Search Results for author:
Found 54 papers, 11 papers with code
One Wug, Two Wug+s Transformer Inflection Models Hallucinate Affixes
Data augmentation strategies are increasingly important in NLP pipelines for low-resourced and endangered languages, and in neural morphological inflection, augmentation by so called data hallucination is a popular technique.
Dim Wihl Gat Tun: The Case for Linguistic Expertise in NLP for Under-Documented Languages
With this paper, we make the case that IGT data can be leveraged successfully provided that target language expertise is available.
Penalizing Divergence: Multi-Parallel Translation for Low-Resource Languages of North America
Experiments on very low-resourced Indigenous North American languages show that an initially deficient multilingual translator can improve by 4. 9 BLEU through mBART pre-training, and 5. 5 BLEU points with the strategic addition of monolingual data, and that a divergence penalty leads to further increases of 0. 4 BLEU.
Morphological Processing of Low-Resource Languages: Where We Are and What’s Next
Automatic morphological processing can aid downstream natural language processing applications, especially for low-resource languages, and assist language documentation efforts for endangered languages.
Ensembles of Neural Morphological Inflection Models
We investigate different ensemble learning techniques for neural morphological inflection using bidirectional LSTM encoder-decoder models with attention.
Linguistically-Motivated Yorùbá-English Machine Translation
In this work, we perform fine-grained analysis on how an SMT system compares with two NMT systems (BiLSTM and Transformer) when translating bare nouns in Yorùbá into English.
Generalizing Morphological Inflection Systems to Unseen Lemmas
This paper presents experiments on morphological inflection using data from the SIGMORPHON-UniMorph 2022 Shared Task 0: Generalization and Typologically Diverse Morphological Inflection.
An FST morphological analyzer for the Gitksan language
This paper presents a finite-state morphological analyzer for the Gitksan language.
Unsupervised Paradigm Clustering Using Transformation Rules
Secondly, we experiment with more general rules which can apply transformations inside the input strings in addition to prefix and suffix transformations.
Findings of the SIGMORPHON 2021 Shared Task on Unsupervised Morphological Paradigm Clustering
We describe the second SIGMORPHON shared task on unsupervised morphology: the goal of the SIGMORPHON 2021 Shared Task on Unsupervised Morphological Paradigm Clustering is to cluster word types from a raw text corpus into paradigms.
An Inflectional Database for Gitksan
We use Gitksan data in interlinear glossed format, stemming from language documentation efforts, to build a database of partial inflection tables.
Multiple Sources are Better Than One: Incorporating External Knowledge in Low-Resource Glossing
In this paper, we address the data scarcity problem in automatic data-driven glossing for low-resource languages by coordinating multiple sources of linguistic expertise.
Embedded Translations for Low-resource Automated Glossing
Aided by these enhancements, our model demonstrates an average improvement of 3. 97\%-points over the previous state of the art on datasets from the SIGMORPHON 2023 Shared Task on Interlinear Glossing.
An Investigation of Noise in Morphological Inflection
We aim at closing this gap by investigating the types of noise encountered within a pipeline for truly unsupervised morphological paradigm completion and its impact on morphological inflection systems: First, we propose an error taxonomy and annotation pipeline for inflection training data.
Understanding Compositional Data Augmentation in Typologically Diverse Morphological Inflection
In this study, we aim to shed light on the theoretical aspects of the prominent data augmentation strategy StemCorrupt (Silfverberg et al., 2017; Anastasopoulos and Neubig, 2019), a method that generates synthetic examples by randomly substituting stem characters in gold standard training examples.
Yet Another Format of Universal Dependencies for Korean
In this study, we propose a morpheme-based scheme for Korean dependency parsing and adopt the proposed scheme to Universal Dependencies.
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.
Dim Wihl Gat Tun: The Case for Linguistic Expertise in NLP for Underdocumented Languages
With this paper, we make the case that IGT data can be leveraged successfully provided that target language expertise is available.
Morphological Processing of Low-Resource Languages: Where We Are and What's Next
Automatic morphological processing can aid downstream natural language processing applications, especially for low-resource languages, and assist language documentation efforts for endangered languages.
