Pub Date : 1900-01-01DOI: 10.18653/v1/2023.sigmorphon-1.22
Taiqi He, Lindia Tjuatja, Nathaniel R. Robinson, Shinji Watanabe, David R. Mortensen, Graham Neubig, L. Levin
In our submission to the SIGMORPHON 2023 Shared Task on interlinear glossing (IGT), we explore approaches to data augmentation and modeling across seven low-resource languages. For data augmentation, we explore two approaches: creating artificial data from the provided training data and utilizing existing IGT resources in other languages. On the modeling side, we test an enhanced version of the provided token classification baseline as well as a pretrained multilingual seq2seq model. Additionally, we apply post-correction using a dictionary for Gitksan, the language with the smallest amount of data. We find that our token classification models are the best performing, with the highest word-level accuracy for Arapaho and highest morpheme-level accuracy for Gitksan out of all submissions. We also show that data augmentation is an effective strategy, though applying artificial data pretraining has very different effects across both models tested.
{"title":"SigMoreFun Submission to the SIGMORPHON Shared Task on Interlinear Glossing","authors":"Taiqi He, Lindia Tjuatja, Nathaniel R. Robinson, Shinji Watanabe, David R. Mortensen, Graham Neubig, L. Levin","doi":"10.18653/v1/2023.sigmorphon-1.22","DOIUrl":"https://doi.org/10.18653/v1/2023.sigmorphon-1.22","url":null,"abstract":"In our submission to the SIGMORPHON 2023 Shared Task on interlinear glossing (IGT), we explore approaches to data augmentation and modeling across seven low-resource languages. For data augmentation, we explore two approaches: creating artificial data from the provided training data and utilizing existing IGT resources in other languages. On the modeling side, we test an enhanced version of the provided token classification baseline as well as a pretrained multilingual seq2seq model. Additionally, we apply post-correction using a dictionary for Gitksan, the language with the smallest amount of data. We find that our token classification models are the best performing, with the highest word-level accuracy for Arapaho and highest morpheme-level accuracy for Gitksan out of all submissions. We also show that data augmentation is an effective strategy, though applying artificial data pretraining has very different effects across both models tested.","PeriodicalId":186158,"journal":{"name":"Special Interest Group on Computational Morphology and Phonology Workshop","volume":"69 21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124932351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.18653/v1/2023.sigmorphon-1.30
Chu-Cheng Lin
We propose a universal grapheme-phoneme transduction model using neuralized finite-state transducers. Many computational models of grapheme-phoneme transduction nowadays are based on the (autoregressive) sequence-to-sequence string transduction paradigm. While such models have achieved state-of-the-art performance, they suffer from theoretical limitations of autoregressive models. On the other hand, neuralized finite-state transducers (NFSTs) have shown promising results on various string transduction tasks. NFSTs can be seen as a generalization of weighted finite-state transducers (WFSTs), and can be seen as pairs of a featurized finite-state machine (‘marked finite-state transducer’ or MFST in NFST terminology), and a string scoring function. Instead of taking a product of local contextual feature weights on FST arcs, NFSTs can employ arbitrary scoring functions to weight global contextual features of a string transduction, and therefore break the Markov property. Furthermore, NFSTs can be formally shown to be more expressive than (autoregressive) seq2seq models. Empirically, joint grapheme-phoneme transduction NFSTs have consistently outperformed vanilla seq2seq models on grapheme-tophoneme and phoneme-to-grapheme transduction tasks for English. Furthermore, they provide interpretable aligned string transductions, thanks to their finite-state machine component. In this talk, we propose a multilingual extension of the joint grapheme-phoneme NFST. We achieve this goal by modeling typological and phylogenetic features of languages and scripts as optional latent variables using a finite-state machine. The result is a versatile graphemephoneme transduction model: in addition to standard monolingual and multilingual transduction, the proposed multilingual NFST can also be used in various controlled generation scenarios, such as phoneme-to-grapheme transduction of an unseen language-script pair. We also plan to release an NFST software package.
