From 1067e0c26d238f4274a5292438b8703fd2b33051 Mon Sep 17 00:00:00 2001 From: Simone Conia Date: Sun, 5 Jan 2025 19:26:52 +0100 Subject: [PATCH] Deploy website - based on 45e48beb4023f6502e4f2f235af9a9a7b2c5d915 --- 404.html | 2 +- assets/js/ef9b9427.064c6919.js | 1 + assets/js/ef9b9427.8f2f846f.js | 1 - ...n.c20d8f80.js => runtime~main.dea8b065.js} | 2 +- docs/about_us.html | 2 +- docs/category/the-ea-mt-task.html | 2 +- docs/contact_us.html | 2 +- docs/task/data.html | 2 +- docs/task/evaluation.html | 2 +- docs/task/important_dates.html | 2 +- docs/task/introduction.html | 47 ++++++++++++++++++- docs/task/submission.html | 2 +- index.html | 2 +- news.html | 2 +- news/archive.html | 2 +- news/welcome.html | 2 +- 16 files changed, 59 insertions(+), 16 deletions(-) create mode 100644 assets/js/ef9b9427.064c6919.js delete mode 100644 assets/js/ef9b9427.8f2f846f.js rename assets/js/{runtime~main.c20d8f80.js => runtime~main.dea8b065.js} (58%) diff --git a/404.html b/404.html index b2aba3b..5974bb0 100644 --- a/404.html +++ b/404.html @@ -5,7 +5,7 @@ Page Not Found | SemEval 2025 - Task 2: EA-MT - + diff --git a/assets/js/ef9b9427.064c6919.js b/assets/js/ef9b9427.064c6919.js new file mode 100644 index 0000000..368266c --- /dev/null +++ b/assets/js/ef9b9427.064c6919.js @@ -0,0 +1 @@ +"use strict";(self.webpackChunkea_mt_website=self.webpackChunkea_mt_website||[]).push([[805],{4507:(e,n,t)=>{t.r(n),t.d(n,{assets:()=>l,contentTitle:()=>o,default:()=>d,frontMatter:()=>a,metadata:()=>r,toc:()=>h});var i=t(4848),s=t(8453);const a={sidebar_label:"Introduction",sidebar_position:1},o="Introduction",r={id:"task/introduction",title:"Introduction",description:"This is a 2-minute introduction to our task, Entity-Aware Machine Translation (EA-MT), for SemEval-2025.",source:"@site/docs/task/introduction.md",sourceDirName:"task",slug:"/task/introduction",permalink:"/ea-mt/docs/task/introduction",draft:!1,unlisted:!1,tags:[],version:"current",sidebarPosition:1,frontMatter:{sidebar_label:"Introduction",sidebar_position:1},sidebar:"taskSidebar",previous:{title:"The EA-MT Task",permalink:"/ea-mt/docs/category/the-ea-mt-task"},next:{title:"Important Dates",permalink:"/ea-mt/docs/task/important_dates"}},l={},h=[{value:"What is SemEval?",id:"what-is-semeval",level:2},{value:"EA-MT: Entity-Aware Machine Translation",id:"ea-mt-entity-aware-machine-translation",level:2},{value:"What is it about?",id:"what-is-it-about",level:3},{value:"Why is it important?",id:"why-is-it-important",level:3},{value:"How can you participate?",id:"how-can-you-participate",level:3},{value:"Is my system good enough?",id:"is-my-system-good-enough",level:3},{value:"Negative Results",id:"negative-results",level:4},{value:"Write a system paper",id:"write-a-system-paper",level:3},{value:"Examples",id:"examples",level:3},{value:"Example 1: English to French",id:"example-1-english-to-french",level:4},{value:"Example 2: English to Italian",id:"example-2-english-to-italian",level:4},{value:"Example 3: English to Chinese",id:"example-3-english-to-chinese",level:4},{value:"Example 4: English to Korean",id:"example-4-english-to-korean",level:4},{value:"Language Pairs",id:"language-pairs",level:3},{value:"Next steps",id:"next-steps",level:2}];function c(e){const n={a:"a",admonition:"admonition",em:"em",h1:"h1",h2:"h2",h3:"h3",h4:"h4",img:"img",li:"li",p:"p",strong:"strong",ul:"ul",...(0,s.R)(),...e.components};return(0,i.jsxs)(i.Fragment,{children:[(0,i.jsx)(n.h1,{id:"introduction",children:"Introduction"}),"\n",(0,i.jsx)(n.p,{children:"This is a 2-minute introduction to our task, Entity-Aware Machine Translation (EA-MT), for SemEval-2025."}),"\n",(0,i.jsx)(n.h2,{id:"what-is-semeval",children:"What is SemEval?"}),"\n",(0,i.jsxs)(n.p,{children:[(0,i.jsx)(n.strong,{children:"SemEval"})," is a long-standing series of international natural language processing (NLP) research workshops whose mission is to advance the current state of the art in semantic analysis and to help create high-quality annotated datasets in a range of increasingly challenging problems in natural language semantics."]}),"\n",(0,i.jsx)(n.admonition,{title:"More on SemEval",type:"note",children:(0,i.jsxs)(n.p,{children:["You can find more information about SemEval on the ",(0,i.jsx)(n.a,{href:"https://semeval.github.io/",children:"official website"}),"."]})}),"\n",(0,i.jsx)(n.h2,{id:"ea-mt-entity-aware-machine-translation",children:"EA-MT: Entity-Aware Machine Translation"}),"\n",(0,i.jsxs)(n.p,{children:["Let's dive into our SemEval-2025 task, ",(0,i.jsx)(n.strong,{children:"Entity-Aware Machine Translation (EA-MT)"}),"."]}),"\n",(0,i.jsx)(n.p,{children:(0,i.jsx)(n.img,{alt:"Background Image",src:t(5863).A+"",width:"1792",height:"1024"})}),"\n",(0,i.jsx)(n.h3,{id:"what-is-it-about",children:"What is it about?"