Khalil Sima’an

Also published as: K. Sima’an


2018

pdf bib
Deep Generative Model for Joint Alignment and Word Representation
Miguel Rios | Wilker Aziz | Khalil Sima’an
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

This work exploits translation data as a source of semantically relevant learning signal for models of word representation. In particular, we exploit equivalence through translation as a form of distributional context and jointly learn how to embed and align with a deep generative model. Our EmbedAlign model embeds words in their complete observed context and learns by marginalisation of latent lexical alignments. Besides, it embeds words as posterior probability densities, rather than point estimates, which allows us to compare words in context using a measure of overlap between distributions (e.g. KL divergence). We investigate our model’s performance on a range of lexical semantics tasks achieving competitive results on several standard benchmarks including natural language inference, paraphrasing, and text similarity.

2017

pdf bib
Alternative Objective Functions for Training MT Evaluation Metrics
Miloš Stanojević | Khalil Sima’an
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

MT evaluation metrics are tested for correlation with human judgments either at the sentence- or the corpus-level. Trained metrics ignore corpus-level judgments and are trained for high sentence-level correlation only. We show that training only for one objective (sentence or corpus level), can not only harm the performance on the other objective, but it can also be suboptimal for the objective being optimized. To this end we present a metric trained for corpus-level and show empirical comparison against a metric trained for sentence-level exemplifying how their performance may vary per language pair, type and level of judgment. Subsequently we propose a model trained to optimize both objectives simultaneously and show that it is far more stable than–and on average outperforms–both models on both objectives.

pdf bib
Graph Convolutional Encoders for Syntax-aware Neural Machine Translation
Jasmijn Bastings | Ivan Titov | Wilker Aziz | Diego Marcheggiani | Khalil Sima’an
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

We present a simple and effective approach to incorporating syntactic structure into neural attention-based encoder-decoder models for machine translation. We rely on graph-convolutional networks (GCNs), a recent class of neural networks developed for modeling graph-structured data. Our GCNs use predicted syntactic dependency trees of source sentences to produce representations of words (i.e. hidden states of the encoder) that are sensitive to their syntactic neighborhoods. GCNs take word representations as input and produce word representations as output, so they can easily be incorporated as layers into standard encoders (e.g., on top of bidirectional RNNs or convolutional neural networks). We evaluate their effectiveness with English-German and English-Czech translation experiments for different types of encoders and observe substantial improvements over their syntax-agnostic versions in all the considered setups.

2016

pdf bib
Hierarchical Permutation Complexity for Word Order Evaluation
Miloš Stanojević | Khalil Sima’an
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Existing approaches for evaluating word order in machine translation work with metrics computed directly over a permutation of word positions in system output relative to a reference translation. However, every permutation factorizes into a permutation tree (PET) built of primal permutations, i.e., atomic units that do not factorize any further. In this paper we explore the idea that permutations factorizing into (on average) shorter primal permutations should represent simpler ordering as well. Consequently, we contribute Permutation Complexity, a class of metrics over PETs and their extension to forests, and define tight metrics, a sub-class of metrics implementing this idea. Subsequently we define example tight metrics and empirically test them in word order evaluation. Experiments on the WMT13 data sets for ten language pairs show that a tight metric is more often than not better than the baselines.

pdf bib
Universal Reordering via Linguistic Typology
Joachim Daiber | Miloš Stanojević | Khalil Sima’an
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

In this paper we explore the novel idea of building a single universal reordering model from English to a large number of target languages. To build this model we exploit typological features of word order for a large number of target languages together with source (English) syntactic features and we train this model on a single combined parallel corpus representing all (22) involved language pairs. We contribute experimental evidence for the usefulness of linguistically defined typological features for building such a model. When the universal reordering model is used for preordering followed by monotone translation (no reordering inside the decoder), our experiments show that this pipeline gives comparable or improved translation performance with a phrase-based baseline for a large number of language pairs (12 out of 22) from diverse language families.

