Difference between revisions of "Kperalt1/Final Project"
From LING073
(→Resources for machine translation between Shanghainese and Mandarin Chinese) |
|||
| (50 intermediate revisions by the same user not shown) | |||
| Line 5: | Line 5: | ||
===External Resources=== | ===External Resources=== | ||
| + | *Link to Shanghainese to English PUBLIC language pair: [https://github.com/kperalt/wuu-eng_MT] | ||
*Link to repository language pair:[https://github.swarthmore.edu/Ling073-sp25/ling073-wuu-eng.git] | *Link to repository language pair:[https://github.swarthmore.edu/Ling073-sp25/ling073-wuu-eng.git] | ||
*Link to Shanghainese repository transducer:[https://github.swarthmore.edu/Ling073-sp25/ling073-wuu.git] | *Link to Shanghainese repository transducer:[https://github.swarthmore.edu/Ling073-sp25/ling073-wuu.git] | ||
| Line 10: | Line 11: | ||
*Link to Shanghainese to English Text: [https://tatoeba.org/en/sentences/search?from=wuu&query=&to=eng] | *Link to Shanghainese to English Text: [https://tatoeba.org/en/sentences/search?from=wuu&query=&to=eng] | ||
| − | ==Shanghainese <code>wuu</code> → English <code>eng</code> Evaluation== | + | ==Shanghainese <code>wuu</code> → English <code>eng</code> Sentence Evaluation== |
===Sentences=== | ===Sentences=== | ||
* (1) <code>wuu</code>: 我爱侬。 | * (1) <code>wuu</code>: 我爱侬。 | ||
** <code>eng</code>: I love you. | ** <code>eng</code>: I love you. | ||
| − | ** lexical transfer output: | + | ** lexical transfer output: ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^爱<vblex>/love<vblex>$ ^侬<prn><pers><p2><sg>/you<prn><pers><p2><mf><sg>$ ^.<sent>/.<sent> |
| − | ** full translation output: | + | ** full translation output: I #love you . |
* (2) <code>wuu</code>: 我有很多朋友。 | * (2) <code>wuu</code>: 我有很多朋友。 | ||
** <code>eng</code>: I have many friends. | ** <code>eng</code>: I have many friends. | ||
| − | ** lexical transfer output: | + | ** lexical transfer output: ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^有<vblex>/have<vblex>$ ^很多<adj>/many<det><qnt><pl>$ ^朋友<n>/friend<n><pl>$ ^.<sent>/.<sent> |
| − | ** full translation output: | + | ** full translation output: I #have many friends . |
* (3) <code>wuu</code>: 侬欢喜唱歌伐？ | * (3) <code>wuu</code>: 侬欢喜唱歌伐？ | ||
** <code>eng</code>: Do you like singing? | ** <code>eng</code>: Do you like singing? | ||
| − | ** lexical transfer output: | + | ** lexical transfer output: ^侬<prn><pers><p2><sg>/you<prn><pers><p2><mf><sg>$ ^欢喜<vblex>/like<vblex>$ ^唱歌<n>/singing<n><sg>$ ^伐<qst>/$ ^.<sent>/.<sent> |
| − | ** full translation output: | + | ** full translation output: you #like singing ? |
| − | * (4) <code>wuu</code>: | + | * (4) <code>wuu</code>: 早上好。 |
| − | ** <code>eng</code>: Good morning | + | ** <code>eng</code>: Good morning. |
| − | ** lexical transfer output: | + | ** lexical transfer output: ^早上好<ij>/good morning<ij>$ ^.<sent>/.<sent> |
| − | ** full translation output: | + | ** full translation output: good morning . |
* (5) <code>wuu</code>: 侬要吃茶还是吃咖啡啊？ | * (5) <code>wuu</code>: 侬要吃茶还是吃咖啡啊？ | ||
** <code>eng</code>: Do you want to drink tea or coffee? | ** <code>eng</code>: Do you want to drink tea or coffee? | ||
| − | ** lexical transfer output: | + | ** lexical transfer output: ^侬<prn><pers><p2><sg>/you<prn><pers><p2><mf><sg>$ ^要<vaux>/want<vblex>/will<vblex>/want to<vbmod>$ ^吃<vblex>/eat<vblex>/drink<vblex>$ ^茶<n>/tea<n><sg>$ ^还是<cnjcoo>/or<cnjcoo>$ ^吃<vblex>/eat<vblex>/drink<vblex>$ ^咖啡<n>/coffee<n><sg>$ ^啊<part>/$ ^.<sent>/.<sent> |
| − | ** full translation output: | + | ** full translation output: you #want to #drink tea or #drink coffee ? |
* (6) <code>wuu</code>: 是我个，勿是伊个。 | * (6) <code>wuu</code>: 是我个，勿是伊个。 | ||
** <code>eng</code>: It's mine, not his. | ** <code>eng</code>: It's mine, not his. | ||
| − | ** lexical transfer output: | + | ** lexical transfer output: ^是<vblex>/is<vblex><p3><sg>/was<vblex><p3><sg>$ ^我<prn><pers><p1><sg><pos>/I<prn><subj><p1><mf><sg><pos>$ ^，<cm>/,<cm>$ ^勿是<vaux>/not<adv>$ ^伊<prn><pers><p3><sg><pos>/he<prn><subj><p3><m><sg><pos>/it<prn><subj><p3><nt><sg><pos>/her<prn><obj><p3><f><sg><pos>/him<prn><obj><p3><m><sg><pos>/his<prn><pos><p3><m><sg><pos>/she<prn><subj><p3><f><sg><pos>/hers<prn><pos><p3><f><sg><pos>$ ^.<sent>/.<sent> |
| − | ** full translation output: | + | ** full translation output: #is my , not his . |
* (7) <code>wuu</code>: 搿是我个行李。 | * (7) <code>wuu</code>: 搿是我个行李。 | ||
** <code>eng</code>: Here is my baggage. | ** <code>eng</code>: Here is my baggage. | ||
| − | ** lexical transfer output: | + | ** lexical transfer output: ^搿<adv>/here<adv>$ ^是<vblex>/is<vblex><p3><sg>/was<vblex><p3><sg>$ ^我<prn><pers><p1><sg><pos>/I<prn><subj><p1><mf><sg><pos>$ ^行李<n>/baggage<n><sg>$ ^.<sent>/.<sent> |
| − | ** full translation output: | + | ** full translation output: here #is my baggage . |