{"title":"A future for universal grapheme-phoneme transduction modeling with neuralized finite-state transducers","authors":"Chu-Cheng Lin","doi":"10.18653/v1/2023.sigmorphon-1.30","DOIUrl":"https://doi.org/10.18653/v1/2023.sigmorphon-1.30","url":null,"abstract":"We propose a universal grapheme-phoneme transduction model using neuralized finite-state transducers. Many computational models of grapheme-phoneme transduction nowadays are based on the (autoregressive) sequence-to-sequence string transduction paradigm. While such models have achieved state-of-the-art performance, they suffer from theoretical limitations of autoregressive models. On the other hand, neuralized finite-state transducers (NFSTs) have shown promising results on various string transduction tasks. NFSTs can be seen as a generalization of weighted finite-state transducers (WFSTs), and can be seen as pairs of a featurized finite-state machine (‘marked finite-state transducer’ or MFST in NFST terminology), and a string scoring function. Instead of taking a product of local contextual feature weights on FST arcs, NFSTs can employ arbitrary scoring functions to weight global contextual features of a string transduction, and therefore break the Markov property. Furthermore, NFSTs can be formally shown to be more expressive than (autoregressive) seq2seq models. Empirically, joint grapheme-phoneme transduction NFSTs have consistently outperformed vanilla seq2seq models on grapheme-tophoneme and phoneme-to-grapheme transduction tasks for English. Furthermore, they provide interpretable aligned string transductions, thanks to their finite-state machine component. In this talk, we propose a multilingual extension of the joint grapheme-phoneme NFST. We achieve this goal by modeling typological and phylogenetic features of languages and scripts as optional latent variables using a finite-state machine. The result is a versatile graphemephoneme transduction model: in addition to standard monolingual and multilingual transduction, the proposed multilingual NFST can also be used in various controlled generation scenarios, such as phoneme-to-grapheme transduction of an unseen language-script pair. We also plan to release an NFST software package.","PeriodicalId":186158,"journal":{"name":"Special Interest Group on Computational Morphology and Phonology Workshop","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115612345","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents several different neural subword modelling based approaches to interlinear glossing for seven under-resourced languages as a part of the 2023 SIGMORPHON shared task on interlinear glossing. We experiment with various augmentation and tokenization strategies for both the open and closed tracks of data. We found that while byte-level models may perform well for greater amounts of data, character based approaches remain competitive in their performance in lower resource settings.
{"title":"Glossy Bytes: Neural Glossing using Subword Encoding","authors":"Ziggy Cross, Michelle Yun, Ananya Apparaju, Jata MacCabe, Garrett Nicolai, Miikka Silfverberg","doi":"10.18653/v1/2023.sigmorphon-1.24","DOIUrl":"https://doi.org/10.18653/v1/2023.sigmorphon-1.24","url":null,"abstract":"This paper presents several different neural subword modelling based approaches to interlinear glossing for seven under-resourced languages as a part of the 2023 SIGMORPHON shared task on interlinear glossing. We experiment with various augmentation and tokenization strategies for both the open and closed tracks of data. We found that while byte-level models may perform well for greater amounts of data, character based approaches remain competitive in their performance in lower resource settings.","PeriodicalId":186158,"journal":{"name":"Special Interest Group on Computational Morphology and Phonology Workshop","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130881352","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.18653/v1/2023.sigmorphon-1.6
Margot Masson, Julie Carson-Berndsen
While the deep learning revolution has led to significant performance improvements in speech recognition, accented speech remains a challenge. Current approaches to this challenge typically do not seek to understand and provide explanations for the variations of accented speech, whether they stem from native regional variation or non-native error patterns. This paper seeks to address non-native speaker variations from both a knowledge-based and a data-driven perspective. We propose to approximate non-native accented-speech pronunciation patterns by the means of two approaches: based on phonetic and phonological knowledge on the one hand and inferred from a text-to-speech system on the other. Artificial speech is then generated with a range of variants which have been captured in confusion matrices representing phoneme similarities. We then show that non-native accent confusions actually propagate to the transcription from the ASR, thus suggesting that the inference of accent specific phoneme confusions is achievable from artificial speech.