}),"\n",(0,i.jsxs)(n.p,{children:["We invite participants to develop machine translation systems that can accurately translate text that includes potentially challenging named entities in the source language. ",(0,i.jsx)(n.strong,{children:"The task is to translate a given input sentence from the source language (English) to the target language, where the input sentence contains named entities that may be challenging for machine translation systems to handle"}),". The named entities may be entities that are rare, ambiguous, or unknown to the machine translation system. The task is to develop machine translation systems that can accurately translate such named entities in the input sentence to the target language."]}),"\n",(0,i.jsx)(n.h3,{id:"why-is-it-important",children:"Why is it important?"}),"\n",(0,i.jsxs)(n.p,{children:["We believe that the ability to accurately translate named entities is crucial for machine translation systems to be effective in real-world scenarios. Named entities are entities that are referred to by ",(0,i.jsx)(n.em,{children:"proper names"}),", such as people, organizations, locations, dates, and more. Named entities are often challenging even for human translators, as sometimes there are ",(0,i.jsx)(n.em,{children:"cultural or domain-specific references"})," that are not easily translatable. This happens more often for some entity types or categories, such as movies, books, TV series, products, and more."]}),"\n",(0,i.jsx)(n.h3,{id:"how-can-you-participate",children:"How can you participate?"}),"\n",(0,i.jsx)(n.p,{children:"There are several ways to participate in the EA-MT task:"}),"\n",(0,i.jsxs)(n.ul,{children:["\n",(0,i.jsxs)(n.li,{children:["\n",(0,i.jsxs)(n.p,{children:[(0,i.jsx)(n.strong,{children:"Fine-tune an existing model"}),": You can fine-tune an existing MT model or LLM on the provided training data. For example:"]}),"\n",(0,i.jsxs)(n.ul,{children:["\n",(0,i.jsxs)(n.li,{children:["You can use popular pre-trained models, such as ",(0,i.jsx)(n.a,{href:"https://huggingface.co/transformers/model_doc/marian.html",children:"MarianMT"}),", ",(0,i.jsx)(n.a,{href:"https://huggingface.co/facebook/m2m100_418M",children:"M2M-100"}),", ",(0,i.jsx)(n.a,{href:"https://huggingface.co/transformers/model_doc/t5.html",children:"T5"}),", and more."]}),"\n",(0,i.jsx)(n.li,{children:"You can use popular LLMs, such as Llama-3, Qwen-2, and more."}),"\n"]}),"\n"]}),"\n",(0,i.jsxs)(n.li,{children:["\n",(0,i.jsxs)(n.p,{children:[(0,i.jsx)(n.strong,{children:"Develop your own machine translation system"}),": You can develop your own machine translation system using your preferred tools and techniques."]}),"\n",(0,i.jsxs)(n.ul,{children:["\n",(0,i.jsx)(n.li,{children:"You can add named entity recognition (NER), entity linking (EL), or other modules to your machine translation system to improve the translation of named entities."}),"\n",(0,i.jsx)(n.li,{children:"You can use data augmentation techniques to improve the performance of your machine translation system."}),"\n"]}),"\n"]}),"\n",(0,i.jsxs)(n.li,{children:["\n",(0,i.jsxs)(n.p,{children:[(0,i.jsx)(n.strong,{children:"Use external systems"}),": You can use external systems, APIs, or services to improve the performance of your machine translation system."]}),"\n",(0,i.jsxs)(n.ul,{children:["\n",(0,i.jsx)(n.li,{children:"You can use GPT-4, Gemini, Claude or other commercial LLMs and build on top of them."}),"\n"]}),"\n"]}),"\n"]}),"\n",(0,i.jsx)(n.h3,{id:"is-my-system-good-enough",children:"Is my system good enough?"}),"\n",(0,i.jsx)(n.p,{children:'The final result is not the only thing that matters: we know that comparing a small BERT-based model with GPT4o or Gemini is not "fair". This shared task is not about winning, but about learning, and sharing. For example:'}),"\n",(0,i.jsxs)(n.ul,{children:["\n",(0,i.jsx)(n.li,{children:(0,i.jsx)(n.em,{children:"Did you find that a simple model works almost as well as a complex one but is much faster?"})}),"\n",(0,i.jsx)(n.li,{children:(0,i.jsx)(n.em,{children:"Did you try a new data augmentation technique?"})}),"\n",(0,i.jsx)(n.li,{children:(0,i.jsx)(n.em,{children:"Did you experiment with a new architecture?"})}),"\n",(0,i.jsx)(n.li,{children:(0,i.jsx)(n.em,{children:"Did you try to fine-tune a model on a new dataset?"})}),"\n",(0,i.jsx)(n.li,{children:(0,i.jsx)(n.em,{children:"Did you try to combine different models?"})}),"\n",(0,i.jsx)(n.li,{children:(0,i.jsx)(n.em,{children:"Did you try to use external systems to improve your model?"})}),"\n",(0,i.jsx)(n.li,{children:(0,i.jsx)(n.em,{children:"What is the extent of the improvement you achieved by combining different techniques?"})}),"\n"]}),"\n",(0,i.jsx)(n.p,{children:"For example, sometimes it may be more interesting to see a super fast model that is 10% worse than the best model, but that can be used in real-world scenarios. Or there may be techniques that are more effective for certain types of named entities, or for certain language pairs."