* (8) <code>wuu</code>: 伊是法国人。 | * (8) <code>wuu</code>: 伊是法国人。 | ||
** <code>eng</code>: She is French. or He is French. | ** <code>eng</code>: She is French. or He is French. | ||
| − | ** lexical transfer output: | + | ** lexical transfer output: ^伊<prn><pers><p3><sg>/he<prn><subj><p3><m><sg>/it<prn><subj><p3><nt><sg>/her<prn><obj><p3><f><sg>/him<prn><obj><p3><m><sg>/his<prn><pos><p3><m><sg>/she<prn><subj><p3><f><sg>/hers<prn><pos><p3><f><sg>$ ^是<vblex>/is<vblex><p3><sg>/was<vblex><p3><sg>$ ^法国人<n>/French<n><pl>$ ^.<sent>/.<sent> |
| − | ** full translation output: | + | ** full translation output: he #is French . |
* (9) <code>wuu</code>: 我每天六点钟起床。 | * (9) <code>wuu</code>: 我每天六点钟起床。 | ||
** <code>eng</code>: I get up at six every day. | ** <code>eng</code>: I get up at six every day. | ||
| − | ** lexical transfer output: | + | ** lexical transfer output: ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^每天<adv>/every day<adv>$ ^六点钟<n>/six<num><pl>$ ^起床<vblex>/wake up<vblex>$ ^.<sent>/.<sent> |
| − | ** full translation output: | + | ** full translation output: I every day six #wake up . |
* (10) <code>wuu</code>: 一、二、三、四、五、六、七、八、九、十。 | * (10) <code>wuu</code>: 一、二、三、四、五、六、七、八、九、十。 | ||
** <code>eng</code>: One, two, three, four, five, six, seven, right, nine, ten. | ** <code>eng</code>: One, two, three, four, five, six, seven, right, nine, ten. | ||
| − | ** lexical transfer output: | + | ** lexical transfer output: ^一<num>/one<num><sg>$ ^、<cm>/,<cm>$ ^二<num>/two<num><pl>$ ^、<cm>/,<cm>$ ^三<num>/three<num><pl>$ ^、<cm>/,<cm>$ ^四<num>/four<num><pl>$ ^、<cm>/,<cm>$ ^五<num>/five<num><pl>$ ^、<cm>/,<cm>$ ^六<num>/six<num><pl>$ ^、<cm>/,<cm>$ ^七<num>/seven<num><pl>$ ^、<cm>/,<cm>$ ^八<num>/eight<num><pl>$ ^、<cm>/,<cm>$ ^九<num>/nine<num><pl>$ ^、<cm>/,<cm>$ ^十<num>/ten<num><pl>$ ^.<sent>/.<sent> |
| − | ** full translation output: | + | ** full translation output: one , two , three , four , five , six , seven , eight , nine , ten . |
| + | * (11) <code>wuu</code>: 侬要走啦？ | ||
| + | ** <code>eng</code>: Do you want to go? | ||
| + | ** lexical transfer output: ^侬<prn><pers><p2><sg>/you<prn><pers><p2><mf><sg>$ ^要<vaux>/want<vblex>/will<vblex>/want to<vbmod>$ ^走<vblex>/go<vblex>$ ^啦<part>/$ ^.<sent>/.<sent> | ||
| + | ** full translation output: you #want to #go ? | ||
| + | * (12) <code>wuu</code>: 麻烦侬了。 | ||
| + | ** <code>eng</code>: Sorry to trouble you. | ||
| + | ** lexical transfer output: ^麻烦<vblex>/trouble<vblex>$ ^侬<prn><pers><p2><sg>/you<prn><pers><p2><mf><sg>$ ^了<part>/$ ^.<sent>/.<sent> | ||
| + | ** full translation output: #trouble you . | ||
| − | [[Category:Shanghainese]] | + | * (13) <code>wuu</code>: 我老勿好意思个。 |
| + | ** <code>eng</code>: I'm too ashamed. | ||
| + | ** lexical transfer output: ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^老<adv>/too<adv>$ ^勿好意思<adj>/ashamed<adj>$ ^个<part>/$ ^.<sent>/.<sent> | ||
| + | ** full translation output: I too ashamed . | ||
| + | |||
| + | * (14) <code>wuu</code>: 谢谢侬噢！ | ||
| + | ** <code>eng</code>: Thank you! | ||
| + | ** lexical transfer output: ^谢谢<vblex>/thank<vblex>$ ^侬<prn><pers><p2><sg>/you<prn><pers><p2><mf><sg>$ ^噢<part>/$ ^.<sent>/.<sent> | ||
| + | ** full translation output: #thank you . | ||
| + | |||
| + | * (15) <code>wuu</code>: 昨日是啥个天气？ | ||
| + | ** <code>eng</code>: What was the weather yesterday? | ||
| + | ** lexical transfer output: ^昨日<n>/yesterday<n><sg>$ ^是<vblex>/is<vblex><p3><sg>/was<vblex><p3><sg>$ ^啥<prn><itg>/what<prn><itg><mf><sp>$ ^个<part>/$ ^天气<n>/weather<n><sg>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: yesterday #is what weather ? | ||
| + | |||
| + | * (16) <code>wuu</code>: 明朝要落雪。 | ||
| + | ** <code>eng</code>: It will snow tomorrow. | ||
| + | ** lexical transfer output: ^明朝<n>/tomorrow<n><sg>$ ^要<vaux>/want<vblex>/will<vblex>/want to<vbmod>$ ^落雪<vblex>/snow<vblex>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: tomorrow #will #snow . | ||
| + | |||
| + | * (17) <code>wuu</code>: 侬住拉阿里搭？ | ||
| + | ** <code>eng</code>: Where do you live? | ||
| + | ** lexical transfer output: ^侬<prn><pers><p2><sg>/you<prn><pers><p2><mf><sg>$ ^住<vblex>/live<vblex>$ ^拉<pr>/at<pr>$ ^阿里搭<adv>/where<adv><itg>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: you #live at where ? | ||
| + | |||
| + | * (18) <code>wuu</code>: 侬要多少钞票？ | ||
| + | ** <code>eng</code>: How much money do you want? | ||
| + | ** lexical transfer output: ^侬<prn><pers><p2><sg>/you<prn><pers><p2><mf><sg>$ ^要<vaux>/want<vblex>/will<vblex>/want to<vbmod>$ ^多少<adv>/how much<adv><itg>$ ^钞票<n>/money<n><sg>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: you #want how much money ? | ||
| + | |||
| + | * (19) <code>wuu</code>: 对勿起。 | ||
| + | ** <code>eng</code>: Excuse me. | ||
| + | ** lexical transfer output: ^对勿起<ij>/excuse me<ij>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: excuse me . | ||
| + | |||
