Semantic Roles for SMT: A Hybrid Two-Pass Model

We present results on a novel hybrid semantic SMT model that incorporates the strengths of both semantic role labeling and phrase-based statistical machine translation. The approach avoids major complexity limitations via a two-pass architecture. The first pass is performed using a conventional phrase-based SMT model. The second pass is performed by a re-ordering strategy guided by shallow semantic parsers that produce both semantic frame and role labels. Evaluation on a Wall Street Journal newswire genre test set showed the hybrid model to yield an improvement of roughly half a point in BLEU score over a strong pure phrase-based SMT baseline -- to our knowledge, the first successful application of semantic role labeling to SMT.

• Publication year

  2009

• Venue

  North American Chapter of the Association for Computational Linguistics

• Publication date

  2009-05-31

• Fields of study

  Computer Science

• Identifiers
  DOI 10.3115/1620853.1620858
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Learning Machine Translation

  2009cited by this paper
• A Smorgasbord of Features for Automatic MT Evaluation

  2008cited by this paper
• Tighter Integration of Rule-Based and Statistical MT in Serial System Combination

  2008cited by this paper
• Word Sense Disambiguation Improves Statistical Machine Translation

  2007cited by this paper
• Context-aware Discriminative Phrase Selection for Statistical Machine Translation

  2007cited by this paper
• Improving Statistical Machine Translation Using Word Sense Disambiguation

  2007cited by this paper
• Learning bilingual semantic frames: shallow semantic parsing vs. semantic role projection

  2007cited by this paper
• Linguistic Features for Automatic Evaluation of Heterogenous MT Systems

  2007cited by this paper
• Automatic Learning of Chinese English Semantic Structure Mapping

  2006cited by this paper
• Automatic Semantic Role Labeling for Chinese Verbs

  2005cited by this paper
• Word Sense Disambiguation vs. Statistical Machine Translation

  2005cited by this paper
• Verb Subcategorization Kernels for Automatic Semantic Labeling

  2005cited by this paper
• Support Vector Learning for Semantic Argument Classification

  2005cited by this paper
• Shallow Semantic Parsing using Support Vector Machines

  2004cited by this paper
• A Smorgasbord of Features for Statistical Machine Translation

  2004cited by this paper
• A maximum-entropy chinese parser augmented by transformation-based learning

  2004cited by this paper
• Shallow Semantic Parsing of Chinese

  2004cited by this paper
• SRILM - an extensible language modeling toolkit

  2002cited by this paper
• Bleu: a Method for Automatic Evaluation of Machine Translation

  2002influential reference
• Fast Decoding and Optimal Decoding for Machine Translation

  2001cited by this paper
• Automatic Labeling of Semantic Roles

  2000cited by this paper
• Stochastic Inversion Transduction Grammars and Bilingual Parsing of Parallel Corpora

  1997cited by this paper
• of the Association for Computational Linguistics

  year unknowncited by this paper

• Semantic Role Labelling: A Systematic Review of Approaches, Challenges, and Trends for English and Indian Languages

  2025cites this paper
• Design and Analysis of English Intelligent Translation System Based on Internet of Things and Big Data Model

  2022cites this paper
• Short Sequence Chinese-English Machine Translation Based on Generative Adversarial Networks of Emotion

  2022cites this paper
• Improving Neural Machine Translation with AMR Semantic Graphs

  2021cites this paper
• Integrating AMR to Neural Machine Translation using Graph Attention Networks

  2020cites this paper
• WikiBank: Using Wikidata to Improve Multilingual Frame-Semantic Parsing

  2020cites this paper
• On the Integration of LinguisticFeatures into Statistical and Neural Machine Translation

  2020cites this paper
• On the Integration of Linguistic Features into Statistical and Neural Machine Translation

  2020cites this paper
• Tackling Graphical NLP problems with Graph Recurrent Networks

  2019cites this paper
• Extending Neural Question Answering with Linguistic Input Features

  2019cites this paper
• Exploiting Frame-Semantics and Frame-Semantic Parsing for Automatic Extraction of Typological Information from Descriptive Grammars of Natural Languages

  2019cites this paper
• Semantic Neural Machine Translation Using AMR

  2019cites this paper
• Semantic frame based automatic extraction of typological information from descriptive grammars

