Morphologically Rich Languages (MRLs) such as Arabic, Hebrew and Turkish often require Morphological Disambiguation (MD), i.e., the prediction of the correct morphological decomposition of tokens into morphemes, early in the pipeline. Neural MD may be addressed as a simple pipeline, where segmentation is followed by sequence tagging, or as an end-to-end model, predicting morphemes from raw tokens. Both approaches are suboptimal; the former is heavily prone to error propagation, and the latter does not enjoy explicit access to the basic processing units called morphemes. This paper offers an MD architecture that combines the symbolic knowledge of morphemes with the learning capacity of neural end-to-end modeling. We propose a new, general and easy-to-implement Pointer Network model where the input is a morphological lattice and the output is a sequence of indices pointing at a single disambiguated path of morphemes. We demonstrate the efficacy of the model on segmentation and tagging, for Hebrew and Turkish texts, based on their respective Universal Dependencies (UD) treebanks. Our experiments show that with complete lattices, our model outperforms all shared-task results on segmenting and tagging these languages. On the SPMRL treebank, our model outperforms all previously reported results for Hebrew MD in realistic scenarios.
|Title of host publication||Findings of the Association for Computational Linguistics Findings of ACL|
|Subtitle of host publication||EMNLP 2020|
|Publisher||Association for Computational Linguistics (ACL)|
|Number of pages||11|
|State||Published - 2020|
|Event||Findings of the Association for Computational Linguistics, ACL 2020: EMNLP 2020 - Virtual, Online|
Duration: 16 Nov 2020 → 20 Nov 2020
|Name||Findings of the Association for Computational Linguistics Findings of ACL: EMNLP 2020|
|Conference||Findings of the Association for Computational Linguistics, ACL 2020: EMNLP 2020|
|Period||16/11/20 → 20/11/20|
Bibliographical noteFunding Information:
We thank the BIU-NLP lab members for comments and discussion, and to four anonymous reviewers for their insightful remarks. This research is funded by grants from the Israeli Science Foundation (ISF grant 1739/26) and the European Research Council (ERC grant 677352), for which we are grateful.
© 2020 Association for Computational Linguistics