Xueqing commited on
Commit
e3a2a55
·
verified ·
1 Parent(s): 72cf9ba

Update frontend/src/pages/QuotePage/QuotePage.js

Browse files
frontend/src/pages/QuotePage/QuotePage.js CHANGED
@@ -108,33 +108,33 @@ const priorWork = [
108
  // },
109
  ];
110
 
111
- const benchmarks = [
112
- {
113
- title: "MultiFin: Instruction-Following Evaluation",
114
- authors: "Zhou et al.",
115
- citation: `@inproceedings{jorgensen-etal-2023-multifin,
116
- title = "{M}ulti{F}in: A Dataset for Multilingual Financial {NLP}",
117
- author = "J{\o}rgensen, Rasmus and
118
- Brandt, Oliver and
119
- Hartmann, Mareike and
120
- Dai, Xiang and
121
- Igel, Christian and
122
- Elliott, Desmond",
123
- editor = "Vlachos, Andreas and
124
- Augenstein, Isabelle",
125
- booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
126
- month = may,
127
- year = "2023",
128
- address = "Dubrovnik, Croatia",
129
- publisher = "Association for Computational Linguistics",
130
- url = "https://aclanthology.org/2023.findings-eacl.66/",
131
- doi = "10.18653/v1/2023.findings-eacl.66",
132
- pages = "894--909",
133
- abstract = "Financial information is generated and distributed across the world, resulting in a vast amount of domain-specific multilingual data. Multilingual models adapted to the financial domain would ease deployment when an organization needs to work with multiple languages on a regular basis. For the development and evaluation of such models, there is a need for multilingual financial language processing datasets. We describe MultiFin {--} a publicly available financial dataset consisting of real-world article headlines covering 15 languages across different writing systems and language families. The dataset consists of hierarchical label structure providing two classification tasks: multi-label and multi-class. We develop our annotation schema based on a real-world application and annotate our dataset using both {\textquoteleft}label by native-speaker' and {\textquoteleft}translate-then-label' approaches. The evaluation of several popular multilingual models, e.g., mBERT, XLM-R, and mT5, show that although decent accuracy can be achieved in high-resource languages, there is substantial room for improvement in low-resource languages."
134
- }`,
135
- url: "https://aclanthology.org/2023.findings-eacl.66/#:~:text=We%20describe%20MultiFin%20%2D%2D%20a,%2Dlabel%20and%20multi%2Dclass.",
136
- },
137
- ];
138
 
139
  const CitationBlock = ({ citation, title, authors, url, type }) => {
140
  const handleCopy = () => {
 
108
  // },
109
  ];
110
 
111
+ // const benchmarks = [
112
+ // {
113
+ // title: "MultiFin: Instruction-Following Evaluation",
114
+ // authors: "Zhou et al.",
115
+ // citation: `@inproceedings{jorgensen-etal-2023-multifin,
116
+ // title = "{M}ulti{F}in: A Dataset for Multilingual Financial {NLP}",
117
+ // author = "J{\o}rgensen, Rasmus and
118
+ // Brandt, Oliver and
119
+ // Hartmann, Mareike and
120
+ // Dai, Xiang and
121
+ // Igel, Christian and
122
+ // Elliott, Desmond",
123
+ // editor = "Vlachos, Andreas and
124
+ // Augenstein, Isabelle",
125
+ // booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
126
+ // month = may,
127
+ // year = "2023",
128
+ // address = "Dubrovnik, Croatia",
129
+ // publisher = "Association for Computational Linguistics",
130
+ // url = "https://aclanthology.org/2023.findings-eacl.66/",
131
+ // doi = "10.18653/v1/2023.findings-eacl.66",
132
+ // pages = "894--909",
133
+ // abstract = "Financial information is generated and distributed across the world, resulting in a vast amount of domain-specific multilingual data. Multilingual models adapted to the financial domain would ease deployment when an organization needs to work with multiple languages on a regular basis. For the development and evaluation of such models, there is a need for multilingual financial language processing datasets. We describe MultiFin {--} a publicly available financial dataset consisting of real-world article headlines covering 15 languages across different writing systems and language families. The dataset consists of hierarchical label structure providing two classification tasks: multi-label and multi-class. We develop our annotation schema based on a real-world application and annotate our dataset using both {\textquoteleft}label by native-speaker' and {\textquoteleft}translate-then-label' approaches. The evaluation of several popular multilingual models, e.g., mBERT, XLM-R, and mT5, show that although decent accuracy can be achieved in high-resource languages, there is substantial room for improvement in low-resource languages."
134
+ // }`,
135
+ // url: "https://aclanthology.org/2023.findings-eacl.66/#:~:text=We%20describe%20MultiFin%20%2D%2D%20a,%2Dlabel%20and%20multi%2Dclass.",
136
+ // },
137
+ // ];
138
 
139
  const CitationBlock = ({ citation, title, authors, url, type }) => {
140
  const handleCopy = () => {