}),"\n",(0,i.jsx)(n.h4,{id:"negative-results",children:"Negative Results"}),"\n",(0,i.jsx)(n.p,{children:"Negative results are also welcome! If you tried something and it didn't work, that's valuable information too. It can help others avoid the same pitfalls and save time in the future."}),"\n",(0,i.jsx)(n.h3,{id:"write-a-system-paper",children:"Write a system paper"}),"\n",(0,i.jsx)(n.p,{children:"We encourage participants to write a system paper describing their approach, the techniques they used, the results they obtained, and the lessons they learned. The system paper will be submitted to the SemEval workshop for review and publication: this is a great opportunity to showcase your work with the NLP community."}),"\n",(0,i.jsxs)(n.ul,{children:["\n",(0,i.jsx)(n.li,{children:"We will provide a template for the system paper, and we will give you detailed instructions on how to write it at the end of January 2025."}),"\n"]}),"\n",(0,i.jsx)(n.h3,{id:"examples",children:"Examples"}),"\n",(0,i.jsx)(n.p,{children:"Here are some examples of sentences that you may encounter in the EA-MT task:"}),"\n",(0,i.jsx)(n.h4,{id:"example-1-english-to-french",children:"Example 1: English to French"}),"\n",(0,i.jsxs)(n.ul,{children:["\n",(0,i.jsxs)(n.li,{children:[(0,i.jsx)(n.strong,{children:"English Sentence"}),": \"I watched the movie 'The Shawshank Redemption' last night.\""]}),"\n",(0,i.jsxs)(n.li,{children:[(0,i.jsx)(n.strong,{children:"French Sentence"}),": \"J'ai regard\xe9 le film 'Les \xc9vad\xe9s' hier soir.\""]}),"\n"]}),"\n",(0,i.jsx)(n.h4,{id:"example-2-english-to-italian",children:"Example 2: English to Italian"}),"\n",(0,i.jsxs)(n.ul,{children:["\n",(0,i.jsxs)(n.li,{children:[(0,i.jsx)(n.strong,{children:"English Sentence"}),": \"I bought a new book called 'The Catcher in the Rye'.\""]}),"\n",(0,i.jsxs)(n.li,{children:[(0,i.jsx)(n.strong,{children:"Italian Sentence"}),": \"Ho comprato un nuovo libro chiamato 'Il Giovane Holden'.\""]}),"\n"]}),"\n",(0,i.jsx)(n.h4,{id:"example-3-english-to-chinese",children:"Example 3: English to Chinese"}),"\n",(0,i.jsxs)(n.ul,{children:["\n",(0,i.jsxs)(n.li,{children:[(0,i.jsx)(n.strong,{children:"English Sentence"}),": \"I watched the TV series 'Breaking Bad' last week.\""]}),"\n",(0,i.jsxs)(n.li,{children:[(0,i.jsx)(n.strong,{children:"Chinese Sentence"}),': "\u6211\u4e0a\u5468\u770b\u4e86\u7535\u89c6\u5267\u300a\u7edd\u547d\u6bd2\u5e08\u300b\u3002"']}),"\n"]}),"\n",(0,i.jsx)(n.h4,{id:"example-4-english-to-korean",children:"Example 4: English to Korean"}),"\n",(0,i.jsxs)(n.ul,{children:["\n",(0,i.jsxs)(n.li,{children:[(0,i.jsx)(n.strong,{children:"English Sentence"}),": \"Who is the author of the book 'The Great Gatsby'?\""]}),"\n",(0,i.jsxs)(n.li,{children:[(0,i.jsx)(n.strong,{children:"Korean Sentence"}),": \"'\uc704\ub300\ud55c \uac1c\uce20\ube44'\uc758 \uc800\uc790\ub294 \ub204\uad6c\uc785\ub2c8\uae4c?\""]}),"\n"]}),"\n",(0,i.jsx)(n.h3,{id:"language-pairs",children:"Language Pairs"}),"\n",(0,i.jsx)(n.p,{children:"The EA-MT task will focus on the following language pairs:"}),"\n",(0,i.jsxs)(n.ul,{children:["\n",(0,i.jsx)(n.li,{children:"English to Arabic"}),"\n",(0,i.jsx)(n.li,{children:"English to Chinese"}),"\n",(0,i.jsx)(n.li,{children:"English to French"}),"\n",(0,i.jsx)(n.li,{children:"English to German"}),"\n",(0,i.jsx)(n.li,{children:"English to Italian"}),"\n",(0,i.jsx)(n.li,{children:"English to Japanese"}),"\n",(0,i.jsx)(n.li,{children:"English to Korean"}),"\n",(0,i.jsx)(n.li,{children:"English to Spanish"}),"\n",(0,i.jsx)(n.li,{children:"English to Thai"}),"\n",(0,i.jsx)(n.li,{children:"English to Turkish"}),"\n"]}),"\n",(0,i.jsx)(n.admonition,{type:"note",children:(0,i.jsx)(n.p,{children:"This edition of EA-MT will focus on translating from English to the target languages mentioned above. We may consider adding more language pairs in future editions."})}),"\n",(0,i.jsx)(n.h2,{id:"next-steps",children:"Next steps"}),"\n",(0,i.jsx)(n.p,{children:"Please, stay tuned for more updates on the EA-MT task for SemEval-2025. We will be releasing more information on the dataset, evaluation metrics, and submission guidelines soon. If you have any questions, feel free to reach out to us."}),"\n",(0,i.jsx)(n.admonition,{title:"Join the Google Group",type:"tip",children:(0,i.jsxs)(n.p,{children:["We invite you to join our Google Group for the latest updates and discussions: ",(0,i.jsx)(n.a,{href:"https://groups.google.com/a/uniroma1.it/g/semeval-2025-task-2-ea-mt",children:"SemEval 2025 - Task 2: EA-MT"}),"."]})})]})}function d(e={}){const{wrapper:n}={...(0,s.R)(),...e.components};return n?