1 |
Unsupervised Morphological Segmentation and Part-of-Speech Tagging for Low-Resource Scenarios
|
|
|
|
Abstract:
With the high cost of manually labeling data and the increasing interest in low-resource languages, for which human annotators might not be even available, unsupervised approaches have become essential for processing a typologically diverse set of languages, whether high-resource or low-resource. In this work, we propose new fully unsupervised approaches for two tasks in morphology: unsupervised morphological segmentation and unsupervised cross-lingual part-of-speech (POS) tagging, which have been two essential subtasks for several downstream NLP applications, such as machine translation, speech recognition, information extraction and question answering. We propose a new unsupervised morphological-segmentation approach that utilizes Adaptor Grammars (AGs), nonparametric Bayesian models that generalize probabilistic context-free grammars (PCFGs), where a PCFG models word structure in the task of morphological segmentation. We implement the approach as a publicly available morphological-segmentation framework, MorphAGram, that enables unsupervised morphological segmentation through the use of several proposed language-independent grammars. In addition, the framework allows for the use of scholar knowledge, when available, in the form of affixes that can be seeded into the grammars. The framework handles the cases when the scholar-seeded knowledge is either generated from language resources, possibly by someone who does not know the language, as weak linguistic priors, or generated by an expert in the underlying language as strong linguistic priors. Another form of linguistic priors is the design of a grammar that models language-dependent specifications. We also propose a fully unsupervised learning setting that approximates the effect of scholar-seeded knowledge through self-training. Moreover, since there is no single grammar that works best across all languages, we propose an approach that picks a nearly optimal configuration (a learning setting and a grammar) for an unseen language, a language that is not part of the development. Finally, we examine multilingual learning for unsupervised morphological segmentation in low-resource setups. For unsupervised POS tagging, two cross-lingual approaches have been widely adapted: 1) annotation projection, where POS annotations are projected across an aligned parallel text from a source language for which a POS tagger is accessible to the target one prior to training a POS model; and 2) zero-shot model transfer, where a model of a source language is directly applied on texts in the target language. We propose an end-to-end architecture for unsupervised cross-lingual POS tagging via annotation projection in truly low-resource scenarios that do not assume access to parallel corpora that are large in size or represent a specific domain. We integrate and expand the best practices in alignment and projection and design a rich neural architecture that exploits non-contextualized and transformer-based contextualized word embeddings, affix embeddings and word-cluster embeddings. Additionally, since parallel data might be available between the target language and multiple source ones, as in the case of the Bible, we propose different approaches for learning from multiple sources. Finally, we combine our work on unsupervised morphological segmentation and unsupervised cross-lingual POS tagging by conducting unsupervised stem-based cross-lingual POS tagging via annotation projection, which relies on the stem as the core unit of abstraction for alignment and projection, which is beneficial to low-resource morphologically complex languages. We also examine morpheme-based alignment and projection, the use of linguistic priors towards better POS models and the use of segmentation information as learning features in the neural architecture. We conduct comprehensive evaluation and analysis to assess the performance of our approaches of unsupervised morphological segmentation and unsupervised POS tagging and show that they achieve the state-of-the-art performance for the two morphology tasks when evaluated on a large set of languages of different typologies: analytic, fusional, agglutinative and synthetic/polysynthetic.
|
|
Keyword:
Automatic speech recognition--Computer programs; Computer science; Machine translating; Question-answering systems; Speech processing systems--Computer programs
|
|
URL: https://doi.org/10.7916/d8-jd2d-9p51
|
|
BASE
|
|
Hide details
|
|
2 |
Hate speech and offensive language detection using transfer learning approaches ; Détection du discours de haine et du langage offensant utilisant des approches de Transfer Learning
|
|
|
|
In: https://tel.archives-ouvertes.fr/tel-03276023 ; Document and Text Processing. Institut Polytechnique de Paris, 2021. English. ⟨NNT : 2021IPPAS007⟩ (2021)
|
|
BASE
|
|
Show details
|
|
3 |
Time-locked Cortical Processing of Speech in Complex Environments ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Unsupervised Morphological Segmentation and Part-of-Speech Tagging for Low-Resource Scenarios ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Discriminative feature modeling for statistical speech recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Parlez-vous le hate?: Examining topics and hate speech in the alternative social network Parler
|
|
|
|
BASE
|
|
Show details
|
|
7 |
ASR and Human Recognition Errors: Predictability and Lexical Factors
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Marqueurs discursifs de neurodégénérescence liée à la pathologie Alzheimer
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Time-locked Cortical Processing of Speech in Complex Environments
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Crowdsourcing linguistic resources for natural non-standardised languages processing ; Myriadisation de ressources linguistiques pour le traitement automatique de langues non standardisées
|
|
|
|
In: https://hal.archives-ouvertes.fr/tel-03083213 ; Informatique et langage [cs.CL]. Sorbonne Universite, 2020. Français (2020)
|
|
BASE
|
|
Show details
|
|
11 |
Parkinson's desease detection by multimodal analysis combining handwriting and speech signals ; Détection de la maladie de Parkinson par analyse multimodale combinant signaux d’écriture et de parole
|
|
|
|
In: https://tel.archives-ouvertes.fr/tel-03594895 ; Signal and Image Processing. Institut Polytechnique de Paris, 2020. English. ⟨NNT : 2020IPPAT039⟩ (2020)
|
|
BASE
|
|
Show details
|
|
12 |
Comment parle un robot ? ; Comment parle un robot ?: Les machines à langage dans la science-fiction
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-02548113 ; Le Bélial', 2020, Collection Parallaxe, 978-2-84344-965-9 ; https://www.belial.fr/ (2020)
|
|
BASE
|
|
Show details
|
|
13 |
The Effects of Prediction and Speech Rate on Lexical Processing ...
|
|
Cole, Alissa. - : Digital Repository at the University of Maryland, 2020
|
|
BASE
|
|
Show details
|
|
14 |
Analysis of Speech Parameters as Indicators of Engagement in Conversation
|
|
ELIAS, CHRISTY. - : Trinity College Dublin. School of Computer Science & Statistics. Discipline of Computer Science, 2020
|
|
BASE
|
|
Show details
|
|
15 |
Uncovering the effects of semantic context on the cortical processing of continuous speech using computational models of language
|
|
BRODERICK, MICHAEL. - : Trinity College Dublin. School of Engineering. Discipline of Electronic & Elect. Engineering, 2020
|
|
BASE
|
|
Show details
|
|
16 |
Investigating the Neural Correlates of Speech Processing & Selective Auditory Attention using EEG
|
|
TEOH, EMILY SIEW. - : Trinity College Dublin. School of Engineering. Discipline of Electronic & Elect. Engineering, 2020
|
|
BASE
|
|
Show details
|
|
18 |
Robust Methods for the Automatic Quantification and Prediction of Affect in Spoken Interactions
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Neural Correlates of Phonetic and Lexical Processing in Children with and without Speech Sound Disorder
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Processamento de fala para triagem de distúrbios fonológicos ; Speech processing for screening off phonological disorders
|
|
Yoshimura, Guilherme Jun. - : Biblioteca Digital de Teses e Dissertações da USP, 2020. : Universidade de São Paulo, 2020. : Instituto de Matemática e Estatística, 2020
|
|
BASE
|
|
Show details
|
|
|
|