{"title":"Investigating Phoneme Similarity with Artificially Accented Speech","authors":"Margot Masson, Julie Carson-Berndsen","doi":"10.18653/v1/2023.sigmorphon-1.6","DOIUrl":"https://doi.org/10.18653/v1/2023.sigmorphon-1.6","url":null,"abstract":"While the deep learning revolution has led to significant performance improvements in speech recognition, accented speech remains a challenge. Current approaches to this challenge typically do not seek to understand and provide explanations for the variations of accented speech, whether they stem from native regional variation or non-native error patterns. This paper seeks to address non-native speaker variations from both a knowledge-based and a data-driven perspective. We propose to approximate non-native accented-speech pronunciation patterns by the means of two approaches: based on phonetic and phonological knowledge on the one hand and inferred from a text-to-speech system on the other. Artificial speech is then generated with a range of variants which have been captured in confusion matrices representing phoneme similarities. We then show that non-native accent confusions actually propagate to the transcription from the ASR, thus suggesting that the inference of accent specific phoneme confusions is achievable from artificial speech.","PeriodicalId":186158,"journal":{"name":"Special Interest Group on Computational Morphology and Phonology Workshop","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114193443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We present a novel approach to the unsupervised learning of morphology. In particular, we use a Multiple Cause Mixture Model (MCMM), a type of autoencoder network consisting of two node layers—hidden and surface—and a matrix of weights connecting hidden nodes to surface nodes. We show that an MCMM shares crucial graphical properties with autosegmental morphology. We argue on the basis of this graphical similarity that our approach is theoretically sound. Experiment results on Hebrew data show that this theoretical soundness bears out in practice.
{"title":"A Multilinear Approach to the Unsupervised Learning of Morphology","authors":"A. Meyer, Markus Dickinson","doi":"10.18653/v1/W16-2020","DOIUrl":"https://doi.org/10.18653/v1/W16-2020","url":null,"abstract":"We present a novel approach to the unsupervised learning of morphology. In particular, we use a Multiple Cause Mixture Model (MCMM), a type of autoencoder network consisting of two node layers—hidden and surface—and a matrix of weights connecting hidden nodes to surface nodes. We show that an MCMM shares crucial graphical properties with autosegmental morphology. We argue on the basis of this graphical similarity that our approach is theoretically sound. Experiment results on Hebrew data show that this theoretical soundness bears out in practice.","PeriodicalId":186158,"journal":{"name":"Special Interest Group on Computational Morphology and Phonology Workshop","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121921934","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
For languages such as German where compounds occur frequently and are written as single tokens, a wide variety of NLP applications benefits from recognizing and splitting compounds. As the traditional word frequency-based approach to compound splitting has several drawbacks, this paper introduces a letter sequence labeling approach, which can utilize rich word form features to build discriminative learning models that are optimized for splitting. Experiments show that the proposed method significantly outperforms state-of-the-art compound splitters.
{"title":"Letter Sequence Labeling for Compound Splitting","authors":"Jianqiang Ma, Verena Henrich, E. Hinrichs","doi":"10.18653/v1/W16-2012","DOIUrl":"https://doi.org/10.18653/v1/W16-2012","url":null,"abstract":"For languages such as German where compounds occur frequently and are written as single tokens, a wide variety of NLP applications benefits from recognizing and splitting compounds. As the traditional word frequency-based approach to compound splitting has several drawbacks, this paper introduces a letter sequence labeling approach, which can utilize rich word form features to build discriminative learning models that are optimized for splitting. Experiments show that the proposed method significantly outperforms state-of-the-art compound splitters.","PeriodicalId":186158,"journal":{"name":"Special Interest Group on Computational Morphology and Phonology Workshop","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122215506","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Due to the lack of data resources, rule-based or transfer learning is mainly used in the morphological tagging of low-resource languages. However, these methods require expert knowledge, ignore contextual features, and have error propagation. Therefore, we propose a joint morphological tagger for low-resource agglutinative languages to alleviate the above challenges. First, we represent the contextual input with multi-dimensional features of agglutinative words. Second, joint training reduces the direct impact of part-of-speech errors on morphological features and increases the indirect influence between the two types of labels through a fusion mechanism. Finally, our model separately predicts part-of-speech and morphological features. Part-of-speech tagging is regarded as sequence tagging. When predicting morphological features, two-label adjacency graphs are dynamically reconstructed by integrating multilingual global features and monolingual local features. Then, a graph convolution network is used to learn the higher-order intersection of labels. A series of experiments show that the proposed model in this paper is superior to other comparative models.