  2019cites this paper
• Deep Semantic Role Labeling for Tweets using 5W1H: Who, What, When, Where, Why and How

  2019cites this paper
• the 21st Annual Conference of the European Association for Machine Translation

  2018cites this paper
• SRL for low resource languages isn’t needed for semantic SMT

  2018cites this paper
• Syntactic and semantic features for statistical and neural machine translation

  2018cites this paper
• Frame Semantics across Languages: Towards a Multilingual FrameNet

  2018cites this paper
• On internal language representations in deep learning: an analysis of machine translation and speech recognition

  2018cites this paper
• LingFN : Towards a Framenet for the Linguistics Domain

  2018cites this paper
• Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks

  2018cites this paper
• Data-driven Machine Translation using Semantic Tree Alignment

  2018cites this paper
• Deep Semantic Role Labeling with Self-Attention

  2017cites this paper
• Current Directions in English and Arabic PropBank

  2017cites this paper
• Semi-supervised Semantic Role Labeling for Brazilian Portuguese

  2017cites this paper
• Explorer Unsupervised Semantic Role Induction with Graph Partitioning

  2017cites this paper
• Constituency Parser for Hindi Noun Sequences and Role of Bracketing in Translation of English Compound Nouns into Hindi

  2017cites this paper
• Meaning preservation in Example-based Machine Translation with structural semantics

  2017cites this paper
• Text Rewriting Improves Semantic Role Labeling (Extended Abstract)

  2017cites this paper
• Hierarchical statistical semantic translation and realization

  2017cites this paper
• Integrating source-side semantic roles into a phrase-based statistical machine translation

  2017cites this paper
• Discourse Structure in Machine Translation Evaluation

  2017cites this paper
• Rewriting Improves Semantic Role Labeling ( Extended Abstract )

  2017cites this paper
• Improving semantic role labeling using high-level classification in complex networks

  2017cites this paper
• Incorporating target language semantic roles into a string-to-tree translation model

  2017cites this paper
• Manual and Automatic Paraphrases for MT Evaluation

  2016cites this paper
• Exploitation d'informations riches pour guider la traduction automatique statistique. (Complex Feature Guidance for Statistical Machine Translation)

  2016cites this paper
• The Hebrew FrameNet Project

  2016cites this paper
• Incorporating pronoun function into statistical machine translation

  2016cites this paper
• Modeling Selectional Preferences of Verbs and Nouns in String-to-Tree Machine Translation

  2016cites this paper
• Evaluating parallel corpora and translation quality for Chinese and English

  2016cites this paper
• An Exploratory Study on Process Representations

  2016cites this paper
• Computational linking theory

  2016cites this paper
• Bilingual Semantic Role Labeling Inference via Dual Decomposition

  2016cites this paper
• Improving Statistical Machine Translation with Selectional Preferences

  2016cites this paper
• Data-driven natural language generation using statistical machine translation and discriminative learning. (L'approche discriminante à la génération de la parole)

  2016cites this paper
• Analysis of Typical Annotation Problems in Bilingual Case Grammar Treebank Construction

  2015cites this paper
• Proceedings of SSST-9, Ninth Workshop on Syntax, Semantics and Structure in Statistical Translation

  2015cites this paper
• Combining Seemingly Incompatible Corpora for Implicit Semantic Role Labeling

  2015cites this paper
• (Lexical) Semantics and Statistical Machine Translation: Hopes, Advances and Challenges

  2015cites this paper
• Conceptual Annotations Preserve Structure Across Translations: A French-English Case Study

  2015cites this paper
• Proceedings of S 2 MT 2015 The 1 st Workshop on Semantics-Driven Statistical Machine Translation

  2015cites this paper
• Evaluating the Impact of Using a Domain-specific Bilingual Lexicon on the Performance of a Hybrid Machine Translation Approach

  2015cites this paper
• Leveraging Semantic Similarity in Parallel Corpora for Natural Language Processing

  2015cites this paper
• Anotação automática de papéis semânticos de textos jornalísticos e de opinião sobre árvores sintáticas não revisadas

  2015cites this paper
• Patent claim translation based on sublanguage-specific sentence structure

  2015cites this paper
• Improving Chinese-English PropBank Alignment

  2015influential citation
• How much hybridization does machine translation Need?