| + | * (20) <code>wuu</code>: 侬非常勇敢。 | ||
| + | ** <code>eng</code>: You are very brave. | ||
| + | ** lexical transfer output: ^侬<prn><pers><p2><sg>/you<prn><pers><p2><mf><sg>$ ^非常<adv>/very<adv>$ ^勇敢<adj>/brave<adj><sint>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: you very brave . | ||
| + | |||
| + | * (21) <code>wuu</code>: 侬选好了伐？ | ||
| + | ** <code>eng</code>: Have you chosen? | ||
| + | ** lexical transfer output: ^侬<prn><pers><p2><sg>/you<prn><pers><p2><mf><sg>$ ^选好<vblex>/chose<vblex>$ ^了<part>/$ ^伐<qst>/$ ^.<sent>/.<sent> | ||
| + | ** full translation output: you #chose ? | ||
| + | |||
| + | * (22) <code>wuu</code>: 够了。 | ||
| + | ** <code>eng</code>: That's enough. | ||
| + | ** lexical transfer output: ^够<adv>/enough<adv>$ ^了<part>/$ ^.<sent>/.<sent> | ||
| + | ** full translation output: enough . | ||
| + | |||
| + | * (23) <code>wuu</code>: 皮带是棕颜色个。 | ||
| + | ** <code>eng</code>: The belt is brown. | ||
| + | ** lexical transfer output: ^皮带<n>/belt<n><sg>$ ^是<vblex>/is<vblex><p3><sg>/was<vblex><p3><sg>$ ^棕颜色<adj>/brown<adj><sint>$ ^个<part>/$ ^.<sent>/.<sent> | ||
| + | ** full translation output: belt #is brown . | ||
| + | |||
| + | * (24) <code>wuu</code>: 我欢喜我个闲话。 | ||
| + | ** <code>eng</code>: I like my language. | ||
| + | ** lexical transfer output: ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^欢喜<vblex>/like<vblex>$ ^我<prn><pers><p1><sg><pos>/I<prn><subj><p1><mf><sg><pos>$ ^闲话<n>/language<n><sg>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: I #like my language . | ||
| + | |||
| + | * (25) <code>wuu</code>: 我有一支笔。 | ||
| + | ** <code>eng</code>: I have a pen. | ||
| + | ** lexical transfer output: ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^有<vblex>/have<vblex>$ ^一<num>/one<num><sg>$ ^支<part>/$ ^笔<n>/pen<n><sg>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: I #have one pen . | ||
| + | |||
| + | * (26) <code>wuu</code>: 有四个方向，东，南，西，北。 | ||
| + | ** <code>eng</code>: There are four cardinal points, East, south, west and north. | ||
| + | ** lexical transfer output: ^有<vblex>/have<vblex>$ ^四<num>/four<num><pl>$ ^个<part>/$ ^方向<n>/direction<n><pl>$ ^，<cm>/,<cm>$ ^东<adj>/east<adj>$ ^，<cm>/,<cm>$ ^南<adj>/south<adj><sint>$ ^，<cm>/,<cm>$ ^西<adj>/west<adj>$ ^，<cm>/,<cm>$ ^北<adj>/north<adj><sint>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: #have four directions , east , south , west , north . | ||
| + | |||
| + | * (27) <code>wuu</code>: 一年有四季，春夏秋冬。 | ||
| + | ** <code>eng</code>: There are four seasons in a year, spring, summer, fall and winter. | ||
| + | ** lexical transfer output: ^一<num>/one<num><sg>$ ^年<n>/year<n><sg>$ ^有<vblex>/have<vblex>$ ^四<num>/four<num><pl>$ ^季<n>/season<n><pl>$ ^，<cm>/,<cm>$ ^春<n>/spring<n><sg>$ ^夏<n>/summer<n><sg>$ ^秋<n>/autumn<n><sg>$ ^冬<n>/winter<n><sg>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: one year #have four seasons , spring summer autumn winter . | ||
| + | |||
| + | * (28) <code>wuu</code>: 请拿。 | ||
| + | ** <code>eng</code>: Take it, please. | ||
| + | ** lexical transfer output: ^请<ij>/please<ij>$ ^拿<vblex>/take<vblex>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: please #take . | ||
| + | |||
| + | * (29) <code>wuu</code>: 我是游客。 | ||
| + | ** <code>eng</code>: I'm a tourist. | ||
| + | ** lexical transfer output: ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^是<vblex>/is<vblex><p3><sg>/was<vblex><p3><sg>$ ^游客<n>/tourist<n><sg>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: I #is tourist . | ||
| + | |||
| + | * (30) <code>wuu</code>: 现在我可以走了𠲎？ | ||
| + | ** <code>eng</code>: Can I leave now? | ||
| + | ** lexical transfer output: ^现在<adv>/now<adv>$ ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^可以<vbmod>/can<vbmod>$ ^走<vblex>/go<vblex>$ ^了<part>/$ ^.<sent>/.<sent> | ||
| + | ** full translation output: now I #can #go ? | ||
| + | |||
| + | * (31) <code>wuu</code>: 我会得弹钢琴。 | ||
| + | ** <code>eng</code>: I can play piano. | ||
| + | ** lexical transfer output: ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^会得<vbmod>/can<vbmod>$ ^弹<vblex>/play<vblex>$ ^钢琴<n>/piano<n><sg>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: I #can #play piano . | ||
| + | |||
| + | * (32) <code>wuu</code>: 打网球是伊个兴趣。 | ||
| + | ** <code>eng</code>: Playing tennis is his hobby. | ||
| + | ** lexical transfer output: ^打<vblex>/play<vblex>$ ^网球<n>/tennis<n><sg>$ ^是<vblex>/is<vblex><p3><sg>/was<vblex><p3><sg>$ ^伊<prn><pers><p3><sg><pos>/he<prn><subj><p3><m><sg><pos>/it<prn><subj><p3><nt><sg><pos>/her<prn><obj><p3><f><sg><pos>/him<prn><obj><p3><m><sg><pos>/his<prn><pos><p3><m><sg><pos>/she<prn><subj><p3><f><sg><pos>/hers<prn><pos><p3><f><sg><pos>$ ^兴趣<n>/hobby<n><sg>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: #play tennis #is his hobby . | ||
| + | |||
| + | * (33) <code>wuu</code>: 勿是我个。 | ||
| + | ** <code>eng</code>: It's not mine. | ||
