The 2023 SIGMORPHON–UniMorph shared task on typologically diverse morphological inflection included a wide range of languages: 26 languages from 9 primary language families. The data this year was all lemma-split, to allow testing models’ generalization ability, and structured along the new hierarchical schema presented in (Batsuren et al., 2022). The systems submitted this year, 9 in number, showed ingenuity and innovativeness, including hard attention for explainability and bidirectional decoding. Special treatment was also given by many participants to the newly-introduced data in Japanese, due to the high abundance of unseen Kanji characters in its test set.
2023年SIGMORPHON-UniMorph共享任务涉及9个主要语系的26种语言。今年的数据都是引理分裂的，以便测试模型的泛化能力，并按照(Batsuren et al.， 2022)中提出的新的分层模式进行结构化。今年提交的9个系统显示出独创性和创新性，包括对可解释性和双向解码的努力关注。由于测试集中有大量未见过的汉字，许多参与者对新引入的日文数据也给予了特殊的处理。
{"title":"SIGMORPHON–UniMorph 2023 Shared Task 0: Typologically Diverse Morphological Inflection","authors":"Omer Goldman, Khuyagbaatar Batsuren, Salam Khalifa, Aryaman Arora, Garrett Nicolai, Reut Tsarfaty, Ekaterina Vylomova","doi":"10.18653/v1/2023.sigmorphon-1.13","DOIUrl":"https://doi.org/10.18653/v1/2023.sigmorphon-1.13","url":null,"abstract":"The 2023 SIGMORPHON–UniMorph shared task on typologically diverse morphological inflection included a wide range of languages: 26 languages from 9 primary language families. The data this year was all lemma-split, to allow testing models’ generalization ability, and structured along the new hierarchical schema presented in (Batsuren et al., 2022). The systems submitted this year, 9 in number, showed ingenuity and innovativeness, including hard attention for explainability and bidirectional decoding. Special treatment was also given by many participants to the newly-introduced data in Japanese, due to the high abundance of unseen Kanji characters in its test set.","PeriodicalId":186158,"journal":{"name":"Special Interest Group on Computational Morphology and Phonology Workshop","volume":"86 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":"122427800","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 an algorithm for automatic word forms inflection. We use the method of longest common subsequence to extract abstract paradigms from given pairs of basic and inflected word forms, as well as suffix and prefix features to predict this paradigm automatically. We elaborate this algorithm using combination of affix feature-based and character ngram models, which substantially enhances performance especially for the languages possessing nonlocal phenomena such as vowel harmony. Our system took part in SIGMORPHON 2016 Shared Task and took 3rd place in 17 of 30 subtasks and 4th place in 7 substasks among 7 participants.
{"title":"Using longest common subsequence and character models to predict word forms","authors":"A. Sorokin","doi":"10.18653/v1/W16-2009","DOIUrl":"https://doi.org/10.18653/v1/W16-2009","url":null,"abstract":"This paper presents an algorithm for automatic word forms inflection. We use the method of longest common subsequence to extract abstract paradigms from given pairs of basic and inflected word forms, as well as suffix and prefix features to predict this paradigm automatically. We elaborate this algorithm using combination of affix feature-based and character ngram models, which substantially enhances performance especially for the languages possessing nonlocal phenomena such as vowel harmony. Our system took part in SIGMORPHON 2016 Shared Task and took 3rd place in 17 of 30 subtasks and 4th place in 7 substasks among 7 participants.","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":"131330208","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-1.27
Arya D. McCarthy, Jackson L. Lee, Alexandra DeLucia, Travis M. Bartley, M. Agarwal, Lucas F. E. Ashby, L. Signore, Cameron Gibson, R. Raff, Winston Wu
Grapheme-to-phoneme conversion is an important component in many speech technologies, but until recently there were no multilingual benchmarks for this task. The third iteration of the SIGMORPHON shared task on multilingual grapheme-to-phoneme conversion features many improvements from the previous year’s task (Ashby et al., 2021), including additional languages, three subtasks varying the amount of available resources, extensive quality assurance procedures, and automated error analyses. Three teams submitted a total of fifteen systems, at best achieving relative reductions of word error rate of 14% in the crosslingual subtask and 14% in the very-low resource subtask. The generally consistent result is that cross-lingual transfer substantially helps grapheme-to-phoneme modeling, but not to the same degree as in-language examples.
