Not an Interlingua, But Close: Comparison of English AMRs to Chinese and Czech. Xue, N., Bojar, O., Hajic, J., Palmer, M., Uresová, Z., & Zhang, X. In May, 2014.
Paper abstract bibtex Abstract Meaning Representations (AMRs) are rooted, directional and labeled graphs that abstract away from morpho-syntactic idiosyncrasies such as word category (verbs and nouns), word order, and function words (determiners, some prepositions). Because these syntactic idiosyncrasies account for many of the cross-lingual differences, it would be interesting to see if this representation can serve, e.g., as a useful, minimally divergent transfer layer in machine translation. To answer this question, we have translated 100 English sentences that have existing AMRs into Chinese and Czech to create AMRs for them. A cross-linguistic comparison of English to Chinese and Czech AMRs reveals both cases where the AMRs for the language pairs align well structurally and cases of linguistic divergence. We found that the level of compatibility of AMR between English and Chinese is higher than between English and Czech. We believe this kind of comparison is beneficial to further refining the annotation standards for each of the three languages and will lead to more compatible annotation guidelines between the languages.
@inproceedings{xue_not_2014,
title = {Not an {Interlingua}, {But} {Close}: {Comparison} of {English} {AMRs} to {Chinese} and {Czech}},
shorttitle = {Not an {Interlingua}, {But} {Close}},
url = {https://www.semanticscholar.org/paper/Not-an-Interlingua%2C-But-Close%3A-Comparison-of-AMRs-Xue-Bojar/7099fd783370d14cdd6b5bc399feca970b658563},
abstract = {Abstract Meaning Representations (AMRs) are rooted, directional and labeled graphs that abstract away from morpho-syntactic idiosyncrasies such as word category (verbs and nouns), word order, and function words (determiners, some prepositions). Because these syntactic idiosyncrasies account for many of the cross-lingual differences, it would be interesting to see if this representation can serve, e.g., as a useful, minimally divergent transfer layer in machine translation. To answer this question, we have translated 100 English sentences that have existing AMRs into Chinese and Czech to create AMRs for them. A cross-linguistic comparison of English to Chinese and Czech AMRs reveals both cases where the AMRs for the language pairs align well structurally and cases of linguistic divergence. We found that the level of compatibility of AMR between English and Chinese is higher than between English and Czech. We believe this kind of comparison is beneficial to further refining the annotation standards for each of the three languages and will lead to more compatible annotation guidelines between the languages.},
urldate = {2025-02-18},
author = {Xue, Nianwen and Bojar, Ondrej and Hajic, Jan and Palmer, Martha and Uresová, Zdenka and Zhang, Xiuhong},
month = may,
year = {2014},
keywords = {Meaning representation},
}
Downloads: 0
{"_id":"zHASzzk6NReDi4P44","bibbaseid":"xue-bojar-hajic-palmer-uresov-zhang-notaninterlinguabutclosecomparisonofenglishamrstochineseandczech-2014","author_short":["Xue, N.","Bojar, O.","Hajic, J.","Palmer, M.","Uresová, Z.","Zhang, X."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Not an Interlingua, But Close: Comparison of English AMRs to Chinese and Czech","shorttitle":"Not an Interlingua, But Close","url":"https://www.semanticscholar.org/paper/Not-an-Interlingua%2C-But-Close%3A-Comparison-of-AMRs-Xue-Bojar/7099fd783370d14cdd6b5bc399feca970b658563","abstract":"Abstract Meaning Representations (AMRs) are rooted, directional and labeled graphs that abstract away from morpho-syntactic idiosyncrasies such as word category (verbs and nouns), word order, and function words (determiners, some prepositions). Because these syntactic idiosyncrasies account for many of the cross-lingual differences, it would be interesting to see if this representation can serve, e.g., as a useful, minimally divergent transfer layer in machine translation. To answer this question, we have translated 100 English sentences that have existing AMRs into Chinese and Czech to create AMRs for them. A cross-linguistic comparison of English to Chinese and Czech AMRs reveals both cases where the AMRs for the language pairs align well structurally and cases of linguistic divergence. We found that the level of compatibility of AMR between English and Chinese is higher than between English and Czech. We believe this kind of comparison is beneficial to further refining the annotation standards for each of the three languages and will lead to more compatible annotation guidelines between the languages.","urldate":"2025-02-18","author":[{"propositions":[],"lastnames":["Xue"],"firstnames":["Nianwen"],"suffixes":[]},{"propositions":[],"lastnames":["Bojar"],"firstnames":["Ondrej"],"suffixes":[]},{"propositions":[],"lastnames":["Hajic"],"firstnames":["Jan"],"suffixes":[]},{"propositions":[],"lastnames":["Palmer"],"firstnames":["Martha"],"suffixes":[]},{"propositions":[],"lastnames":["Uresová"],"firstnames":["Zdenka"],"suffixes":[]},{"propositions":[],"lastnames":["Zhang"],"firstnames":["Xiuhong"],"suffixes":[]}],"month":"May","year":"2014","keywords":"Meaning representation","bibtex":"@inproceedings{xue_not_2014,\n\ttitle = {Not an {Interlingua}, {But} {Close}: {Comparison} of {English} {AMRs} to {Chinese} and {Czech}},\n\tshorttitle = {Not an {Interlingua}, {But} {Close}},\n\turl = {https://www.semanticscholar.org/paper/Not-an-Interlingua%2C-But-Close%3A-Comparison-of-AMRs-Xue-Bojar/7099fd783370d14cdd6b5bc399feca970b658563},\n\tabstract = {Abstract Meaning Representations (AMRs) are rooted, directional and labeled graphs that abstract away from morpho-syntactic idiosyncrasies such as word category (verbs and nouns), word order, and function words (determiners, some prepositions). Because these syntactic idiosyncrasies account for many of the cross-lingual differences, it would be interesting to see if this representation can serve, e.g., as a useful, minimally divergent transfer layer in machine translation. To answer this question, we have translated 100 English sentences that have existing AMRs into Chinese and Czech to create AMRs for them. A cross-linguistic comparison of English to Chinese and Czech AMRs reveals both cases where the AMRs for the language pairs align well structurally and cases of linguistic divergence. We found that the level of compatibility of AMR between English and Chinese is higher than between English and Czech. We believe this kind of comparison is beneficial to further refining the annotation standards for each of the three languages and will lead to more compatible annotation guidelines between the languages.},\n\turldate = {2025-02-18},\n\tauthor = {Xue, Nianwen and Bojar, Ondrej and Hajic, Jan and Palmer, Martha and Uresová, Zdenka and Zhang, Xiuhong},\n\tmonth = may,\n\tyear = {2014},\n\tkeywords = {Meaning representation},\n}\n\n\n\n","author_short":["Xue, N.","Bojar, O.","Hajic, J.","Palmer, M.","Uresová, Z.","Zhang, X."],"key":"xue_not_2014","id":"xue_not_2014","bibbaseid":"xue-bojar-hajic-palmer-uresov-zhang-notaninterlinguabutclosecomparisonofenglishamrstochineseandczech-2014","role":"author","urls":{"Paper":"https://www.semanticscholar.org/paper/Not-an-Interlingua%2C-But-Close%3A-Comparison-of-AMRs-Xue-Bojar/7099fd783370d14cdd6b5bc399feca970b658563"},"keyword":["Meaning representation"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/abhishek-p","dataSources":["h7kKWXpJh2iaX92T5"],"keywords":["meaning representation"],"search_terms":["interlingua","close","comparison","english","amrs","chinese","czech","xue","bojar","hajic","palmer","uresová","zhang"],"title":"Not an Interlingua, But Close: Comparison of English AMRs to Chinese and Czech","year":2014}