{"title":"Joint Learning Model for Low-Resource Agglutinative Language Morphological Tagging","authors":"Gulinigeer Abudouwaili, Kahaerjiang Abiderexiti, Nian Yi, Aishan Wumaier","doi":"10.18653/v1/2023.sigmorphon-1.4","DOIUrl":"https://doi.org/10.18653/v1/2023.sigmorphon-1.4","url":null,"abstract":"Due to the lack of data resources, rule-based or transfer learning is mainly used in the morphological tagging of low-resource languages. However, these methods require expert knowledge, ignore contextual features, and have error propagation. Therefore, we propose a joint morphological tagger for low-resource agglutinative languages to alleviate the above challenges. First, we represent the contextual input with multi-dimensional features of agglutinative words. Second, joint training reduces the direct impact of part-of-speech errors on morphological features and increases the indirect influence between the two types of labels through a fusion mechanism. Finally, our model separately predicts part-of-speech and morphological features. Part-of-speech tagging is regarded as sequence tagging. When predicting morphological features, two-label adjacency graphs are dynamically reconstructed by integrating multilingual global features and monolingual local features. Then, a graph convolution network is used to learn the higher-order intersection of labels. A series of experiments show that the proposed model in this paper is superior to other comparative models.","PeriodicalId":186158,"journal":{"name":"Special Interest Group on Computational Morphology and Phonology Workshop","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116037226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.18653/v1/2023.sigmorphon-1.7
David R. Mortensen, Ela Gulsen, Taiqi He, Nathaniel R. Robinson, Jonathan D. Amith, Lindia Tjuatja, L. Levin
Interlinear glossing provides a vital type of morphosyntactic annotation, both for linguists and language revitalists, and numerous conventions exist for representing it formally and computationally. Some of these formats are human readable; others are machine readable. Some are easy to edit with general-purpose tools. Few represent non-concatentative processes like infixation, reduplication, mutation, truncation, and tonal overwriting in a consistent and formally rigorous way (on par with affixation). We propose an annotation convention—Generalized Glossing Guidelines (GGG) that combines all of these positive properties using an Item-and-Process (IP) framework. We describe the format, demonstrate its linguistic adequacy, and compare it with two other interlinear glossed text annotation schemes.
{"title":"Generalized Glossing Guidelines: An Explicit, Human- and Machine-Readable, Item-and-Process Convention for Morphological Annotation","authors":"David R. Mortensen, Ela Gulsen, Taiqi He, Nathaniel R. Robinson, Jonathan D. Amith, Lindia Tjuatja, L. Levin","doi":"10.18653/v1/2023.sigmorphon-1.7","DOIUrl":"https://doi.org/10.18653/v1/2023.sigmorphon-1.7","url":null,"abstract":"Interlinear glossing provides a vital type of morphosyntactic annotation, both for linguists and language revitalists, and numerous conventions exist for representing it formally and computationally. Some of these formats are human readable; others are machine readable. Some are easy to edit with general-purpose tools. Few represent non-concatentative processes like infixation, reduplication, mutation, truncation, and tonal overwriting in a consistent and formally rigorous way (on par with affixation). We propose an annotation convention—Generalized Glossing Guidelines (GGG) that combines all of these positive properties using an Item-and-Process (IP) framework. We describe the format, demonstrate its linguistic adequacy, and compare it with two other interlinear glossed text annotation schemes.","PeriodicalId":186158,"journal":{"name":"Special Interest Group on Computational Morphology and Phonology Workshop","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126911561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.18653/v1/2023.sigmorphon-1.2
M. Elsner, Jordan Needle
We investigate how well words in the polysynthetic language Inuktitut can be translated by combining dictionary definitions, without use of a neural machine translation model trained on parallel text. Such a translation system would allow natural language technology to benefit from resources designed for community use in a language revitalization or education program, rather than requiring a separate parallel corpus. We show that the text-to-text generation capabilities of GPT-3 allow it to perform this task with BLEU scores of up to 18.5. We investigate prompting GPT-3 to provide multiple translations, which can help slightly, and providing it with grammar information, which is mostly ineffective. Finally, we test GPT-3’s ability to derive morpheme definitions from whole-word translations, but find this process is prone to errors including hallucinations.