pdf bib
Word Alignment without NULL Words
Philip Schulz | Wilker Aziz | Khalil Sima’an
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

pdf bib
Examining the Relationship between Preordering and Word Order Freedom in Machine Translation
Joachim Daiber | Miloš Stanojević | Wilker Aziz | Khalil Sima’an
Proceedings of the First Conference on Machine Translation: Volume 1, Research Papers

pdf bib
ILLC-UvA Adaptation System (Scorpio) at WMT’16 IT-DOMAIN Task
Hoang Cuong | Stella Frank | Khalil Sima’an
Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers

pdf bib
A Shared Task on Multimodal Machine Translation and Crosslingual Image Description
Lucia Specia | Stella Frank | Khalil Sima’an | Desmond Elliott
Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers

pdf bib
Multi30K: Multilingual English-German Image Descriptions
Desmond Elliott | Stella Frank | Khalil Sima’an | Lucia Specia
Proceedings of the 5th Workshop on Vision and Language

pdf bib
Factoring Adjunction in Hierarchical Phrase-Based SMT
Sophie Arnoult | Khalil Sima’an
Proceedings of the 2nd Deep Machine Translation Workshop

pdf bib
Adapting to All Domains at Once: Rewarding Domain Invariance in SMT
Hoang Cuong | Khalil Sima’an | Ivan Titov
Transactions of the Association for Computational Linguistics, Volume 4

Existing work on domain adaptation for statistical machine translation has consistently assumed access to a small sample from the test distribution (target domain) at training time. In practice, however, the target domain may not be known at training time or it may change to match user needs. In such situations, it is natural to push the system to make safer choices, giving higher preference to domain-invariant translations, which work well across domains, over risky domain-specific alternatives. We encode this intuition by (1) inducing latent subdomains from the training data only; (2) introducing features which measure how specialized phrases are to individual induced sub-domains; (3) estimating feature weights on out-of-domain data (rather than on the target domain). We conduct experiments on three language pairs and a number of different domains. We observe consistent improvements over a baseline which does not explicitly reward domain invariance.

2015

pdf bib
Reordering Grammar Induction
Miloš Stanojević | Khalil Sima’an
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
BEER 1.1: ILLC UvA submission to metrics and tuning task
Miloš Stanojević | Khalil Sima’an
Proceedings of the Tenth Workshop on Statistical Machine Translation

pdf bib
Modelling the Adjunct/Argument Distinction in Hierarchical Phrase-Based SMT
Sophie Arnoult | Khalil Sima’an
Proceedings of the 1st Deep Machine Translation Workshop

pdf bib
Delimiting Morphosyntactic Search Space with Source-Side Reordering Models
Joachim Daiber | Khalil Sima’an
Proceedings of the 1st Deep Machine Translation Workshop

pdf bib
Latent Domain Word Alignment for Heterogeneous Corpora
Hoang Cuong | Khalil Sima’an
Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

2014

pdf bib
BEER: BEtter Evaluation as Ranking
Miloš Stanojević | Khalil Sima’an
Proceedings of the Ninth Workshop on Statistical Machine Translation

pdf bib
Bilingual Markov Reordering Labels for Hierarchical SMT
Gideon Maillette de Buy Wenniger | Khalil Sima’an
Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation

pdf bib
Evaluating Word Order Recursively over Permutation-Forests
Miloš Stanojević | Khalil Sima’an
Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation

pdf bib
How Synchronous are Adjuncts in Translation Data?
Sophie Arnoult | Khalil Sima’an
Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation

pdf bib
Latent Domain Translation Models in Mix-of-Domains Haystack
Hoang Cuong | Khalil Sima’an
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers

pdf bib
Fitting Sentence Level Translation Evaluation with Many Dense Features
Miloš Stanojević | Khalil Sima’an
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

pdf bib
Latent Domain Phrase-based Models for Adaptation
Hoang Cuong | Khalil Sima’an
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

pdf bib
All Fragments Count in Parser Evaluation
Jasmijn Bastings | Khalil Sima’an
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)

