms should be extended to include
morphological cues to verb learning in morphologically rich languages.
Full post...
Related link