Do RNN States Encode Abstract Phonological Alternations?
Sequence-to-sequence models have delivered impressive results in word formation tasks such as morphological inflection, often learning to model subtle morphophonological details with limited training data.
Do RNN States Encode Abstract Phonological Processes?
Sequence-to-sequence models have delivered impressive results in word formation tasks such as morphological inflection, often learning to model subtle morphophonological details with limited training data.
Translating the Unseen? Yoruba-English MT in Low-Resource, Morphologically-Unmarked Settings
In this work, we perform fine-grained analysis on how an SMT system compares with two NMT systems (BiLSTM and Transformer) when translating bare nouns in Yor\`ub\'a into English.
Noise Isn't Always Negative: Countering Exposure Bias in Sequence-to-Sequence Inflection Models
Morphological inflection, like many sequence-to-sequence tasks, sees great performance from recurrent neural architectures when data is plentiful, but performance falls off sharply in lower-data settings.
One Model to Pronounce Them All: Multilingual Grapheme-to-Phoneme Conversion With a Transformer Ensemble
The task of grapheme-to-phoneme (G2P) conversion is important for both speech recognition and synthesis.
SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection
Systems were developed using data from 45 languages and just 5 language families, fine-tuned with data from an additional 45 languages and 10 language families (13 in total), and evaluated on all 90 languages.
UniMorph 3.0: 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.
Automated Phonological Transcription of Akkadian Cuneiform Text
Several Akkadian text corpora contain only the transliterated text.
BabyFST - Towards a Finite-State Based Computational Model of Ancient Babylonian
Akkadian is a fairly well resourced extinct language that does not yet have a comprehensive morphological analyzer available.
Weird Inflects but OK: Making Sense of Morphological Generation Errors
We conduct a manual error analysis of the CoNLL-SIGMORPHON Shared Task on Morphological Reinflection.
The SIGMORPHON 2019 Shared Task: Morphological Analysis in Context and Cross-Lingual Transfer for Inflection
The SIGMORPHON 2019 shared task on cross-lingual transfer and contextual analysis in morphology examined transfer learning of inflection between 100 language pairs, as well as contextual lemmatization and morphosyntactic description in 66 languages.
A Finnish News Corpus for Named Entity Recognition
We present a corpus of Finnish news articles with a manually prepared named entity annotation.
A Report on the Third VarDial Evaluation Campaign
In this paper, we present the findings of the Third VarDial Evaluation Campaign organized as part of the sixth edition of the workshop on Natural Language Processing (NLP) for Similar Languages, Varieties and Dialects (VarDial), co-located with NAACL 2019.
The CoNLL--SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection
Apart from extending the number of languages involved in earlier supervised tasks of generating inflected forms, this year the shared task also featured a new second task which asked participants to inflect words in sentential context, similar to a cloze task.
Marrying Universal Dependencies and Universal Morphology
The Universal Dependencies (UD) and Universal Morphology (UniMorph) projects each present schemata for annotating the morphosyntactic details of language.
Phonological Features for Morphological Inflection
Modeling morphological inflection is an important task in Natural Language Processing.
Sub-label dependencies for Neural Morphological Tagging -- The Joint Submission of University of Colorado and University of Helsinki for VarDial 2018
This paper presents the submission of the UH{\&}CU team (Joint University of Colorado and University of Helsinki team) for the VarDial 2018 shared task on morphosyntactic tagging of Croatian, Slovenian and Serbian tweets.
A Computational Model for the Linguistic Notion of Morphological Paradigm
In supervised learning of morphological patterns, the strategy of generalizing inflectional tables into more abstract paradigms through alignment of the longest common subsequence found in an inflection table has been proposed as an efficient method to deduce the inflectional behavior of unseen word forms.
Weakly supervised learning of allomorphy
Most NLP resources that offer annotations at the word segment level provide morphological annotation that includes features indicating tense, aspect, modality, gender, case, and other inflectional information.
Heuristic Hyper-minimization of Finite State Lexicons
The most noticeable reduction in size we got with a morphological transducer for Greenlandic, whose original size is on average about 15 times larger than other morphologies.