(0,i.jsx)(n,{...e,children:(0,i.jsx)(c,{...e})}):c(e)}},5863:(e,n,t)=>{t.d(n,{A:()=>i});const i=t.p+"assets/images/background-blurred-8b33d8c033c83c5049ad5ecc21e7fe67.jpg"},8453:(e,n,t)=>{t.d(n,{R:()=>o,x:()=>r});var i=t(6540);const s={},a=i.createContext(s);function o(e){const n=i.useContext(a);return i.useMemo((function(){return"function"==typeof e?e(n):{...n,...e}}),[n,e])}function r(e){let n;return n=e.disableParentContext?"function"==typeof e.components?e.components(s):e.components||s:o(e.components),i.createElement(a.Provider,{value:n},e.children)}}}]); \ No newline at end of file diff --git a/assets/js/ef9b9427.8f2f846f.js b/assets/js/ef9b9427.8f2f846f.js deleted file mode 100644 index 912b861..0000000 --- a/assets/js/ef9b9427.8f2f846f.js +++ /dev/null @@ -1 +0,0 @@ -"use strict";(self.webpackChunkea_mt_website=self.webpackChunkea_mt_website||[]).push([[805],{4507:(e,n,t)=>{t.r(n),t.d(n,{assets:()=>r,contentTitle:()=>l,default:()=>d,frontMatter:()=>s,metadata:()=>o,toc:()=>h});var i=t(4848),a=t(8453);const s={sidebar_label:"Introduction",sidebar_position:1},l="Introduction",o={id:"task/introduction",title:"Introduction",description:"This is a 2-minute introduction to our task, Entity-Aware Machine Translation (EA-MT), for SemEval-2025.",source:"@site/docs/task/introduction.md",sourceDirName:"task",slug:"/task/introduction",permalink:"/ea-mt/docs/task/introduction",draft:!1,unlisted:!1,tags:[],version:"current",sidebarPosition:1,frontMatter:{sidebar_label:"Introduction",sidebar_position:1},sidebar:"taskSidebar",previous:{title:"The EA-MT Task",permalink:"/ea-mt/docs/category/the-ea-mt-task"},next:{title:"Important Dates",permalink:"/ea-mt/docs/task/important_dates"}},r={},h=[{value:"What is SemEval?",id:"what-is-semeval",level:2},{value:"EA-MT: Entity-Aware Machine Translation",id:"ea-mt-entity-aware-machine-translation",level:2},{value:"What is it about?",id:"what-is-it-about",level:3},{value:"Why is it important?",id:"why-is-it-important",level:3},{value:"Examples",id:"examples",level:3},{value:"Example 1: English to French",id:"example-1-english-to-french",level:4},{value:"Example 2: English to Italian",id:"example-2-english-to-italian",level:4},{value:"Example 3: English to Chinese",id:"example-3-english-to-chinese",level:4},{value:"Example 4: English to Korean",id:"example-4-english-to-korean",level:4},{value:"Language Pairs",id:"language-pairs",level:3},{value:"Next steps",id:"next-steps",level:2}];function c(e){const n={a:"a",admonition:"admonition",em:"em",h1:"h1",h2:"h2",h3:"h3",h4:"h4",img:"img",li:"li",p:"p",strong:"strong",ul:"ul",...(0,a.R)(),...e.components};return(0,i.jsxs)(i.Fragment,{children:[(0,i.jsx)(n.h1,{id:"introduction",children:"Introduction"}),"\n",(0,i.jsx)(n.p,{children:"This is a 2-minute introduction to our task, Entity-Aware Machine Translation (EA-MT), for SemEval-2025."}),"\n",(0,i.jsx)(n.h2,{id:"what-is-semeval",children:"What is SemEval?"}),"\n",(0,i.jsxs)(n.p,{children:[(0,i.jsx)(n.strong,{children:"SemEval"})," is a long-standing series of international natural language processing (NLP) research workshops whose mission is to advance the current state of the art in semantic analysis and to help create high-quality annotated datasets in a range of increasingly challenging problems in natural language semantics."]}),"\n",(0,i.jsx)(n.admonition,{title:"More on SemEval",type:"note",children:(0,i.jsxs)(n.p,{children:["You can find more information about SemEval on the ",(0,i.jsx)(n.a,{href:"https://semeval.github.io/",children:"official website"}),"."]})}),"\n",(0,i.jsx)(n.h2,{id:"ea-mt-entity-aware-machine-translation",children:"EA-MT: Entity-Aware Machine Translation"}),"\n",(0,i.jsxs)(n.p,{children:["Let's dive into our SemEval-2025 task, ",(0,i.jsx)(n.strong,{children:"Entity-Aware Machine Translation (EA-MT)"}),"."]}),"\n",(0,i.jsx)(n.p,{children:(0,i.jsx)(n.img,{alt:"Background Image",src:t(5863).A+"",width:"1792",height:"1024"})}),"\n",(0,i.jsx)(n.h3,{id:"what-is-it-about",children:"What is it about?"}),"\n",(0,i.jsxs)(n.p,{children:["We invite participants to develop machine translation systems that can accurately translate text that includes potentially challenging named entities in the source language. ",(0,i.jsx)(n.strong,{children:"The task is to translate a given input sentence from the source language (English) to the target language, where the input sentence contains named entities that may be challenging for machine translation systems to handle"}),". The named entities may be entities that are rare, ambiguous, or unknown to the machine translation system. The task is to develop machine translation systems that can accurately translate such named entities in the input sentence to the target language."]}),"\n",(0,i.jsx)(n.h3,{id:"why-is-it-important",children:"Why is it important?"