Webber, Bonnie

Lopez, Adam

Fancellu, Federico

Engineering and Physical Sciences Research Council (EPSRC)

2018-09-17T12:21:00Z

2018-09-17T12:21:00Z

2018-11-29

Negation is a common property of languages, in that there are few languages, if any, that lack means to revert the truth-value of a statement. A challenge to cross-lingual studies of negation lies in the fact that languages encode and use it in different ways. Although this variation has been extensively researched in linguistics, little has been done in automated language processing. In particular, we lack computational models of processing negation that can be generalized across language. We even lack knowledge of what the development of such models would require. These models however exist and can be built by means of existing cross-lingual resources, even when annotated data for a language other than English is not available. This thesis shows this in the context of detecting string-level negation scope, i.e. the set of tokens in a sentence whose meaning is affected by a negation marker (e.g. ‘not’). Our contribution has two parts. First, we investigate the scenario where annotated training data is available. We show that Bi-directional Long Short Term Memory (BiLSTM) networks are state-of-the-art models whose features can be generalized across language. We also show that these models suffer from genre effects and that for most of the corpora we have experimented with, high performance is simply an artifact of the annotation styles, where negation scope is often a span of text delimited by punctuation. Second, we investigate the scenario where annotated data is available in only one language, experimenting with model transfer. To test our approach, we first build NEGPAR, a parallel corpus annotated for negation, where pre-existing annotations on English sentences have been edited and extended to Chinese translations. We then show that transferring a model for negation scope detection across languages is possible by means of structured neural models where negation scope is detected on top of a cross-linguistically consistent representation, Universal Dependencies. On the other hand, we found cross-lingual lexical information only to help very little with performance. Finally, error analysis shows that performance is better when a negation marker is in the same dependency substructure as its scope and that some of the phenomena related to negation scope requiring lexical knowledge are still not captured correctly. In the conclusions, we tie up the contributions of this thesis and we point future work towards representing negation scope across languages at the level of logical form as well.

http://hdl.handle.net/1842/33038

en

The University of Edinburgh

Fancellu, F., Reddy, S., Lopez, A., and Webber, B. (2017). Universal dependencies to logical form with negation scope. In Proceedings of the Workshop Computational Semantics Beyond Events and Roles, pages 22–32.

Fancellu, F. and Webber, B. (2015). Translating Negation: A Manual Error Analysis, pages 2–11. Association for Computational Linguistics.

Fancellu, F. and Webber, B. L. (2014). Applying the semantics of negation to SMT through n-best list re-ranking. In Bouma, G. and Parmentier, Y., editors, EACL, pages 598–606. The Association for Computer Linguistics.

cross-lingual studies

negation

automated language processing

Bi-directional Long Short Term Memory networks

BiLSTM networks

NEGPAR

structured neural models

Computational models for multilingual negation scope detection

Thesis or Dissertation

Doctoral

PhD Doctor of Philosophy