{"title":"The SIGMORPHON 2022 Shared Task on Cross-lingual and Low-Resource Grapheme-to-Phoneme Conversion","authors":"Arya D. McCarthy, Jackson L. Lee, Alexandra DeLucia, Travis M. Bartley, M. Agarwal, Lucas F. E. Ashby, L. Signore, Cameron Gibson, R. Raff, Winston Wu","doi":"10.18653/v1/2023.sigmorphon-1.27","DOIUrl":"https://doi.org/10.18653/v1/2023.sigmorphon-1.27","url":null,"abstract":"Grapheme-to-phoneme conversion is an important component in many speech technologies, but until recently there were no multilingual benchmarks for this task. The third iteration of the SIGMORPHON shared task on multilingual grapheme-to-phoneme conversion features many improvements from the previous year’s task (Ashby et al., 2021), including additional languages, three subtasks varying the amount of available resources, extensive quality assurance procedures, and automated error analyses. Three teams submitted a total of fifteen systems, at best achieving relative reductions of word error rate of 14% in the crosslingual subtask and 14% in the very-low resource subtask. The generally consistent result is that cross-lingual transfer substantially helps grapheme-to-phoneme modeling, but not to the same degree as in-language examples.","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":"129884903","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}
Syllabification is sometimes influenced by morphological boundaries. We show that incorporating morphological information can improve the accuracy of orthographic syllabification in English and German. Surprisingly, unsupervised segmenters, such as Morfessor, can be more useful for this purpose than the supervised ones.
{"title":"Morphological Segmentation Can Improve Syllabification","authors":"Garrett Nicolai, Lei Yao, Grzegorz Kondrak","doi":"10.18653/v1/W16-2016","DOIUrl":"https://doi.org/10.18653/v1/W16-2016","url":null,"abstract":"Syllabification is sometimes influenced by morphological boundaries. We show that incorporating morphological information can improve the accuracy of orthographic syllabification in English and German. Surprisingly, unsupervised segmenters, such as Morfessor, can be more useful for this purpose than the supervised ones.","PeriodicalId":186158,"journal":{"name":"Special Interest Group on Computational Morphology and Phonology Workshop","volume":"43 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":"121354637","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}
It is commonly accepted that morphological dependencies are finite-state in nature. We argue that the upper bound on morphological expressivity is much lower. Drawing on technical results from computational phonology, we show that a variety of morphotactic phenomena are tierbased strictly local and do not fall into weaker subclasses such as the strictly local or strictly piecewise languages. Since the tier-based strictly local languages are learnable in the limit from positive texts, this marks a first important step towards general machine learning algorithms for morphology. Furthermore, the limitation to tier-based strictly local languages explains typological gaps that are puzzling from a purely linguistic perspective.
{"title":"Morphotactics as Tier-Based Strictly Local Dependencies","authors":"Alëna Aksënova, T. Graf, S. Moradi","doi":"10.18653/v1/W16-2019","DOIUrl":"https://doi.org/10.18653/v1/W16-2019","url":null,"abstract":"It is commonly accepted that morphological dependencies are finite-state in nature. We argue that the upper bound on morphological expressivity is much lower. Drawing on technical results from computational phonology, we show that a variety of morphotactic phenomena are tierbased strictly local and do not fall into weaker subclasses such as the strictly local or strictly piecewise languages. Since the tier-based strictly local languages are learnable in the limit from positive texts, this marks a first important step towards general machine learning algorithms for morphology. Furthermore, the limitation to tier-based strictly local languages explains typological gaps that are puzzling from a purely linguistic perspective.","PeriodicalId":186158,"journal":{"name":"Special Interest Group on Computational Morphology and Phonology Workshop","volume":"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":"122975938","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-1.29
Michael Hammond
In this paper we explore a very simple nonneural approach to mapping orthography to phonetic transcription in a low-resource context with transfer data from a related language. We start from a baseline system and focus our efforts on data augmentation. We make three principal moves. First, we start with an HMMbased system (Novak et al., 2012). Second, we augment our basic system by recombining legal substrings in restricted fashion (Ryan and Hulden, 2020). Finally, we limit our transfer data by only using training pairs where the phonetic form shares all bigrams with the target language.