| + | ** lexical transfer output: ^勿是<vaux>/not<adv>$ ^我<prn><pers><p1><sg><pos>/I<prn><subj><p1><mf><sg><pos>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: not my . | ||
| + | |||
| + | * (34) <code>wuu</code>: 我學習中國言話。 | ||
| + | ** <code>eng</code>: I learn Chinese. | ||
| + | ** lexical transfer output: ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^學習<vblex>/study<vblex>$ ^中國言話<adj>/Chinese<adj>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: I #study Chinese . | ||
| + | |||
| + | * (35) <code>wuu</code>: 我申请了签证。 | ||
| + | ** <code>eng</code>: I applied for a visa. | ||
| + | ** lexical transfer output: ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^申请<vblex>/apply<vblex>$ ^了<part>/$ ^签证<n>/visa<n><sg>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: I #apply visa . | ||
| + | |||
| + | * (36) <code>wuu</code>: 吾欢喜吾个工作。 | ||
| + | ** <code>eng</code>: I like my job. | ||
| + | ** lexical transfer output: ^吾<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^欢喜<vblex>/like<vblex>$ ^吾<prn><pers><p1><sg><pos>/I<prn><subj><p1><mf><sg><pos>$ ^工作<n>/job<n><sg>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: I #like my job . | ||
| + | |||
| + | * (37) <code>wuu</code>: 生日快乐! | ||
| + | ** <code>eng</code>: Happy birthday! | ||
| + | ** lexical transfer output: ^生日快乐<ij>/Happy birthday<ij>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: Happy birthday ! | ||
| + | |||
| + | * (38) <code>wuu</code>: 再会！ | ||
| + | ** <code>eng</code>: Bye! | ||
| + | ** lexical transfer output: ^再会<ij>/bye<ij>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: bye . | ||
| + | |||
| + | * (39) <code>wuu</code>: 房间里向有老多学生子。 | ||
| + | ** <code>eng</code>: There are many students in the room. | ||
| + | ** lexical transfer output: ^房间<n>/room<n><sg>$ ^里向<n>/in<adv>$ ^有<vblex>/have<vblex>$ ^老<adv>/too<adv>$ ^多<adj>/many<det><qnt><pl>$ ^学生子<n>/student<n><pl>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: room in #have too many students . | ||
| + | |||
| + | * (40) <code>wuu</code>: 伊会得讲十种语言。 | ||
| + | ** <code>eng</code>: He can speak ten languages. | ||
| + | ** lexical transfer output: ^伊<prn><pers><p3><sg>/he<prn><subj><p3><m><sg>/it<prn><subj><p3><nt><sg>/her<prn><obj><p3><f><sg>/him<prn><obj><p3><m><sg>/his<prn><pos><p3><m><sg>/she<prn><subj><p3><f><sg>/hers<prn><pos><p3><f><sg>$ ^会得<vbmod>/can<vbmod>$ ^讲<vblex>/speak<vblex>$ ^十<num>/ten<num><pl>$ ^种<part>/$ ^语言<n>/language<n><pl>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: he #can #speak ten languages . | ||
| + | |||
| + | * (41) <code>wuu</code>: 吾嘴巴干。 | ||
| + | ** <code>eng</code>: I'm thirsty. | ||
| + | ** lexical transfer output: ^吾<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^嘴<n>/mouth<n><sg>$ ^巴干<vblex>/dry<vblex>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: I mouth #dry . | ||
| + | |||
| + | * (42) <code>wuu</code>: 吾肚皮饿了。 | ||
| + | ** <code>eng</code>: I am hungry. | ||
| + | ** lexical transfer output: ^吾<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^肚皮<n>/stomach<n><sg>$ ^饿<vblex>/hungry<vblex>$ ^了<part>/$ ^.<sent>/.<sent> | ||
| + | ** full translation output: I stomach #hungry | ||
| + | |||
| + | * (43) <code>wuu</code>: 吾肚皮痛。 | ||
| + | ** <code>eng</code>: I have a stomachache. | ||
| + | ** lexical transfer output: ^吾<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^肚皮<n>/stomach<n><sg>$ ^痛<n>/ache<n><pl>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: I stomach aches . | ||
| + | |||
| + | * (44) <code>wuu</code>: 伊是个好人。 | ||
| + | ** <code>eng</code>: He is a good person. | ||
| + | ** lexical transfer output: ^伊<prn><pers><p3><sg>/he<prn><subj><p3><m><sg>/it<prn><subj><p3><nt><sg>/her<prn><obj><p3><f><sg>/him<prn><obj><p3><m><sg>/his<prn><pos><p3><m><sg>/she<prn><subj><p3><f><sg>/hers<prn><pos><p3><f><sg>$ ^是<vblex>/is<vblex><p3><sg>/was<vblex><p3><sg>$ ^个<part>/$ ^好<adj>/good<adj><sint>$ ^人<n>/person<n><sg>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: he #is good person . | ||
| + | |||
| + | * (45) <code>wuu</code>: 我要吃鱼跟海鲜。 | ||
| + | ** <code>eng</code>: I want to eat fish and seafood. | ||
| + | ** lexical transfer output: ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^要<vaux>/want<vblex>/will<vblex>/want to<vbmod>$ ^吃<vblex>/eat<vblex>/drink<vblex>$ ^鱼<n>/fish<n><sg>$ ^跟<cnjcoo>/and<cnjcoo>$ ^海鲜<n>/seafood<n><sg>$ ^.<sent>/.<sent> | ||
| + | ** full translation output: I #want to #eat fish and seafood . | ||
| + | |||
| + | ==Statistics about input files== | ||
| + | Evaluation Corpus: | ||
| + | **Number of words in reference: 8105 | ||
| + | **Number of words in test: 9263 | ||
| + | **Number of unknown words (marked with a star) in test: 4696 | ||
| + | **Percentage of unknown words: 50.70 % | ||
| + | |||
| + | Results when removing unknown-word marks (stars) | ||
