 |
 |
 |
| 'Home | 'Contact | 'Brief CV | 'Publications | 'Activities |
'Research | 'Teaching | 'Misc. |
|---|
Khalil Sima'an
- All
publications
in reverse chronological order are here
- Publications concerning Consistent Statistical Estimators for DOP and Phrase-Based SMT are here
Highlighted publications
| Markos Mylonakis and Khalil Sima'an. Learning Hierarchical Translation Structure with Linguistic Annotations. In the Proceedings of The 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL:HLT 2011). Feb 2011. | Syntactic statistical
Machine Translation; Estimation; Learning
reordering |
 |
| Hany Hassan, Khalil Sima'an and Andy Way. A Morpho-Syntactically Enriched Direct Translation Model with Efficient Decoding. Machine Translation Journal, Springer, 2011. | Syntactic statistical
Machine Translation; Incremental decoding and
parsing |
|
| Markos
Mylonakis and Khalil Sima'an. Learning
Probabilistic Synchronous
CFGs for Phrase Translation Models. In Proceedings
of
the Fourteenth Conference on Computational
Natural Language Learning
(CoNLL 2010), Uppsala, Sweden,
July 2010 |
Statistical Machine Translation; Estimation; Learning reordering | |
| Reut Tsarfaty, Khalil Sima'an and Remko Scha. Evaluating an Alternative to Head-Driven Approaches to Parsing a (Relatively) Free Word-Order Language. In Proceedings of the Conference on Empirical Methods in NLP (EMNLP'09), Singapore. | Statistical Parsing;
Morphology-syntax interface |
pdf |
| Hany Hassan, Khalil Sima'an and Andy Way. A Syntactified Direct Translation Model with Linear-Time Decoding. In Proceedings of the Conference on Empirical Methods in NLP (EMNLP'09), Singapore. | Syntactic Machine Translation; Incremental decoding and parsing | |
| Hany
Hassan, Khalil Sima'an and
Andy Way. Syntactically
Lexicalized
Phrase-Based
Statistical Translation. In IEEE Transactions
on Audio, Speech and Language Processing,
Volume 16, Number 7.
September 2008. |
Syntactic Machine Translation; Incremental decoding and parsing | |
| Barbara Plank and Khalil Sima'an. Parsing with Subdomain Instance Weighting from Raw Corpora. In proceedings Interspeech 2008, Australia, Sep. 2008. | Subdomain; Domain
Adaptation; Inference from unannotated data. |
|
| Markos
Mylonakis and Khalil Sima'an. Phrase Translation
Probabilities with ITG Priors and Smoothing as
Learning Objective. In
Proceedings of the Conference
on Empirical Methods in NLP (EMNLP'08),
2008. |
Statistical Machine Translation; Estimation; Learning | |
| Reut
Tsarfaty
and Khalil Sima'an. Relational
Realizational
Parsing. In
proceedings COLING
2008,
Manchester, UK, August 2008. |
Statistical Parsing; Morphology-syntax interface | |
| Roy Bar-Haim, Khalil Sima'an and Yoad Winter. Part-of-Speech Tagging of Modern Hebrew Text. In Journal of Natural Language Engineering (J-NLE), 14(2):223-251, 2008. | HMM-based Morphological
disambiguation for Hebrew and Arabic |
|
| Markos
Mylonakis, Khalil Sima'an and
Rebecca
Hwa. Unsupervised
Estimation for Noisy-Channel Models . In Proceedings
24th Annual International
Conference on
Machine Learning (ICML 2007).
|
Learning lexicon
probabilities from non-parallel data |
|
| Hany
Hassan, Khalil Sima'an
and Andy Way.
Supertagged
Phrase-Based Statistical Machine Translation. In
Proceedings 45th
Annual
Meeting
of
the
Assoc.
for Comp. Linguistics, Prague,
2007 (ACL 2007). |
Syntactic Machine Translation; Incremental decoding and parsing | |
| Andreas
Zollmann
and Khalil Sima'an. A
Consistent and Efficient Estimator for
Data-Oriented Parsing. Journal
of Automata, Languages and
Combinatorics (JALC) Vol. 10
(2005)
Number 2/3, pages 367-388. Presents a consistent estimator for DOP with a proof of consistency. |
Consistent estimators for
DOP |
|
| Khalil Sima'an. Robust Data-Oriented Understanding of Spoken Utterances. In H. Bunt, J. Carroll and G. Satta (eds.), New Developments in Parsing Technologies, pages 323-338, Kluwer (2004). | Speech understanding;
Update Semantics; Statistical Parsing |
|
| Khalil
Sima'an and
Luciano
Buratto. Backoff
Parameter Estimation for the DOP Model.