  2015cites this paper
• Semantics-based pretranslation for SMT using fuzzy matches

  2015cites this paper
• Comparing Representations of Semantic Roles for String-To-Tree Decoding

  2014cites this paper
• Chunk-Based Dependency-to-String Model with Japanese Case Frame

  2014cites this paper
• Bilingual Sentiment Consistency for Statistical Machine Translation

  2014cites this paper
• Translation-based ranking in cross-language information retrieval

  2014cites this paper
• A Unified Model for Soft Linguistic Reordering Constraints in Statistical Machine Translation

  2014cites this paper
• Similarity-Driven Semantic Role Induction via Graph Partitioning

  2014cites this paper
• Statistical machine translation enhancements through linguistic levels: A survey

  2014cites this paper
• Unsupervised Induction of Semantic Roles within a Reconstruction-Error Minimization Framework

  2014cites this paper
• Text Rewriting Improves Semantic Role Labeling

  2014cites this paper
• Using Discourse Structure Improves Machine Translation Evaluation

  2014cites this paper
• Using subcategorization knowledge to improve case prediction for translation to German

  2013cites this paper
• Modeling Syntactic and Semantic Structures in Hierarchical Phrase-based Translation

  2013cites this paper
• Multilingual Joint Parsing of Syntactic and Semantic Dependencies with a Latent Variable Model

  2013cites this paper
• Semantic Roles for String to Tree Machine Translation

  2013cites this paper
• Composition of semantic relations: Theoretical framework and case study

  2013cites this paper
• Name-aware Machine Translation

  2013cites this paper
• Improving machine translation by training against an automatic semantic frame based evaluation metric

  2013influential citation
• A two-step convolutional neural network approach for semantic role labeling

  2013cites this paper
• Handling Ambiguities of Bilingual Predicate-Argument Structures for Statistical Machine Translation

  2013cites this paper
• Can Informal Genres be better Translated by Tuning on Automatic Semantic Metrics?

  2013cites this paper
• Getting Past the Language Gap: Innovations in Machine Translation

  2013cites this paper
• Uma abordagem conexionista para anotação de papéis semânticos

  2013cites this paper
• Anotação automática semissupervisionada de papéis semânticos para o português do Brasil

  2013cites this paper
• Multilingual Joint Parsing of Syntactic and Semantic Dependencies with a Latent Variable Model

  2013cites this paper
• LTG vs. ITG Coverage of Cross-Lingual Verb Frame Alternations

  2012cites this paper
• Semi-Supervised Semantic Role Labeling: Approaching from an Unsupervised Perspective

  2012cites this paper
• Fine-Grained Focus for Pinpointing Positive Implicit Meaning from Negated Statements

  2012cites this paper
• *SEM 2012 Shared Task: Resolving the Scope and Focus of Negation

  2012cites this paper
• Machine Translation by Modeling Predicate-Argument Structure Transformation

  2012cites this paper
• Modeling the Translation of Predicate-Argument Structure for SMT

  2012influential citation
• Semantic Cohesion Model for Phrase-Based SMT

  2012cites this paper
• Crosslingual Induction of Semantic Roles

  2012cites this paper
• Semi-Supervised and Latent-Variable Models of Natural Language Semantics

  2012cites this paper
• A Bayesian Approach to Unsupervised Semantic Role Induction

  2012cites this paper
• Semi-Supervised Semantic Role Labeling via Structural Alignment

  2012cites this paper
• Automatic Projection of Semantic Structures: an Application to Pairwise Translation Ranking

  2011cites this paper
• Unsupervised Semantic Role Induction via Split-Merge Clustering

  2011cites this paper
• Semi-supervised Semantic Role Labeling via Graph Alignment

  2011cites this paper
• Utilizing Target-Side Semantic Role Labels to Assist Hierarchical Phrase-based Machine Translation

  2011cites this paper
• Rol semantikoen etiketatze automatikoa: rol multzoak eta hautapen murriztapenak

  2011cites this paper
• Semantic Mapping Using Automatic Word Alignment and Semantic Role Labeling

  2011influential citation