PARSEVAL, the default paradigm for evaluating constituency parsers, calculates parsing success (Precision/Recall) as a function of the number of matching labeled brackets across the test set. Nodes in constituency trees, however, are connected together to reflect important linguistic relations such as predicate-argument and direct-dominance relations between categories. In this paper, we present FREVAL, a generalization of PARSEVAL, where the precision and recall are calculated not only for individual brackets, but also for co-occurring, connected brackets (i.e. fragments). FREVAL fragments precision (FLP) and recall (FLR) interpolate the match across the whole spectrum of fragment sizes ranging from those consisting of individual nodes (labeled brackets) to those consisting of full parse trees. We provide evidence that FREVAL is informative for inspecting relative parser performance by comparing a range of existing parsers.

2013

pdf bib
Hierarchical Alignment Decomposition Labels for Hiero Grammar Rules
Gideon Maillette de Buy Wenniger | Khalil Sima’an
Proceedings of the Seventh Workshop on Syntax, Semantics and Structure in Statistical Translation

pdf bib
A Formal Characterization of Parsing Word Alignments by Synchronous Grammars with Empirical Evidence to the ITG Hypothesis.
Gideon Maillette de Buy Wenniger | Khalil Sima’an
Proceedings of the Seventh Workshop on Syntax, Semantics and Structure in Statistical Translation

2012

pdf bib
Adjunct Alignment in Translation Data with an Application to Phrase Based Statistical Machine Translation
Sophie Arnoult | Khalil Sima’an
Proceedings of the 16th Annual conference of the European Association for Machine Translation

2011

pdf bib
ILLC-UvA translation system for EMNLP-WMT 2011
Maxim Khalilov | Khalil Sima’an
Proceedings of the Sixth Workshop on Statistical Machine Translation

pdf bib
Learning Structural Dependencies of Words in the Zipfian Tail
Tejaswini Deoskar | Markos Mylonakis | Khalil Sima’an
Proceedings of the 12th International Conference on Parsing Technologies

pdf bib
Context-Sensitive Syntactic Source-Reordering by Statistical Transduction
Maxim Khalilov | Khalil Sima’an
Proceedings of 5th International Joint Conference on Natural Language Processing

pdf bib
Learning Hierarchical Translation Structure with Linguistic Annotations
Markos Mylonakis | Khalil Sima’an
Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies

2010

pdf bib
Source reordering using MaxEnt classifiers and supertags
Maxim Khalilov | Khalil Sima’an
Proceedings of the 14th Annual conference of the European Association for Machine Translation

pdf bib
Modeling Morphosyntactic Agreement in Constituency-Based Parsing of Modern Hebrew
Reut Tsarfaty | Khalil Sima’an
Proceedings of the NAACL HLT 2010 First Workshop on Statistical Parsing of Morphologically-Rich Languages

pdf bib
Learning Probabilistic Synchronous CFGs for Phrase-Based Translation
Markos Mylonakis | Khalil Sima’an
Proceedings of the Fourteenth Conference on Computational Natural Language Learning

pdf bib
A Discriminative Syntactic Model for Source Permutation via Tree Transduction
Maxim Khalilov | Khalil Sima’an
Proceedings of the 4th Workshop on Syntax and Structure in Statistical Translation

2009

pdf bib
An Alternative to Head-Driven Approaches for Parsing a (Relatively) Free Word-Order Language
Reut Tsarfaty | Khalil Sima’an | Remko Scha
Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing

pdf bib
A Syntactified Direct Translation Model with Linear-time Decoding
Hany Hassan | Khalil Sima’an | Andy Way
Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing

pdf bib
Lexicalized Semi-incremental Dependency Parsing
Hany Hassan | Khalil Sima’an | Andy Way
Proceedings of the International Conference RANLP-2009

pdf bib
Smoothing fine-grained PCFG lexicons
Tejaswini Deoskar | Mats Rooth | Khalil Sima’an
Proceedings of the 11th International Conference on Parsing Technologies (IWPT’09)