In
Proceedings
of
the
European Conference on Machine Learning
(ECML'03), N.
Lavrac, D. Gamberger, H.
Blockeel and L. Todorovski (ed.). Lecture
Notes
in Artificial
Intelligence (LNAI
2837), pages 373-384,
Springer, 2003. |
Consistent estimators for DOP | |
| Khalil
Sima'an. On
Maximizing Metrics for Syntactic Disambiguation. In
Proceedings of the International Workshop
on Parsing Technologies (IWPT'03). Nancy,
France, April 2003. Presents among others a Minimum-Bayes Risk decoding algorithm referred to by others as the MAX-RULE-SUM (see, e.g., Bansal and Klein 2010, ..., Petrov et al 2007 , Matsuzaki et al 2005), or the Maximum Expected CFG Rule count algorithm (see, e.g., Cohn et al 2008). |
Minimum-Bayes Risk
decoding for statistical parsing models |
|
| Rend Bod, Remko Scha and Khalil Sima'an (editors). Data-Oriented Parsing. Studies in Computational Linguistics, CSLI Publications, University of Chicago Press, 2003. | Data-Oriented Parsing |
|
| Khalil Sima'an. Computational Complexity of Probabilistic Disambiguation: NP-Completeness Results for Language and Speech Processing. In Grammars, Volume 5(2), Kluwer Publishers, 2002. | Computational Complexity
of statistical disambiguation |
|
| Khalil Sima'an, A. Itai, Y. Winter, A. Altman and N. Nativ. Building a Tree-Bank of Modern Hebrew Text. In Beatrice Daille and Laurent Romary (eds.), Journal Traitement Automatique des Langues (T.A.L) , 2001. Special Issue on Natural Language Processing and Corpus Linguistics. | Hebrew treebanking;
Statistical Parsing |
|
| Khalil
Sima'an.
Tree-gram
Parsing:
Lexical
Dependencies
and Structural
Relations
Proceedings
of
38th
Annual
Meeting
of
the
Association
for
Computational
Linguistics (ACL'00)
,
Hong
Kong, China,
2000. Content: Presents a novel model for parsing that combines the strengths of DOP with those of bilexical-dependency models (Charniak 1999; Collins 1997), including head-binarized ``subtrees" (Tree-grams) with label splitting by parent-encoding (Johnson 1999) and head pre-terminals. The implementation employs a coarse-to-fine parser (PCFG then Tree-gram). See Mohit Bansal and Dan Klein 2010 for an exploration extending this model with compact Goodman representations, optimized parameter settings and state-of-the-art parsing results for different languages. |
Treegrams; Statistical
Parsing; Horizonal-Markov DOP; Lexicalized DOP |
|
| Khalil Sima'an. Efficient Disambiguation by means of Stochastic Tree Substitution Grammars. In New Methods in Language Processing . D. Jones and H. Somers (editors), UCL Press, UK, 1997. | Statistical Parsing |
|
| Remko Scha, Rens Bod and Khalil Sima'an. A Memory-Based Model of Syntactic Analysis: Data-Oriented Parsing. In special Issue on Memory-Based Processing, W. Daelemans (ed.), Journal of Empirical and Theoretical Artificial Intelligence (JETAI), 11 (3), 1999. | Data-Oriented Parsing;
Memory-based models |
|
| Khalil Sima'an. Explanation-Based Learning of Data-Oriented Parsing. In Proceedings of the Conference on Computational Natural Language Learning (CoNLL), jointly with ACL/EACL-97, Madrid, Spain, July 1997. The first publication aiming at learning the set of fragments for a DOP model from a treebank. | Statistical learning of
compact DOP models |
|
| Khalil
Sima'an.
Computational
Complexity
of
Probabilistic
Disambiguation
by means of
Tree Grammars.In
Proceedings
of the
International
Conference on
Computational
Linguistics
(COLING '96),
pp.1175-1180
(vol.
2),
Copenhagen,
Denmark,
August 1996. Content: Presents a proof of NP-Completeness for a set of related problems including computing the highest probability parse for an input sentence under probabilistic tree-subsitution grammars (PTSGs), computing the highest probability string from an input lattice under a probabilistic context-free grammar (PCFG) and under PTSG. The latter two problems are the problems of ``decoding" in speech recognition and machine translation when the (target) language model is a PCFG or PTSG. |
Computational complexity
of statistical disambiguation |