在本文中，我们探索了一种非常简单的非神经方法来映射正字法到语音转录在低资源背景下与相关语言的传输数据。我们从一个基线系统开始，把精力集中在数据增强上。我们有三个主要动作。首先，我们从基于hmm的系统开始(Novak et al.， 2012)。其次，我们通过以受限的方式重组合法子字符串来增强我们的基本系统(Ryan和Hulden, 2020)。最后，我们通过只使用语音形式与目标语言共享所有双字母的训练对来限制我们的迁移数据。
{"title":"Low-resource grapheme-to-phoneme mapping with phonetically-conditioned transfer","authors":"Michael Hammond","doi":"10.18653/v1/2023.sigmorphon-1.29","DOIUrl":"https://doi.org/10.18653/v1/2023.sigmorphon-1.29","url":null,"abstract":"In this paper we explore a very simple nonneural approach to mapping orthography to phonetic transcription in a low-resource context with transfer data from a related language. We start from a baseline system and focus our efforts on data augmentation. We make three principal moves. First, we start with an HMMbased system (Novak et al., 2012). Second, we augment our basic system by recombining legal substrings in restricted fashion (Ryan and Hulden, 2020). Finally, we limit our transfer data by only using training pairs where the phonetic form shares all bigrams with the target language.","PeriodicalId":186158,"journal":{"name":"Special Interest Group on Computational Morphology and Phonology Workshop","volume":"120 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":"127289786","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-1.20
Michael Ginn, Sarah Moeller, Alexis Palmer, Anna Stacey, Garrett Nicolai, Mans Hulden, Miikka Silfverberg
This paper presents the findings of the SIGMORPHON 2023 Shared Task on Interlinear Glossing. This first iteration of the shared task explores glossing of a set of six typologically diverse languages: Arapaho, Gitksan, Lezgi, Natügu, Tsez and Uspanteko. The shared task encompasses two tracks: a resource-scarce closed track and an open track, where participants are allowed to utilize external data resources. Five teams participated in the shared task. The winning team Tü-CL achieved a 23.99%-point improvement over a baseline RoBERTa system in the closed track and a 17.42%-point improvement in the open track.
{"title":"Findings of the SIGMORPHON 2023 Shared Task on Interlinear Glossing","authors":"Michael Ginn, Sarah Moeller, Alexis Palmer, Anna Stacey, Garrett Nicolai, Mans Hulden, Miikka Silfverberg","doi":"10.18653/v1/2023.sigmorphon-1.20","DOIUrl":"https://doi.org/10.18653/v1/2023.sigmorphon-1.20","url":null,"abstract":"This paper presents the findings of the SIGMORPHON 2023 Shared Task on Interlinear Glossing. This first iteration of the shared task explores glossing of a set of six typologically diverse languages: Arapaho, Gitksan, Lezgi, Natügu, Tsez and Uspanteko. The shared task encompasses two tracks: a resource-scarce closed track and an open track, where participants are allowed to utilize external data resources. Five teams participated in the shared task. The winning team Tü-CL achieved a 23.99%-point improvement over a baseline RoBERTa system in the closed track and a 17.42%-point improvement in the open track.","PeriodicalId":186158,"journal":{"name":"Special Interest Group on Computational Morphology and Phonology Workshop","volume":"67 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":"122815172","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-1.23
Edith Coates
This paper presents my submission to Track 1 of the 2023 SIGMORPHON shared task on interlinear glossed text (IGT). There are a wide amount of techniques for building and training IGT models (see Moeller and Hulden, 2018; McMillan-Major, 2020; Zhao et al., 2020). I describe my ensembled sequence-to-sequence approach, perform experiments, and share my submission’s test-set accuracy. I also discuss future areas of research in low-resource token classification methods for IGT.