| + | ------------------------------------------------------- | ||
| + | **Edit distance: 9777 | ||
| + | **Word error rate (WER): 120.63 % | ||
| + | **Number of position-independent correct words: 156 | ||
| + | **Position-independent word error rate (PER): 112.36 % | ||
| + | |||
| + | Development Corpus: | ||
| + | **Number of words in reference: 80 | ||
| + | **Number of words in test: 74 | ||
| + | **Number of unknown words (marked with a star) in test: 1 | ||
| + | **Percentage of unknown words: 1.35 % | ||
| + | |||
| + | Results when removing unknown-word marks (stars) | ||
| + | ------------------------------------------------------- | ||
| + | **Edit distance: 89 | ||
| + | **Word error rate (WER): 111.25 % | ||
| + | **Number of position-independent correct words: 4 | ||
| + | **Position-independent word error rate (PER): 95.00 % | ||
| + | |||
| + | ==Final Evaluation== | ||
| + | The goal of this project was to develop a simple yet intelligible translation system from Shanghainese to English. While there is still a long way to go, the current progress demonstrates that this goal is achievable. Currently, the system produces literal or direct translations. As a result, the English output may lack grammatical function words such as "the" or "a," which are typically absent in Shanghainese. A key future improvement would be refining the translations to produce more grammatically correct English, making the system more robust. Another issue to address is the handling of verb tags, which currently affect the system’s accuracy. | ||
| + | |||
| + | As for the evaluation, the current WER and PER are relatively high. However, there's been an great improvement, over a 10% increase in performance, after expanding the development corpus from 10 to over 40 sentences. The high error rates can likely be attributed to incomplete verb tagging and perhaps the limited amount of structural transfer rules. | ||
| + | |||
| + | Based on the examples shown on this wiki, the system performs reasonably well on simple sentence structures and produces intelligible translations. With continued refinement, especially in grammatical handling and structural rules, the system will become more defined. Most importantly, this project demonstrates that it is possible to build translation systems even for languages with different grammatical structures. | ||
| + | |||
| + | [[Category:Sp25_FinalProjects]] [[Category:Shanghainese]] | ||
Latest revision as of 16:33, 24 July 2025
Contents
Resources for machine translation between Shanghainese and English
- Resources developed for Shanghainese:
- Link to resources developed for Shanghainese: [1]
- Resources developed for English:
External Resources
- Link to Shanghainese to English PUBLIC language pair: [2]
- Link to repository language pair:[3]
- Link to Shanghainese repository transducer:[4]
- Link to English repository transducer:[5]
- Link to Shanghainese to English Text: [6]
Shanghainese wuu → English eng Sentence Evaluation
Sentences
- (1)
wuu: 我爱侬。-
eng: I love you. - lexical transfer output: ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^爱<vblex>/love<vblex>$ ^侬<prn><pers><p2><sg>/you<prn><pers><p2><mf><sg>$ ^.<sent>/.<sent>
- full translation output: I #love you .
-
- (2)
wuu: 我有很多朋友。-
eng: I have many friends. - lexical transfer output: ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^有<vblex>/have<vblex>$ ^很多<adj>/many<det><qnt><pl>$ ^朋友<n>/friend<n><pl>$ ^.<sent>/.<sent>
- full translation output: I #have many friends .
-
- (3)
wuu: 侬欢喜唱歌伐？-
eng: Do you like singing? - lexical transfer output: ^侬<prn><pers><p2><sg>/you<prn><pers><p2><mf><sg>$ ^欢喜<vblex>/like<vblex>$ ^唱歌<n>/singing<n><sg>$ ^伐<qst>/$ ^.<sent>/.<sent>
- full translation output: you #like singing ?
-
- (4)
wuu: 早上好。-
eng: Good morning. - lexical transfer output: ^早上好<ij>/good morning<ij>$ ^.<sent>/.<sent>
- full translation output: good morning .
-
- (5)
wuu: 侬要吃茶还是吃咖啡啊？-
eng: Do you want to drink tea or coffee? - lexical transfer output: ^侬<prn><pers><p2><sg>/you<prn><pers><p2><mf><sg>$ ^要<vaux>/want<vblex>/will<vblex>/want to<vbmod>$ ^吃<vblex>/eat<vblex>/drink<vblex>$ ^茶<n>/tea<n><sg>$ ^还是<cnjcoo>/or<cnjcoo>$ ^吃<vblex>/eat<vblex>/drink<vblex>$ ^咖啡<n>/coffee<n><sg>$ ^啊<part>/$ ^.<sent>/.<sent>
- full translation output: you #want to #drink tea or #drink coffee ?
-
- (6)
wuu: 是我个，勿是伊个。-
eng: It's mine, not his. - lexical transfer output: ^是<vblex>/is<vblex><p3><sg>/was<vblex><p3><sg>$ ^我<prn><pers><p1><sg><pos>/I<prn><subj><p1><mf><sg><pos>$ ^，<cm>/,<cm>$ ^勿是<vaux>/not<adv>$ ^伊<prn><pers><p3><sg><pos>/he<prn><subj><p3><m><sg><pos>/it<prn><subj><p3><nt><sg><pos>/her<prn><obj><p3><f><sg><pos>/him<prn><obj><p3><m><sg><pos>/his<prn><pos><p3><m><sg><pos>/she<prn><subj><p3><f><sg><pos>/hers<prn><pos><p3><f><sg><pos>$ ^.<sent>/.<sent>
- full translation output: #is my , not his .
