Search Results for author:
Found 25 papers, 6 papers with code
The University of Edinburgh’s English-Tamil and English-Inuktitut Submissions to the WMT20 News Translation Task
We describe the University of Edinburgh’s submissions to the WMT20 news translation shared task for the low resource language pair English-Tamil and the mid-resource language pair English-Inuktitut.
SIGMORPHON 2021 Shared Task on Morphological Reinflection: Generalization Across Languages
This year's iteration of the SIGMORPHON Shared Task on morphological reinflection focuses on typological diversity and cross-lingual variation of morphosyntactic features.
Representation of Yine [Arawak] Morphology by Finite State Transducer Formalism
We represent the complexity of Yine (Arawak) morphology with a finite state transducer (FST) based morphological analyzer.
Peru is Multilingual, Its Machine Translation Should Be Too?
Peru is a multilingual country with a long history of contact between the indigenous languages and Spanish.
Findings of the AmericasNLP 2021 Shared Task on Open Machine Translation for Indigenous Languages of the Americas
This paper presents the results of the 2021 Shared Task on Open Machine Translation for Indigenous Languages of the Americas.
CLD² Language Documentation Meets Natural Language Processing for Revitalising Endangered Languages
Language revitalisation should not be understood as a direct outcome of language documentation, which is mainly focused on the creation of language repositories.
Meeting the Needs of Low-Resource Languages: The Value of Automatic Alignments via Pretrained Models
However, the languages most in need of automatic alignment are low-resource and, thus, not typically included in the pretraining data.
Revisiting Syllables in Language Modelling and their Application on Low-Resource Machine Translation
Moreover, we study the importance of syllables on neural machine translation for a non-related and low-resource language-pair (Spanish--Shipibo-Konibo).
Building an Endangered Language Resource in the Classroom: Universal Dependencies for Kakataibo
In this paper, we launch a new Universal Dependencies treebank for an endangered language from Amazonia: Kakataibo, a Panoan language spoken in Peru.
UniMorph 4.0: Universal Morphology
The project comprises two major thrusts: a language-independent feature schema for rich morphological annotation and a type-level resource of annotated data in diverse languages realizing that schema.
Quantifying Synthesis and Fusion and their Impact on Machine Translation
In this work, we propose to reduce the rigidity of such claims, by quantifying morphological typology at the word and segment level.
BPE vs. Morphological Segmentation: A Case Study on Machine Translation of Four Polysynthetic Languages
Morphologically-rich polysynthetic languages present a challenge for NLP systems due to data sparsity, and a common strategy to handle this issue is to apply subword segmentation.
AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages
Continued pretraining offers improvements, with an average accuracy of 44. 05%.
Revisiting Neural Language Modelling with Syllables
Language modelling is regularly analysed at word, subword or character units, but syllables are seldom used.
Monolingual corpus creation and evaluation of truly low-resource languages from Peru
We introduce new monolingual corpora for four indigenous and endangered languages from Peru: Shipibo-konibo, Ashaninka, Yanesha and Yine.
Efficient strategies for hierarchical text classification: External knowledge and auxiliary tasks
We use the class-definition embeddings as an additional input to condition the prediction of the next layer and in an adapted beam search.
No Data to Crawl? Monolingual Corpus Creation from PDF Files of Truly low-Resource Languages in Peru
We introduce new monolingual corpora for four indigenous and endangered languages from Peru: Shipibo-konibo, Ashaninka, Yanesha and Yine.
Bridging Linguistic Typology and Multilingual Machine Translation with Multi-View Language Representations
Sparse language vectors from linguistic typology databases and learned embeddings from tasks like multilingual machine translation have been investigated in isolation, without analysing how they could benefit from each other's language characterisation.
CSI Peru News: finding the culprit, victim and location in news articles
We introduce a shift on the DS method over the domain of crime-related news from Peru, attempting to find the culprit, victim and location of a crime description from a RE perspective.
Assessing Back-Translation as a Corpus Generation Strategy for non-English Tasks: A Study in Reading Comprehension and Word Sense Disambiguation
Corpora curated by experts have sustained Natural Language Processing mainly in English, but the expensiveness of corpora creation is a barrier for the development in further languages.
Toward Universal Dependencies for Shipibo-Konibo
We present an initial version of the Universal Dependencies (UD) treebank for Shipibo-Konibo, the first South American, Amazonian, Panoan and Peruvian language with a resource built under UD.
Corpus Creation and Initial SMT Experiments between Spanish and Shipibo-konibo
In this paper, we present the first attempts to develop a machine translation (MT) system between Spanish and Shipibo-konibo (es-shp).
Spell-Checking based on Syllabification and Character-level Graphs for a Peruvian Agglutinative Language
In this way, this spelling corrector is being developed based on two steps: an automatic rule-based syllabification method and a character-level graph to detect the degree of error in a misspelled word.