{"title":"An Ensembled Encoder-Decoder System for Interlinear Glossed Text","authors":"Edith Coates","doi":"10.18653/v1/2023.sigmorphon-1.23","DOIUrl":"https://doi.org/10.18653/v1/2023.sigmorphon-1.23","url":null,"abstract":"This paper presents my submission to Track 1 of the 2023 SIGMORPHON shared task on interlinear glossed text (IGT). There are a wide amount of techniques for building and training IGT models (see Moeller and Hulden, 2018; McMillan-Major, 2020; Zhao et al., 2020). I describe my ensembled sequence-to-sequence approach, perform experiments, and share my submission’s test-set accuracy. I also discuss future areas of research in low-resource token classification methods for IGT.","PeriodicalId":186158,"journal":{"name":"Special Interest Group on Computational Morphology and Phonology Workshop","volume":"86 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":"126454721","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-1.14
Canaan Breiss, Jinyoung Jo
This paper summarises data collection and curation for Part 2 of the 2023 SIGMORPHON-UniMorph Shared Task 0, which focused on modeling speaker knowledge and generalization of a pair of interacting phonological processes in Korean. We briefly describe how modeling the generalization task could be of interest to researchers in both Natural Language Processing and linguistics, and then summarise the traditional description of the phonological processes that are at the center of the modeling challenge. We then describe the criteria we used to select and code cases of process application in two Korean speech corpora, which served as the primary learning data. We also report the technical details of the experiment we carried out that served as the primary test data.
{"title":"SIGMORPHON–UniMorph 2023 Shared Task 0, Part 2: Cognitively Plausible Morphophonological Generalization in Korean","authors":"Canaan Breiss, Jinyoung Jo","doi":"10.18653/v1/2023.sigmorphon-1.14","DOIUrl":"https://doi.org/10.18653/v1/2023.sigmorphon-1.14","url":null,"abstract":"This paper summarises data collection and curation for Part 2 of the 2023 SIGMORPHON-UniMorph Shared Task 0, which focused on modeling speaker knowledge and generalization of a pair of interacting phonological processes in Korean. We briefly describe how modeling the generalization task could be of interest to researchers in both Natural Language Processing and linguistics, and then summarise the traditional description of the phonological processes that are at the center of the modeling challenge. We then describe the criteria we used to select and code cases of process application in two Korean speech corpora, which served as the primary learning data. We also report the technical details of the experiment we carried out that served as the primary test data.","PeriodicalId":186158,"journal":{"name":"Special Interest Group on Computational Morphology and Phonology Workshop","volume":"76 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":"134630502","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-1.16
Cheon-Yeong Jeong, Dominic Schmitz, Akhilesh Kakolu Ramarao, Anna Stein, Kevin Tang
This paper presents our submission to the SIGMORPHON 2023 task 2 of Cognitively Plausible Morphophonological Generalization in Korean. We implemented both Linear Discriminative Learning and Transformer models and found that the Linear Discriminative Learning model trained on a combination of corpus and experimental data showed the best performance with the overall accuracy of around 83%. We found that the best model must be trained on both corpus data and the experimental data of one particular participant. Our examination of speaker-variability and speaker-specific information did not explain why a particular participant combined well with the corpus data. We recommend Linear Discriminative Learning models as a future non-neural baseline system, owning to its training speed, accuracy, model interpretability and cognitive plausibility. In order to improve the model performance, we suggest using bigger data and/or performing data augmentation and incorporating speaker- and item-specifics considerably.
{"title":"Linear Discriminative Learning: a competitive non-neural baseline for morphological inflection","authors":"Cheon-Yeong Jeong, Dominic Schmitz, Akhilesh Kakolu Ramarao, Anna Stein, Kevin Tang","doi":"10.18653/v1/2023.sigmorphon-1.16","DOIUrl":"https://doi.org/10.18653/v1/2023.sigmorphon-1.16","url":null,"abstract":"This paper presents our submission to the SIGMORPHON 2023 task 2 of Cognitively Plausible Morphophonological Generalization in Korean. We implemented both Linear Discriminative Learning and Transformer models and found that the Linear Discriminative Learning model trained on a combination of corpus and experimental data showed the best performance with the overall accuracy of around 83%. We found that the best model must be trained on both corpus data and the experimental data of one particular participant. Our examination of speaker-variability and speaker-specific information did not explain why a particular participant combined well with the corpus data. We recommend Linear Discriminative Learning models as a future non-neural baseline system, owning to its training speed, accuracy, model interpretability and cognitive plausibility. In order to improve the model performance, we suggest using bigger data and/or performing data augmentation and incorporating speaker- and item-specifics considerably.","PeriodicalId":186158,"journal":{"name":"Special Interest Group on Computational Morphology and Phonology Workshop","volume":"55 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132287091","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：