}),"\n",(0,i.jsxs)(n.p,{children:["We believe that the ability to accurately translate named entities is crucial for machine translation systems to be effective in real-world scenarios. Named entities are entities that are referred to by ",(0,i.jsx)(n.em,{children:"proper names"}),", such as people, organizations, locations, dates, and more. Named entities are often challenging even for human translators, as sometimes there are ",(0,i.jsx)(n.em,{children:"cultural or domain-specific references"})," that are not easily translatable. This happens more often for some entity types or categories, such as movies, books, TV series, products, and more."]}),"\n",(0,i.jsx)(n.h3,{id:"examples",children:"Examples"}),"\n",(0,i.jsx)(n.p,{children:"Here are some examples of sentences that you may encounter in the EA-MT task:"}),"\n",(0,i.jsx)(n.h4,{id:"example-1-english-to-french",children:"Example 1: English to French"}),"\n",(0,i.jsxs)(n.ul,{children:["\n",(0,i.jsxs)(n.li,{children:[(0,i.jsx)(n.strong,{children:"English Sentence"}),": \"I watched the movie 'The Shawshank Redemption' last night.\""]}),"\n",(0,i.jsxs)(n.li,{children:[(0,i.jsx)(n.strong,{children:"French Sentence"}),": \"J'ai regard\xe9 le film 'Les \xc9vad\xe9s' hier soir.\""]}),"\n"]}),"\n",(0,i.jsx)(n.h4,{id:"example-2-english-to-italian",children:"Example 2: English to Italian"}),"\n",(0,i.jsxs)(n.ul,{children:["\n",(0,i.jsxs)(n.li,{children:[(0,i.jsx)(n.strong,{children:"English Sentence"}),": \"I bought a new book called 'The Catcher in the Rye'.\""]}),"\n",(0,i.jsxs)(n.li,{children:[(0,i.jsx)(n.strong,{children:"Italian Sentence"}),": \"Ho comprato un nuovo libro chiamato 'Il Giovane Holden'.\""]}),"\n"]}),"\n",(0,i.jsx)(n.h4,{id:"example-3-english-to-chinese",children:"Example 3: English to Chinese"}),"\n",(0,i.jsxs)(n.ul,{children:["\n",(0,i.jsxs)(n.li,{children:[(0,i.jsx)(n.strong,{children:"English Sentence"}),": \"I watched the TV series 'Breaking Bad' last week.\""]}),"\n",(0,i.jsxs)(n.li,{children:[(0,i.jsx)(n.strong,{children:"Chinese Sentence"}),': "\u6211\u4e0a\u5468\u770b\u4e86\u7535\u89c6\u5267\u300a\u7edd\u547d\u6bd2\u5e08\u300b\u3002"']}),"\n"]}),"\n",(0,i.jsx)(n.h4,{id:"example-4-english-to-korean",children:"Example 4: English to Korean"}),"\n",(0,i.jsxs)(n.ul,{children:["\n",(0,i.jsxs)(n.li,{children:[(0,i.jsx)(n.strong,{children:"English Sentence"}),": \"Who is the author of the book 'The Great Gatsby'?\""]}),"\n",(0,i.jsxs)(n.li,{children:[(0,i.jsx)(n.strong,{children:"Korean Sentence"}),": \"'\uc704\ub300\ud55c \uac1c\uce20\ube44'\uc758 \uc800\uc790\ub294 \ub204\uad6c\uc785\ub2c8\uae4c?\""]}),"\n"]}),"\n",(0,i.jsx)(n.h3,{id:"language-pairs",children:"Language Pairs"}),"\n",(0,i.jsx)(n.p,{children:"The EA-MT task will focus on the following language pairs:"}),"\n",(0,i.jsxs)(n.ul,{children:["\n",(0,i.jsx)(n.li,{children:"English to Arabic"}),"\n",(0,i.jsx)(n.li,{children:"English to Chinese"}),"\n",(0,i.jsx)(n.li,{children:"English to French"}),"\n",(0,i.jsx)(n.li,{children:"English to German"}),"\n",(0,i.jsx)(n.li,{children:"English to Italian"}),"\n",(0,i.jsx)(n.li,{children:"English to Japanese"}),"\n",(0,i.jsx)(n.li,{children:"English to Korean"}),"\n",(0,i.jsx)(n.li,{children:"English to Spanish"}),"\n",(0,i.jsx)(n.li,{children:"English to Thai"}),"\n",(0,i.jsx)(n.li,{children:"English to Turkish"}),"\n"]}),"\n",(0,i.jsx)(n.admonition,{type:"note",children:(0,i.jsx)(n.p,{children:"This edition of EA-MT will focus on translating from English to the target languages mentioned above. We may consider adding more language pairs in future editions."})}),"\n",(0,i.jsx)(n.h2,{id:"next-steps",children:"Next steps"}),"\n",(0,i.jsx)(n.p,{children:"Please, stay tuned for more updates on the EA-MT task for SemEval-2025. We will be releasing more information on the dataset, evaluation metrics, and submission guidelines soon. If you have any questions, feel free to reach out to us."}),"\n",(0,i.jsx)(n.admonition,{title:"Join the Google Group",type:"tip",children:(0,i.jsxs)(n.p,{children:["We invite you to join our Google Group for the latest updates and discussions: ",(0,i.jsx)(n.a,{href:"https://groups.google.com/a/uniroma1.it/g/semeval-2025-task-2-ea-mt",children:"SemEval 2025 - Task 2: EA-MT"}),"."]})})]})}function d(e={}){const{wrapper:n}={...(0,a.R)(),...e.components};return n?(0,i.jsx)(n,{...e,children:(0,i.jsx)(c,{...e})}):c(e)}},5863:(e,n,t)=>{t.d(n,{A:()=>i});const i=t.p+"assets/images/background-blurred-8b33d8c033c83c5049ad5ecc21e7fe67.jpg"},8453:(e,n,t)=>{t.d(n,{R:()=>l,x:()=>o});var i=t(6540);const a={},s=i.createContext(a);function l(e){const n=i.useContext(s);return i.useMemo((function(){return"function"==typeof e?e(n):{...n,...e}}),[n,e])}function o(e){let n;return n=e.disableParentContext?"function"==typeof e.components?e.components(a):e.components||a:l(e.components),i.createElement(s.Provider,{value:n},e.children)}}}]); \ No newline at end of file diff --git a/assets/js/runtime~main.c20d8f80.js b/assets/js/runtime~main.dea8b065.js similarity index 58% rename from assets/js/runtime~main.c20d8f80.js rename to assets/js/runtime~main.dea8b065.js index a612dd2..ee94c8d 100644 --- a/assets/js/runtime~main.c20d8f80.js +++ b/assets/js/runtime~main.dea8b065.js @@ -1 +1 @@ -(()=>{"use strict";var e,t,r,a,o,d={},f={};function n(e){var t=f[e];if(void 0!==t)return t.exports;var r=f[e]={id:e,loaded:!1,exports:{}};return d[e].call(r.exports,r,r.exports,n),r.loaded=!0,r.exports}n.m=d,n.c=f,e=[],n.O=(t,r,a,o)=>{if(!r){var d=1/0;for(b=0;b=o)&&Object.keys(n.O).every((e=>n.O[e](r[c])))?r.splice(c--,1):(f=!1,o0&&e[b-1][2]>o;b--)e[b]=e[b-1];e[b]=[r,a,o]},n.n=e=>{var t=e&&e.__esModule?()=>e.default:()=>e;return n.d(t,{a:t}),t},r=Object.getPrototypeOf?e=>Object.getPrototypeOf(e):e=>e.__proto__,n.t=function(e,a){if(1&a&&(e=this(e)),8&a)return e;if("object"==typeof e&&e){if(4&a&&e.__esModule)return e;if(16&a&&"function"==typeof e.then)return e}var o=Object.create(null);n.r(o);var d={};t=t||[null,r({}),r([]),r(r)];for(var f=2&a&&e;"object"==typeof f&&!~t.indexOf(f);f=r(f))Object.getOwnPropertyNames(f).forEach((t=>d[t]=()=>e[t]));return d.default=()=>e,n.d(o,d),o},n.d=(e,t)=>{for(var r in t)n.o(t,r)&&!n.o(e,r)&&Object.defineProperty(e,r,{enumerable:!0,get:t[r]})},n.f={},n.e=e=>Promise.all(Object.keys(n.f).reduce(((t,r)=>(n.f[r](e,t),t)),[])),n.u=e=>"assets/js/"+({33:"d783dd4b",48:"a94703ab",91:"d5ddce42",98:"a7bd4aaa",235:"a7456010",249:"ccc49370",291:"d5734869",301:"8fe22858",342:"d65623e0",401:"17896441",415:"bf19ee00",472:"814f3328",535:"e194e136",564:"8ed1270f",634:"c4f5d8e4",643:"a6aa9e1f",647:"5e95c892",711:"9e4087bc",742:"aba21aa0",751:"fa28b54f",761:"2e2eef25",786:"ad704199",805:"ef9b9427",858:"36994c47",897:"b6eb3fd0",903:"acecf23e",969:"14eb3368"}[e]||e)+"."+{33:"a219a2f9",48:"f5f58c9b",91:"268b859f",98:"e69b25fc",235:"c5398906",237:"c85e5d35",249:"27f0dfd7",291:"060a3e72",301:"800a2f7b",342:"29903dc9",401:"459564f7",415:"a8c63bdd",472:"9d7e8607",535:"c8b3393d",554:"5106122a",564:"54d771fb",634:"75fcb030",643:"ff2b2793",647:"c95c2d86",667:"29823a64",711:"d802448c",742:"7179b4a2",751:"8b55c5b1",761:"6f79168c",786:"083c42e2",805:"8f2f846f",858:"a61da9c7",897:"99d38c3b",903:"5c31bba2",969:"5606f88c"}[e]+".js",n.miniCssF=e=>{},n.g=function(){if("object"==typeof globalThis)return globalThis;try{return this||new Function("return this")()}catch(e){if("object"==typeof window)return window}}(),n.o=(e,t)=>Object.prototype.hasOwnProperty.call(e,t),a={},o="ea-mt-website:",n.l=(e,t,r,d)=>{if(a[e])a[e].push(t);else{var f,c;if(void 0!==r)for(var i=document.getElementsByTagName("script"),b=0;b{f.onerror=f.onload=null,clearTimeout(s);var o=a[e];if(delete a[e],f.parentNode&&f.parentNode.removeChild(f),o&&o.forEach((e=>e(r))),t)return t(r)},s=setTimeout(l.bind(null,void 0,{type:"timeout",target:f}),12e4);f.onerror=l.bind(null,f.onerror),f.onload=l.bind(null,f.onload),c&&document.head.appendChild(f)}},n.r=e=>{"undefined"!=typeof Symbol&&Symbol.toStringTag&&Object.defineProperty(e,Symbol.toStringTag,{value:"Module"}),Object.defineProperty(e,"__esModule",{value:!0})},n.p="/ea-mt/",n.gca=function(e){return e={17896441:"401",d783dd4b:"33",a94703ab:"48",d5ddce42:"91",a7bd4aaa:"98",a7456010:"235",ccc49370:"249",d5734869:"291","8fe22858":"301",d65623e0:"342",bf19ee00:"415","814f3328":"472",e194e136:"535","8ed1270f":"564",c4f5d8e4:"634",a6aa9e1f:"643","5e95c892":"647","9e4087bc":"711",aba21aa0:"742",fa28b54f:"751","2e2eef25":"761",ad704199:"786",ef9b9427:"805","36994c47":"858",b6eb3fd0:"897",acecf23e:"903","14eb3368":"969"}[e]||e,n.p+n.u(e)},(()=>{var e={354:0,869:0};n.f.j=(t,r)=>{var a=n.o(e,t)?e[t]:void 0;if(0!==a)if(a)r.push(a[2]);else if(/^(354|869)$/.test(t))e[t]=0;else{var o=new Promise(((r,o)=>a=e[t]=[r,o]));r.push(a[2]=o);var d=n.p+n.u(t),f=new Error;n.l(d,(r=>{if(n.o(e,t)&&(0!==(a=e[t])&&(e[t]=void 0),a)){var o=r&&("load"===r.type?"missing":r.type),d=r&&r.target&&r.target.src;f.message="Loading chunk "+t+" failed.\n("+o+": "+d+")",f.name="ChunkLoadError",f.type=o,f.request=d,a[1](f)}}),"chunk-"+t,t)}},n.O.j=t=>0===e[t];var t=(t,r)=>{var a,o,d=r[0],f=r[1],c=r[2],i=0;if(d.some((t=>0!==e[t]))){for(a in f)n.o(f,a)&&(n.m[a]=f[a]);if(c)var b=c(n)}for(t&&t(r);i{"use strict";var e,t,r,a,o,f={},d={};function n(e){var t=d[e];if(void 0!==t)return t.exports;var r=d[e]={id:e,loaded:!1,exports:{}};return f[e].call(r.exports,r,r.exports,n),r.loaded=!0,r.exports}n.m=f,n.c=d,e=[],n.O=(t,r,a,o)=>{if(!r){var f=1/0;for(b=0;b=o)&&Object.keys(n.O).every((e=>n.O[e](r[c])))?r.splice(c--,1):(d=!1,o0&&e[b-1][2]>o;b--)e[b]=e[b-1];e[b]=[r,a,o]},n.n=e=>{var t=e&&e.__esModule?()=>e.default:()=>e;return n.d(t,{a:t}),t},r=Object.getPrototypeOf?e=>Object.getPrototypeOf(e):e=>e.__proto__,n.t=function(e,a){if(1&a&&(e=this(e)),8&a)return e;if("object"==typeof e&&e){if(4&a&&e.__esModule)return e;if(16&a&&"function"==typeof e.then)return e}var o=Object.create(null);n.r(o);var f={};t=t||[null,r({}),r([]),r(r)];for(var d=2&a&&e;"object"==typeof d&&!~t.indexOf(d);d=r(d))Object.getOwnPropertyNames(d).forEach((t=>f[t]=()=>e[t]));return f.default=()=>e,n.d(o,f),o},n.d=(e,t)=>{for(var r in t)n.o(t,r)&&!n.o(e,r)&&Object.defineProperty(e,r,{enumerable:!0,get:t[r]})},n.f={},n.e=e=>Promise.all(Object.keys(n.f).reduce(((t,r)=>(n.f[r](e,t),t)),[])),n.u=e=>"assets/js/"+({33:"d783dd4b",48:"a94703ab",91:"d5ddce42",98:"a7bd4aaa",235:"a7456010",249:"ccc49370",291:"d5734869",301:"8fe22858",342:"d65623e0",401:"17896441",415:"bf19ee00",472:"814f3328",535:"e194e136",564:"8ed1270f",634:"c4f5d8e4",643:"a6aa9e1f",647:"5e95c892",711:"9e4087bc",742:"aba21aa0",751:"fa28b54f",761:"2e2eef25",786:"ad704199",805:"ef9b9427",858:"36994c47",897:"b6eb3fd0",903:"acecf23e",969:"14eb3368"}[e]||e)+"."+{33:"a219a2f9",48:"f5f58c9b",91:"268b859f",98:"e69b25fc",235:"c5398906",237:"c85e5d35",249:"27f0dfd7",291:"060a3e72",301:"800a2f7b",342:"29903dc9",401:"459564f7",415:"a8c63bdd",472:"9d7e8607",535:"c8b3393d",554:"5106122a",564:"54d771fb",634:"75fcb030",643:"ff2b2793",647:"c95c2d86",667:"29823a64",711:"d802448c",742:"7179b4a2",751:"8b55c5b1",761:"6f79168c",786:"083c42e2",805:"064c6919",858:"a61da9c7",897:"99d38c3b",903:"5c31bba2",969:"5606f88c"}[e]+".js",n.miniCssF=e=>{},n.g=function(){if("object"==typeof globalThis)return globalThis;try{return this||new Function("return this")()}catch(e){if("object"==typeof window)return window}}(),n.o=(e,t)=>Object.prototype.hasOwnProperty.call(e,t),a={},o="ea-mt-website:",n.l=(e,t,r,f)=>{if(a[e])a[e].push(t);else{var d,c;if(void 0!==r)for(var i=document.getElementsByTagName("script"),b=0;b{d.onerror=d.onload=null,clearTimeout(s);var o=a[e];if(delete a[e],d.parentNode&&d.parentNode.removeChild(d),o&&o.forEach((e=>e(r))),t)return t(r)},s=setTimeout(l.bind(null,void 0,{type:"timeout",target:d}),12e4);d.onerror=l.bind(null,d.onerror),d.onload=l.bind(null,d.onload),c&&document.head.appendChild(d)}},n.r=e=>{"undefined"!=typeof Symbol&&Symbol.toStringTag&&Object.defineProperty(e,Symbol.toStringTag,{value:"Module"}),Object.defineProperty(e,"__esModule",{value:!0})},n.p="/ea-mt/",n.gca=function(e){return e={17896441:"401",d783dd4b:"33",a94703ab:"48",d5ddce42:"91",a7bd4aaa:"98",a7456010:"235",ccc49370:"249",d5734869:"291","8fe22858":"301",d65623e0:"342",bf19ee00:"415","814f3328":"472",e194e136:"535","8ed1270f":"564",c4f5d8e4:"634",a6aa9e1f:"643","5e95c892":"647","9e4087bc":"711",aba21aa0:"742",fa28b54f:"751","2e2eef25":"761",ad704199:"786",ef9b9427:"805","36994c47":"858",b6eb3fd0:"897",acecf23e:"903","14eb3368":"969"}[e]||e,n.p+n.u(e)},(()=>{var e={354:0,869:0};n.f.j=(t,r)=>{var a=n.o(e,t)?e[t]:void 0;if(0!==a)if(a)r.push(a[2]);else if(/^(354|869)$/.test(t))e[t]=0;else{var o=new Promise(((r,o)=>a=e[t]=[r,o]));r.push(a[2]=o);var f=n.p+n.u(t),d=new Error;n.l(f,(r=>{if(n.o(e,t)&&(0!==(a=e[t])&&(e[t]=void 0),a)){var o=r&&("load"===r.type?"missing":r.type),f=r&&r.target&&r.target.src;d.message="Loading chunk "+t+" failed.\n("+o+": "+f+")",d.name="ChunkLoadError",d.type=o,d.request=f,a[1](d)}}),"chunk-"+t,t)}},n.O.j=t=>0===e[t];var t=(t,r)=>{var a,o,f=r[0],d=r[1],c=r[2],i=0;if(f.some((t=>0!==e[t]))){for(a in d)n.o(d,a)&&(n.m[a]=d[a]);if(c)var b=c(n)}for(t&&t(r);i About Us | SemEval 2025 - Task 2: EA-MT - + diff --git a/docs/category/the-ea-mt-task.html b/docs/category/the-ea-mt-task.html index eecf854..acf863e 100644 --- a/docs/category/the-ea-mt-task.html +++ b/docs/category/the-ea-mt-task.html @@ -5,7 +5,7 @@ The EA-MT Task | SemEval 2025 - Task 2: EA-MT - + diff --git a/docs/contact_us.html b/docs/contact_us.html index c3b16f2..4784694 100644 --- a/docs/contact_us.html +++ b/docs/contact_us.html @@ -5,7 +5,7 @@ Contact Us | SemEval 2025 - Task 2: EA-MT - + diff --git a/docs/task/data.html b/docs/task/data.html index 6235039..4ce1df9 100644 --- a/docs/task/data.html +++ b/docs/task/data.html @@ -5,7 +5,7 @@ Data | SemEval 2025 - Task 2: EA-MT - + diff --git a/docs/task/evaluation.html b/docs/task/evaluation.html index 5fc5bb0..89de9df 100644 --- a/docs/task/evaluation.html +++ b/docs/task/evaluation.html @@ -5,7 +5,7 @@ Evaluation | SemEval 2025 - Task 2: EA-MT - + diff --git a/docs/task/important_dates.html b/docs/task/important_dates.html index cde61d6..c84deaf 100644 --- a/docs/task/important_dates.html +++ b/docs/task/important_dates.html @@ -5,7 +5,7 @@ Important Dates | SemEval 2025 - Task 2: EA-MT - + diff --git a/docs/task/introduction.html b/docs/task/introduction.html index 7ac988d..e7cc87a 100644 --- a/docs/task/introduction.html +++ b/docs/task/introduction.html @@ -5,7 +5,7 @@ Introduction | SemEval 2025 - Task 2: EA-MT - + @@ -21,6 +21,49 @@