-
- (7)
wuu: 搿是我个行李。-
eng: Here is my baggage. - lexical transfer output: ^搿<adv>/here<adv>$ ^是<vblex>/is<vblex><p3><sg>/was<vblex><p3><sg>$ ^我<prn><pers><p1><sg><pos>/I<prn><subj><p1><mf><sg><pos>$ ^行李<n>/baggage<n><sg>$ ^.<sent>/.<sent>
- full translation output: here #is my baggage .
-
- (8)
wuu: 伊是法国人。-
eng: She is French. or He is French. - lexical transfer output: ^伊<prn><pers><p3><sg>/he<prn><subj><p3><m><sg>/it<prn><subj><p3><nt><sg>/her<prn><obj><p3><f><sg>/him<prn><obj><p3><m><sg>/his<prn><pos><p3><m><sg>/she<prn><subj><p3><f><sg>/hers<prn><pos><p3><f><sg>$ ^是<vblex>/is<vblex><p3><sg>/was<vblex><p3><sg>$ ^法国人<n>/French<n><pl>$ ^.<sent>/.<sent>
- full translation output: he #is French .
-
- (9)
wuu: 我每天六点钟起床。-
eng: I get up at six every day. - lexical transfer output: ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^每天<adv>/every day<adv>$ ^六点钟<n>/six<num><pl>$ ^起床<vblex>/wake up<vblex>$ ^.<sent>/.<sent>
- full translation output: I every day six #wake up .
-
- (10)
wuu: 一、二、三、四、五、六、七、八、九、十。-
eng: One, two, three, four, five, six, seven, right, nine, ten. - lexical transfer output: ^一<num>/one<num><sg>$ ^、<cm>/,<cm>$ ^二<num>/two<num><pl>$ ^、<cm>/,<cm>$ ^三<num>/three<num><pl>$ ^、<cm>/,<cm>$ ^四<num>/four<num><pl>$ ^、<cm>/,<cm>$ ^五<num>/five<num><pl>$ ^、<cm>/,<cm>$ ^六<num>/six<num><pl>$ ^、<cm>/,<cm>$ ^七<num>/seven<num><pl>$ ^、<cm>/,<cm>$ ^八<num>/eight<num><pl>$ ^、<cm>/,<cm>$ ^九<num>/nine<num><pl>$ ^、<cm>/,<cm>$ ^十<num>/ten<num><pl>$ ^.<sent>/.<sent>
- full translation output: one , two , three , four , five , six , seven , eight , nine , ten .
-
- (11)
wuu: 侬要走啦？-
eng: Do you want to go? - lexical transfer output: ^侬<prn><pers><p2><sg>/you<prn><pers><p2><mf><sg>$ ^要<vaux>/want<vblex>/will<vblex>/want to<vbmod>$ ^走<vblex>/go<vblex>$ ^啦<part>/$ ^.<sent>/.<sent>
- full translation output: you #want to #go ?
-
- (12)
wuu: 麻烦侬了。-
eng: Sorry to trouble you. - lexical transfer output: ^麻烦<vblex>/trouble<vblex>$ ^侬<prn><pers><p2><sg>/you<prn><pers><p2><mf><sg>$ ^了<part>/$ ^.<sent>/.<sent>
- full translation output: #trouble you .
-
- (13)
wuu: 我老勿好意思个。-
eng: I'm too ashamed. - lexical transfer output: ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^老<adv>/too<adv>$ ^勿好意思<adj>/ashamed<adj>$ ^个<part>/$ ^.<sent>/.<sent>
- full translation output: I too ashamed .
-
- (14)
wuu: 谢谢侬噢！-
eng: Thank you! - lexical transfer output: ^谢谢<vblex>/thank<vblex>$ ^侬<prn><pers><p2><sg>/you<prn><pers><p2><mf><sg>$ ^噢<part>/$ ^.<sent>/.<sent>
- full translation output: #thank you .
-
- (15)
wuu: 昨日是啥个天气？-
eng: What was the weather yesterday? - lexical transfer output: ^昨日<n>/yesterday<n><sg>$ ^是<vblex>/is<vblex><p3><sg>/was<vblex><p3><sg>$ ^啥<prn><itg>/what<prn><itg><mf><sp>$ ^个<part>/$ ^天气<n>/weather<n><sg>$ ^.<sent>/.<sent>
- full translation output: yesterday #is what weather ?
-
- (16)
wuu: 明朝要落雪。-
eng: It will snow tomorrow. - lexical transfer output: ^明朝<n>/tomorrow<n><sg>$ ^要<vaux>/want<vblex>/will<vblex>/want to<vbmod>$ ^落雪<vblex>/snow<vblex>$ ^.<sent>/.<sent>
- full translation output: tomorrow #will #snow .
-
- (17)
wuu: 侬住拉阿里搭？-
eng: Where do you live? - lexical transfer output: ^侬<prn><pers><p2><sg>/you<prn><pers><p2><mf><sg>$ ^住<vblex>/live<vblex>$ ^拉<pr>/at<pr>$ ^阿里搭<adv>/where<adv><itg>$ ^.<sent>/.<sent>
- full translation output: you #live at where ?
-
- (18)
wuu: 侬要多少钞票？-
eng: How much money do you want? - lexical transfer output: ^侬<prn><pers><p2><sg>/you<prn><pers><p2><mf><sg>$ ^要<vaux>/want<vblex>/will<vblex>/want to<vbmod>$ ^多少<adv>/how much<adv><itg>$ ^钞票<n>/money<n><sg>$ ^.<sent>/.<sent>
- full translation output: you #want how much money ?
-
- (19)
wuu: 对勿起。-
eng: Excuse me. - lexical transfer output: ^对勿起<ij>/excuse me<ij>$ ^.<sent>/.<sent>
- full translation output: excuse me .