2008

pdf bib
Subdomain Sensitive Statistical Parsing using Raw Corpora
Barbara Plank | Khalil Sima’an
Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08)

Modern statistical parsers are trained on large annotated corpora (treebanks). These treebanks usually consist of sentences addressing different subdomains (e.g. sports, politics, music), which implies that the statistics gathered by current statistical parsers are mixtures of subdomains of language use. In this paper we present a method that exploits raw subdomain corpora gathered from the web to introduce subdomain sensitivity into a given parser. We employ statistical techniques for creating an ensemble of domain sensitive parsers, and explore methods for amalgamating their predictions. Our experiments show that introducing domain sensitivity by exploiting raw corpora can improve over a tough, state-of-the-art baseline.

pdf bib
Relational-Realizational Parsing
Reut Tsarfaty | Khalil Sima’an
Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008)

pdf bib
Phrase Translation Probabilities with ITG Priors and Smoothing as Learning Objective
Markos Mylonakis | Khalil Sima’an
Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing

2007

pdf bib
Smoothing a Lexicon-based POS Tagger for Arabic and Hebrew
Saib Manour | Khalil Sima’an | Yoad Winter
Proceedings of the 2007 Workshop on Computational Approaches to Semitic Languages: Common Issues and Resources

pdf bib
Three-Dimensional Parametrization for Parsing Morphologically Rich Languages
Reut Tsarfaty | Khalil Sima’an
Proceedings of the Tenth International Conference on Parsing Technologies

pdf bib
Supertagged Phrase-Based Statistical Machine Translation
Hany Hassan | Khalil Sima’an | Andy Way
Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics

2005

pdf bib
Choosing an Optimal Architecture for Segmentation and POS-Tagging of Modern Hebrew
Roy Bar-Haim | Khalil Sima’an | Yoad Winter
Proceedings of the ACL Workshop on Computational Approaches to Semitic Languages

2004

pdf bib
BioGrapher: Biography Questions as a Restricted Domain Question Answering Task
Oren Tsur | Maarten de Rijke | Khalil Sima’an
Proceedings of the Conference on Question Answering in Restricted Domains

2003

pdf bib
On maximizing metrics for syntactic disambiguation
Khalil Sima’an
Proceedings of the Eighth International Conference on Parsing Technologies

Given a probabilistic parsing model and an evaluation metric for scoring the match between parse-trees, e.g., PARSEVAL [Black et al., 1991], this paper addresses the problem of how to select the on average best scoring parse-tree for an input sentence. Common wisdom dictates that it is optimal to select the parse with the highest probability, regardless of the evaluation metric. In contrast, the Maximizing Metrics (MM) method [Goodman, 1998, Stolcke et al., 1997] proposes that an algorithm that optimizes the evaluation metric itself constitutes the optimal choice. We study the MM method within parsing. We observe that the MM does not always hold for tree-bank models, and that optimizing weak metrics is not interesting for semantic processing. Subsequently, we state an alternative proposition: the optimal algorithm must maximize the metric that scores parse-trees according to linguistically relevant features. We present new algorithms that optimize metrics that take into account increasingly more linguistic features, and exhibit experiments in support of our claim.

2001

pdf bib
Robust Data Oriented Parsing of Speech Utterances
Khalil Sima’an
Proceedings of the Seventh International Workshop on Parsing Technologies

2000

pdf bib
Tree-gram Parsing: Lexical Dependencies and Structural Relations
K. Sima’an
Proceedings of the 38th Annual Meeting of the Association for Computational Linguistics

1997

pdf bib
Explanation-Based Learning of Data-Oriented Parsing
K. Sima’an
CoNLL97: Computational Natural Language Learning

1996

pdf bib
Computational Complexity of Probabilistic Disambiguation by means of Tree-Grammars
Khalil Sima’an
COLING 1996 Volume 2: The 16th International Conference on Computational Linguistics