What is it

We invite participants to develop machine translation systems that can accurately translate text that includes potentially challenging named entities in the source language. The task is to translate a given input sentence from the source language (English) to the target language, where the input sentence contains named entities that may be challenging for machine translation systems to handle. The named entities may be entities that are rare, ambiguous, or unknown to the machine translation system. The task is to develop machine translation systems that can accurately translate such named entities in the input sentence to the target language.

Why is it important?​

We believe that the ability to accurately translate named entities is crucial for machine translation systems to be effective in real-world scenarios. Named entities are entities that are referred to by proper names, such as people, organizations, locations, dates, and more. Named entities are often challenging even for human translators, as sometimes there are cultural or domain-specific references that are not easily translatable. This happens more often for some entity types or categories, such as movies, books, TV series, products, and more.

+

How can you participate?​

+

There are several ways to participate in the EA-MT task:

+
    +
  • +

    Fine-tune an existing model: You can fine-tune an existing MT model or LLM on the provided training data. For example:

    +
      +
    • You can use popular pre-trained models, such as MarianMT, M2M-100, T5, and more.
      • +
    • You can use popular LLMs, such as Llama-3, Qwen-2, and more.
      • +
    +
    • +
  • +

    Develop your own machine translation system: You can develop your own machine translation system using your preferred tools and techniques.

    +
      +
    • You can add named entity recognition (NER), entity linking (EL), or other modules to your machine translation system to improve the translation of named entities.
      • +
    • You can use data augmentation techniques to improve the performance of your machine translation system.
      • +
    +
    • +
  • +

    Use external systems: You can use external systems, APIs, or services to improve the performance of your machine translation system.

    +
      +
    • You can use GPT-4, Gemini, Claude or other commercial LLMs and build on top of them.
      • +
    +
    • +
+

Is my system good enough?​

+

The final result is not the only thing that matters: we know that comparing a small BERT-based model with GPT4o or Gemini is not "fair". This shared task is not about winning, but about learning, and sharing. For example:

+
    +
  • Did you find that a simple model works almost as well as a complex one but is much faster?
    • +
  • Did you try a new data augmentation technique?
    • +
  • Did you experiment with a new architecture?
    • +
  • Did you try to fine-tune a model on a new dataset?
    • +
  • Did you try to combine different models?
    • +
  • Did you try to use external systems to improve your model?
    • +
  • What is the extent of the improvement you achieved by combining different techniques?
    • +
+

For example, sometimes it may be more interesting to see a super fast model that is 10% worse than the best model, but that can be used in real-world scenarios. Or there may be techniques that are more effective for certain types of named entities, or for certain language pairs.

+

Negative Results​

+

Negative results are also welcome! If you tried something and it didn't work, that's valuable information too. It can help others avoid the same pitfalls and save time in the future.

+

Write a system paper​

+

We encourage participants to write a system paper describing their approach, the techniques they used, the results they obtained, and the lessons they learned. The system paper will be submitted to the SemEval workshop for review and publication: this is a great opportunity to showcase your work with the NLP community.

+
    +
  • We will provide a template for the system paper, and we will give you detailed instructions on how to write it at the end of January 2025.
    • +

Examples​

Here are some examples of sentences that you may encounter in the EA-MT task:

Example 1: English to French​

@@ -60,6 +103,6 @@

Language Pair
note

This edition of EA-MT will focus on translating from English to the target languages mentioned above. We may consider adding more language pairs in future editions.

Next steps​

Please, stay tuned for more updates on the EA-MT task for SemEval-2025. We will be releasing more information on the dataset, evaluation metrics, and submission guidelines soon. If you have any questions, feel free to reach out to us.

-
Join the Google Group

We invite you to join our Google Group for the latest updates and discussions: SemEval 2025 - Task 2: EA-MT.

+
Join the Google Group

We invite you to join our Google Group for the latest updates and discussions: SemEval 2025 - Task 2: EA-MT.

\ No newline at end of file diff --git a/docs/task/submission.html b/docs/task/submission.html index bb0b80a..7fafcd2 100644 --- a/docs/task/submission.html +++ b/docs/task/submission.html @@ -5,7 +5,7 @@ Submit Your Results! | SemEval 2025 - Task 2: EA-MT - + diff --git a/index.html b/index.html index 6fa349c..1fbe529 100644 --- a/index.html +++ b/index.html @@ -5,7 +5,7 @@ Hello from SemEval 2025 - Task 2: EA-MT | SemEval 2025 - Task 2: EA-MT - + diff --git a/news.html b/news.html index 6bdb7fd..e461c8b 100644 --- a/news.html +++ b/news.html @@ -5,7 +5,7 @@ Blog | SemEval 2025 - Task 2: EA-MT - + diff --git a/news/archive.html b/news/archive.html index fa1c4ba..df0efd0 100644 --- a/news/archive.html +++ b/news/archive.html @@ -5,7 +5,7 @@ Archive | SemEval 2025 - Task 2: EA-MT - + diff --git a/news/welcome.html b/news/welcome.html index 778fc4d..0908e05 100644 --- a/news/welcome.html +++ b/news/welcome.html @@ -5,7 +5,7 @@ Welcome! | SemEval 2025 - Task 2: EA-MT - +