-
- (20)
wuu: 侬非常勇敢。-
eng: You are very brave. - lexical transfer output: ^侬<prn><pers><p2><sg>/you<prn><pers><p2><mf><sg>$ ^非常<adv>/very<adv>$ ^勇敢<adj>/brave<adj><sint>$ ^.<sent>/.<sent>
- full translation output: you very brave .
-
- (21)
wuu: 侬选好了伐？-
eng: Have you chosen? - lexical transfer output: ^侬<prn><pers><p2><sg>/you<prn><pers><p2><mf><sg>$ ^选好<vblex>/chose<vblex>$ ^了<part>/$ ^伐<qst>/$ ^.<sent>/.<sent>
- full translation output: you #chose ?
-
- (22)
wuu: 够了。-
eng: That's enough. - lexical transfer output: ^够<adv>/enough<adv>$ ^了<part>/$ ^.<sent>/.<sent>
- full translation output: enough .
-
- (23)
wuu: 皮带是棕颜色个。-
eng: The belt is brown. - lexical transfer output: ^皮带<n>/belt<n><sg>$ ^是<vblex>/is<vblex><p3><sg>/was<vblex><p3><sg>$ ^棕颜色<adj>/brown<adj><sint>$ ^个<part>/$ ^.<sent>/.<sent>
- full translation output: belt #is brown .
-
- (24)
wuu: 我欢喜我个闲话。-
eng: I like my language. - lexical transfer output: ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^欢喜<vblex>/like<vblex>$ ^我<prn><pers><p1><sg><pos>/I<prn><subj><p1><mf><sg><pos>$ ^闲话<n>/language<n><sg>$ ^.<sent>/.<sent>
- full translation output: I #like my language .
-
- (25)
wuu: 我有一支笔。-
eng: I have a pen. - lexical transfer output: ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^有<vblex>/have<vblex>$ ^一<num>/one<num><sg>$ ^支<part>/$ ^笔<n>/pen<n><sg>$ ^.<sent>/.<sent>
- full translation output: I #have one pen .
-
- (26)
wuu: 有四个方向，东，南，西，北。-
eng: There are four cardinal points, East, south, west and north. - lexical transfer output: ^有<vblex>/have<vblex>$ ^四<num>/four<num><pl>$ ^个<part>/$ ^方向<n>/direction<n><pl>$ ^，<cm>/,<cm>$ ^东<adj>/east<adj>$ ^，<cm>/,<cm>$ ^南<adj>/south<adj><sint>$ ^，<cm>/,<cm>$ ^西<adj>/west<adj>$ ^，<cm>/,<cm>$ ^北<adj>/north<adj><sint>$ ^.<sent>/.<sent>
- full translation output: #have four directions , east , south , west , north .
-
- (27)
wuu: 一年有四季，春夏秋冬。-
eng: There are four seasons in a year, spring, summer, fall and winter. - lexical transfer output: ^一<num>/one<num><sg>$ ^年<n>/year<n><sg>$ ^有<vblex>/have<vblex>$ ^四<num>/four<num><pl>$ ^季<n>/season<n><pl>$ ^，<cm>/,<cm>$ ^春<n>/spring<n><sg>$ ^夏<n>/summer<n><sg>$ ^秋<n>/autumn<n><sg>$ ^冬<n>/winter<n><sg>$ ^.<sent>/.<sent>
- full translation output: one year #have four seasons , spring summer autumn winter .
-
- (28)
wuu: 请拿。-
eng: Take it, please. - lexical transfer output: ^请<ij>/please<ij>$ ^拿<vblex>/take<vblex>$ ^.<sent>/.<sent>
- full translation output: please #take .
-
- (29)
wuu: 我是游客。-
eng: I'm a tourist. - lexical transfer output: ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^是<vblex>/is<vblex><p3><sg>/was<vblex><p3><sg>$ ^游客<n>/tourist<n><sg>$ ^.<sent>/.<sent>
- full translation output: I #is tourist .
-
- (30)
wuu: 现在我可以走了𠲎？-
eng: Can I leave now? - lexical transfer output: ^现在<adv>/now<adv>$ ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^可以<vbmod>/can<vbmod>$ ^走<vblex>/go<vblex>$ ^了<part>/$ ^.<sent>/.<sent>
- full translation output: now I #can #go ?
-
- (31)
wuu: 我会得弹钢琴。-
eng: I can play piano. - lexical transfer output: ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^会得<vbmod>/can<vbmod>$ ^弹<vblex>/play<vblex>$ ^钢琴<n>/piano<n><sg>$ ^.<sent>/.<sent>
- full translation output: I #can #play piano .
-
- (32)
wuu: 打网球是伊个兴趣。-
eng: Playing tennis is his hobby. - lexical transfer output: ^打<vblex>/play<vblex>$ ^网球<n>/tennis<n><sg>$ ^是<vblex>/is<vblex><p3><sg>/was<vblex><p3><sg>$ ^伊<prn><pers><p3><sg><pos>/he<prn><subj><p3><m><sg><pos>/it<prn><subj><p3><nt><sg><pos>/her<prn><obj><p3><f><sg><pos>/him<prn><obj><p3><m><sg><pos>/his<prn><pos><p3><m><sg><pos>/she<prn><subj><p3><f><sg><pos>/hers<prn><pos><p3><f><sg><pos>$ ^兴趣<n>/hobby<n><sg>$ ^.<sent>/.<sent>
- full translation output: #play tennis #is his hobby .
-
- (33)
wuu: 勿是我个。-
eng: It's not mine. - lexical transfer output: ^勿是<vaux>/not<adv>$ ^我<prn><pers><p1><sg><pos>/I<prn><subj><p1><mf><sg><pos>$ ^.<sent>/.<sent>
- full translation output: not my .
-
- (34)
wuu: 我學習中國言話。-
eng: I learn Chinese. - lexical transfer output: ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^學習<vblex>/study<vblex>$ ^中國言話<adj>/Chinese<adj>$ ^.<sent>/.<sent>
- full translation output: I #study Chinese .
-
- (35)
wuu: 我申请了签证。-
eng: I applied for a visa. - lexical transfer output: ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^申请<vblex>/apply<vblex>$ ^了<part>/$ ^签证<n>/visa<n><sg>$ ^.<sent>/.<sent>
- full translation output: I #apply visa .
