Summary of the paper
| Title | Inferring Syntactic Rules for Word Alignment through Inductive Logic Programming |
|---|---|
| Authors | Sylwia Ozdowska and Vincent Claveau |
| Abstract | This paper presents and evaluates an original approach to automatically alignbitexts at the word level. It relies on a syntactic dependency analysis of thesource and target texts and is based on a machine-learning technique, namelyinductive logic programming (ILP).We show that ILP is particularly well suited for this task in which the datacan only be expressed by (translational and syntactic) relations. It allows usto infer easily rules called syntactic alignment rules. These rules make themost of the syntactic information to align words. A simple bootstrapping technique provides the examples needed by ILP, makingthis machine learning approach entirely automatic. Moreover, through different experiments, we show that this approach requires avery small amount of training data, and its performance rivals some of the bestexisting alignment systems. Furthermore, cases of syntactic isomorphisms or non-isomorphisms between thesource language and the target language are easily identified through theinferred rules. |
| Language | Grammar and Syntax |
| Topics | Statistical and machine learning methods, Machine Translation, SpeechToSpeech Translation, Grammar and Syntax |
Full paper  |
Inferring Syntactic Rules for Word Alignment through Inductive Logic Programming |
| Bibtex | @InProceedings{OZDOWSKA10.878, author = {Sylwia Ozdowska and Vincent Claveau}, title = {Inferring Syntactic Rules for Word Alignment through Inductive Logic Programming}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |