A Morphology-Based Investigation of Positional Encodings
- URL: http://arxiv.org/abs/2404.04530v2
- Date: Thu, 30 May 2024 14:44:10 GMT
- Title: A Morphology-Based Investigation of Positional Encodings
- Authors: Poulami Ghosh, Shikhar Vashishth, Raj Dabre, Pushpak Bhattacharyya,
- Abstract summary: Morphology and word order are closely linked, with the latter incorporated into transformer-based models through positional encodings.
This prompts a fundamental inquiry: Is there a correlation between the morphological complexity of a language and the utilization of positional encoding in pre-trained language models?
In pursuit of an answer, we present the first study addressing this question, encompassing 22 languages and 5 downstream tasks.
- Score: 46.667985003225496
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: Contemporary deep learning models effectively handle languages with diverse morphology despite not being directly integrated into them. Morphology and word order are closely linked, with the latter incorporated into transformer-based models through positional encodings. This prompts a fundamental inquiry: Is there a correlation between the morphological complexity of a language and the utilization of positional encoding in pre-trained language models? In pursuit of an answer, we present the first study addressing this question, encompassing 22 languages and 5 downstream tasks. Our findings reveal that the importance of positional encoding diminishes with increasing morphological complexity in languages. Our study motivates the need for a deeper understanding of positional encoding, augmenting them to better reflect the different languages under consideration.
Related papers
- On the Role of Morphological Information for Contextual Lemmatization [7.106986689736827]
We investigate the role of morphological information to develop contextual lemmatizers in six languages.
Basque, Turkish, Russian, Czech, Spanish and English.
Experiments suggest that the best lemmatizers out-of-domain are those using simple UPOS tags or those trained without morphology.
arXiv Detail & Related papers (2023-02-01T12:47:09Z) - UniMorph 4.0: Universal Morphology [104.69846084893298]
This paper presents the expansions and improvements made on several fronts over the last couple of years.
Collaborative efforts by numerous linguists have added 67 new languages, including 30 endangered languages.
In light of the last UniMorph release, we also augmented the database with morpheme segmentation for 16 languages.
arXiv Detail & Related papers (2022-05-07T09:19:02Z) - Modeling Target-Side Morphology in Neural Machine Translation: A
Comparison of Strategies [72.56158036639707]
Morphologically rich languages pose difficulties to machine translation.
A large amount of differently inflected word surface forms entails a larger vocabulary.
Some inflected forms of infrequent terms typically do not appear in the training corpus.
Linguistic agreement requires the system to correctly match the grammatical categories between inflected word forms in the output sentence.
arXiv Detail & Related papers (2022-03-25T10:13:20Z) - Morphological Processing of Low-Resource Languages: Where We Are and
What's Next [23.7371787793763]
We focus on approaches suitable for languages with minimal or no annotated resources.
We argue that the field is ready to tackle the logical next challenge: understanding a language's morphology from raw text alone.
arXiv Detail & Related papers (2022-03-16T19:47:04Z) - Morphology Without Borders: Clause-Level Morphological Annotation [8.559428282730021]
We propose to view morphology as a clause-level phenomenon, rather than word-level.
We deliver a novel dataset for clause-level morphology covering 4 typologically-different languages: English, German, Turkish and Hebrew.
Our experiments show that the clause-level tasks are substantially harder than the respective word-level tasks, while having comparable complexity across languages.
arXiv Detail & Related papers (2022-02-25T17:20:28Z) - The Impact of Positional Encodings on Multilingual Compression [3.454503173118508]
Several modifications have been proposed over the sinusoidal positional encodings used in the original transformer architecture.
We first show that surprisingly, while these modifications tend to improve monolingual language models, none of them result in better multilingual language models.
arXiv Detail & Related papers (2021-09-11T23:22:50Z) - Bridging Linguistic Typology and Multilingual Machine Translation with
Multi-View Language Representations [83.27475281544868]
We use singular vector canonical correlation analysis to study what kind of information is induced from each source.
We observe that our representations embed typology and strengthen correlations with language relationships.
We then take advantage of our multi-view language vector space for multilingual machine translation, where we achieve competitive overall translation accuracy.
arXiv Detail & Related papers (2020-04-30T16:25:39Z) - A Simple Joint Model for Improved Contextual Neural Lemmatization [60.802451210656805]
We present a simple joint neural model for lemmatization and morphological tagging that achieves state-of-the-art results on 20 languages.
Our paper describes the model in addition to training and decoding procedures.
arXiv Detail & Related papers (2019-04-04T02:03:19Z) - Cross-lingual, Character-Level Neural Morphological Tagging [57.0020906265213]
We train character-level recurrent neural taggers to predict morphological taggings for high-resource languages and low-resource languages together.
Learning joint character representations among multiple related languages successfully enables knowledge transfer from the high-resource languages to the low-resource ones, improving accuracy by up to 30% over a monolingual model.
arXiv Detail & Related papers (2017-08-30T08:14:34Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.