-
- (36)
wuu: 吾欢喜吾个工作。-
eng: I like my job. - lexical transfer output: ^吾<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^欢喜<vblex>/like<vblex>$ ^吾<prn><pers><p1><sg><pos>/I<prn><subj><p1><mf><sg><pos>$ ^工作<n>/job<n><sg>$ ^.<sent>/.<sent>
- full translation output: I #like my job .
-
- (37)
wuu: 生日快乐!-
eng: Happy birthday! - lexical transfer output: ^生日快乐<ij>/Happy birthday<ij>$ ^.<sent>/.<sent>
- full translation output: Happy birthday !
-
- (38)
wuu: 再会！-
eng: Bye! - lexical transfer output: ^再会<ij>/bye<ij>$ ^.<sent>/.<sent>
- full translation output: bye .
-
- (39)
wuu: 房间里向有老多学生子。-
eng: There are many students in the room. - lexical transfer output: ^房间<n>/room<n><sg>$ ^里向<n>/in<adv>$ ^有<vblex>/have<vblex>$ ^老<adv>/too<adv>$ ^多<adj>/many<det><qnt><pl>$ ^学生子<n>/student<n><pl>$ ^.<sent>/.<sent>
- full translation output: room in #have too many students .
-
- (40)
wuu: 伊会得讲十种语言。-
eng: He can speak ten languages. - lexical transfer output: ^伊<prn><pers><p3><sg>/he<prn><subj><p3><m><sg>/it<prn><subj><p3><nt><sg>/her<prn><obj><p3><f><sg>/him<prn><obj><p3><m><sg>/his<prn><pos><p3><m><sg>/she<prn><subj><p3><f><sg>/hers<prn><pos><p3><f><sg>$ ^会得<vbmod>/can<vbmod>$ ^讲<vblex>/speak<vblex>$ ^十<num>/ten<num><pl>$ ^种<part>/$ ^语言<n>/language<n><pl>$ ^.<sent>/.<sent>
- full translation output: he #can #speak ten languages .
-
- (41)
wuu: 吾嘴巴干。-
eng: I'm thirsty. - lexical transfer output: ^吾<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^嘴<n>/mouth<n><sg>$ ^巴干<vblex>/dry<vblex>$ ^.<sent>/.<sent>
- full translation output: I mouth #dry .
-
- (42)
wuu: 吾肚皮饿了。-
eng: I am hungry. - lexical transfer output: ^吾<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^肚皮<n>/stomach<n><sg>$ ^饿<vblex>/hungry<vblex>$ ^了<part>/$ ^.<sent>/.<sent>
- full translation output: I stomach #hungry
-
- (43)
wuu: 吾肚皮痛。-
eng: I have a stomachache. - lexical transfer output: ^吾<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^肚皮<n>/stomach<n><sg>$ ^痛<n>/ache<n><pl>$ ^.<sent>/.<sent>
- full translation output: I stomach aches .
-
- (44)
wuu: 伊是个好人。-
eng: He is a good person. - lexical transfer output: ^伊<prn><pers><p3><sg>/he<prn><subj><p3><m><sg>/it<prn><subj><p3><nt><sg>/her<prn><obj><p3><f><sg>/him<prn><obj><p3><m><sg>/his<prn><pos><p3><m><sg>/she<prn><subj><p3><f><sg>/hers<prn><pos><p3><f><sg>$ ^是<vblex>/is<vblex><p3><sg>/was<vblex><p3><sg>$ ^个<part>/$ ^好<adj>/good<adj><sint>$ ^人<n>/person<n><sg>$ ^.<sent>/.<sent>
- full translation output: he #is good person .
-
- (45)
wuu: 我要吃鱼跟海鲜。-
eng: I want to eat fish and seafood. - lexical transfer output: ^我<prn><pers><p1><sg>/I<prn><subj><p1><mf><sg>$ ^要<vaux>/want<vblex>/will<vblex>/want to<vbmod>$ ^吃<vblex>/eat<vblex>/drink<vblex>$ ^鱼<n>/fish<n><sg>$ ^跟<cnjcoo>/and<cnjcoo>$ ^海鲜<n>/seafood<n><sg>$ ^.<sent>/.<sent>
- full translation output: I #want to #eat fish and seafood .
-
Statistics about input files
Evaluation Corpus:
- Number of words in reference: 8105
- Number of words in test: 9263
- Number of unknown words (marked with a star) in test: 4696
- Percentage of unknown words: 50.70 %
Results when removing unknown-word marks (stars)
- Edit distance: 9777
- Word error rate (WER): 120.63 %
- Number of position-independent correct words: 156
- Position-independent word error rate (PER): 112.36 %
Development Corpus:
- Number of words in reference: 80
- Number of words in test: 74
- Number of unknown words (marked with a star) in test: 1
- Percentage of unknown words: 1.35 %
Results when removing unknown-word marks (stars)
- Edit distance: 89
- Word error rate (WER): 111.25 %
- Number of position-independent correct words: 4
- Position-independent word error rate (PER): 95.00 %
Final Evaluation
The goal of this project was to develop a simple yet intelligible translation system from Shanghainese to English. While there is still a long way to go, the current progress demonstrates that this goal is achievable. Currently, the system produces literal or direct translations. As a result, the English output may lack grammatical function words such as "the" or "a," which are typically absent in Shanghainese. A key future improvement would be refining the translations to produce more grammatically correct English, making the system more robust. Another issue to address is the handling of verb tags, which currently affect the system’s accuracy.
As for the evaluation, the current WER and PER are relatively high. However, there's been an great improvement, over a 10% increase in performance, after expanding the development corpus from 10 to over 40 sentences. The high error rates can likely be attributed to incomplete verb tagging and perhaps the limited amount of structural transfer rules.
Based on the examples shown on this wiki, the system performs reasonably well on simple sentence structures and produces intelligible translations. With continued refinement, especially in grammatical handling and structural rules, the system will become more defined. Most importantly, this project demonstrates that it is possible to build translation systems even for languages with different grammatical structures.