{"title":"Translating a low-resource language using GPT-3 and a human-readable dictionary","authors":"M. Elsner, Jordan Needle","doi":"10.18653/v1/2023.sigmorphon-1.2","DOIUrl":"https://doi.org/10.18653/v1/2023.sigmorphon-1.2","url":null,"abstract":"We investigate how well words in the polysynthetic language Inuktitut can be translated by combining dictionary definitions, without use of a neural machine translation model trained on parallel text. Such a translation system would allow natural language technology to benefit from resources designed for community use in a language revitalization or education program, rather than requiring a separate parallel corpus. We show that the text-to-text generation capabilities of GPT-3 allow it to perform this task with BLEU scores of up to 18.5. We investigate prompting GPT-3 to provide multiple translations, which can help slightly, and providing it with grammar information, which is mostly ineffective. Finally, we test GPT-3’s ability to derive morpheme definitions from whole-word translations, but find this process is prone to errors including hallucinations.","PeriodicalId":186158,"journal":{"name":"Special Interest Group on Computational Morphology and Phonology Workshop","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131212776","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.18653/v1/2023.sigmorphon-1.9
Bhargav Shandilya, Alexis Palmer
Linguistic analysis is a core task in the process of documenting, analyzing, and describing endangered and less-studied languages. In addition to providing insight into the properties of the language being studied, having tools to automatically label words in a language for grammatical category and morphological features can support a range of applications useful for language pedagogy and revitalization. At the same time, most modern NLP methods for these tasks require both large amounts of data in the language and compute costs well beyond the capacity of most research groups and language communities. In this paper, we present a gloss-to-gloss (g2g) model for linguistic analysis (specifically, morphological analysis and part-of-speech tagging) that is lightweight in terms of both data requirements and computational expense. The model is designed for the interlinear glossed text (IGT) format, in which we expect the source text of a sentence in a low-resource language, a translation of that sentence into a language of wider communication, and a detailed glossing of the morphological properties of each word in the sentence. We first produce silver standard parallel glossed data by automatically labeling the high-resource translation. The model then learns to transform source language morphological labels into output labels for the target language, mediated by a structured linguistic representation layer. We test the model on both low-resource and high-resource languages, and find that our simple CNN-based model achieves comparable performance to a state-of-the-art transformer-based model, at a fraction of the computational cost.
{"title":"Lightweight morpheme labeling in context: Using structured linguistic representations to support linguistic analysis for the language documentation context","authors":"Bhargav Shandilya, Alexis Palmer","doi":"10.18653/v1/2023.sigmorphon-1.9","DOIUrl":"https://doi.org/10.18653/v1/2023.sigmorphon-1.9","url":null,"abstract":"Linguistic analysis is a core task in the process of documenting, analyzing, and describing endangered and less-studied languages. In addition to providing insight into the properties of the language being studied, having tools to automatically label words in a language for grammatical category and morphological features can support a range of applications useful for language pedagogy and revitalization. At the same time, most modern NLP methods for these tasks require both large amounts of data in the language and compute costs well beyond the capacity of most research groups and language communities. In this paper, we present a gloss-to-gloss (g2g) model for linguistic analysis (specifically, morphological analysis and part-of-speech tagging) that is lightweight in terms of both data requirements and computational expense. The model is designed for the interlinear glossed text (IGT) format, in which we expect the source text of a sentence in a low-resource language, a translation of that sentence into a language of wider communication, and a detailed glossing of the morphological properties of each word in the sentence. We first produce silver standard parallel glossed data by automatically labeling the high-resource translation. The model then learns to transform source language morphological labels into output labels for the target language, mediated by a structured linguistic representation layer. We test the model on both low-resource and high-resource languages, and find that our simple CNN-based model achieves comparable performance to a state-of-the-art transformer-based model, at a fraction of the computational cost.","PeriodicalId":186158,"journal":{"name":"Special Interest Group on Computational Morphology and Phonology Workshop","volume":"161 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134260124","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：