陈俊杰
commited on
Commit
·
6280ba1
1
Parent(s):
342f2c9
insert html
Browse files
app.py
CHANGED
|
@@ -153,7 +153,7 @@ elif page == "Methodology":
|
|
| 153 |
<li>Third, we manually annotate the answer sets for each question, which will be used as gold standards for evaluating the performance of different evaluation methods.</li>
|
| 154 |
<li>Last, we will collect evaluation results from participants and calculate consistency with manually annotated results. We will use Accuracy, Kendall’s tau and Spearman correlation coefficient as the evaluation metrics.</li>
|
| 155 |
</ol>
|
| 156 |
-
""")
|
| 157 |
|
| 158 |
elif page == "Datasets":
|
| 159 |
st.header("Datasets")
|
|
@@ -166,7 +166,7 @@ elif page == "Datasets":
|
|
| 166 |
<li><strong>Dialogue Generation (DG): <a href="https://huggingface.co/datasets/daily_dialog">DailyDialog</a></strong>: A high-quality dataset of 13k multi-turn dialogues. The language is human-written and less noisy.</li>
|
| 167 |
</ul>
|
| 168 |
<p>For your convenience, we have released <strong>the training set</strong> (with human-annotated results) and <strong>the test set</strong> (without human-annotated results) on <a href="https://huggingface.co/datasets/THUIR/AEOLLM">https://huggingface.co/datasets/THUIR/AEOLLM</a>, which you can easily download.</p>
|
| 169 |
-
""")
|
| 170 |
|
| 171 |
elif page == "Important Dates":
|
| 172 |
st.header("Important Dates")
|
|
@@ -180,7 +180,7 @@ elif page == "Important Dates":
|
|
| 180 |
<span class="event"><strong>Submission Due of Participant Papers (draft)</strong>:</span> <span class="date">March 1, 2025</span><br />
|
| 181 |
<span class="event"><strong>Camera-Ready Participant Paper Due</strong>:</span> <span class="date">May 1, 2025</span><br />
|
| 182 |
<span class="event"><strong>NTCIR-18 Conference</strong>:</span> <span class="date">Jun 10-13 2025</span><br /></p>
|
| 183 |
-
""")
|
| 184 |
elif page == "Evaluation Measures":
|
| 185 |
st.header("Evaluation Measures")
|
| 186 |
st.markdown("""
|
|
@@ -188,7 +188,7 @@ elif page == "Evaluation Measures":
|
|
| 188 |
- **Kendall's tau:** Measures the ordinal association between two ranked variables.
|
| 189 |
|
| 190 |
$$
|
| 191 |
-
|
| 192 |
$$
|
| 193 |
|
| 194 |
where:
|
|
@@ -197,12 +197,12 @@ elif page == "Evaluation Measures":
|
|
| 197 |
- n is the number of pairs.
|
| 198 |
- **Spearman's Rank Correlation Coefficient:** Measures the strength and direction of the association between two ranked variables.
|
| 199 |
$$
|
| 200 |
-
|
| 201 |
$$
|
| 202 |
where:
|
| 203 |
- $d_i$ is the difference between the ranks of corresponding elements in the two lists,
|
| 204 |
- $n$ is the number of elements.
|
| 205 |
-
""")
|
| 206 |
elif page == "Data and File format":
|
| 207 |
st.header("Data and File format")
|
| 208 |
st.markdown("""
|
|
@@ -215,7 +215,7 @@ elif page == "Data and File format":
|
|
| 215 |
<li>the fourth column is score (index the score to the answer given by participants)</li>
|
| 216 |
<li>the fifth column is rank (index the rank of the answer within all answers to the same question)</li>
|
| 217 |
</ol>
|
| 218 |
-
""")
|
| 219 |
elif page == "Submit":
|
| 220 |
st.header("Submit")
|
| 221 |
st.markdown("""
|
|
@@ -301,7 +301,7 @@ elif page == "Organisers":
|
|
| 301 |
<em>Qingyao Ai</em> [aiqy@tsinghua.edu.cn] (Tsinghua University)<br />
|
| 302 |
<em>Junjie Chen</em> [chenjj826@gmail.com] (Tsinghua University) <br />
|
| 303 |
<em>Zhumin Chu</em> [chuzm19@mails.tsinghua.edu.cn] (Tsinghua University)<br />
|
| 304 |
-
<em>Haitao Li</em> [liht22@mails.tsinghua.edu.cn] (Tsinghua University)""")
|
| 305 |
elif page == "References":
|
| 306 |
st.header("References")
|
| 307 |
st.markdown("""TAB""")
|
|
|
|
| 153 |
<li>Third, we manually annotate the answer sets for each question, which will be used as gold standards for evaluating the performance of different evaluation methods.</li>
|
| 154 |
<li>Last, we will collect evaluation results from participants and calculate consistency with manually annotated results. We will use Accuracy, Kendall’s tau and Spearman correlation coefficient as the evaluation metrics.</li>
|
| 155 |
</ol>
|
| 156 |
+
""",unsafe_allow_html=True)
|
| 157 |
|
| 158 |
elif page == "Datasets":
|
| 159 |
st.header("Datasets")
|
|
|
|
| 166 |
<li><strong>Dialogue Generation (DG): <a href="https://huggingface.co/datasets/daily_dialog">DailyDialog</a></strong>: A high-quality dataset of 13k multi-turn dialogues. The language is human-written and less noisy.</li>
|
| 167 |
</ul>
|
| 168 |
<p>For your convenience, we have released <strong>the training set</strong> (with human-annotated results) and <strong>the test set</strong> (without human-annotated results) on <a href="https://huggingface.co/datasets/THUIR/AEOLLM">https://huggingface.co/datasets/THUIR/AEOLLM</a>, which you can easily download.</p>
|
| 169 |
+
""",unsafe_allow_html=True)
|
| 170 |
|
| 171 |
elif page == "Important Dates":
|
| 172 |
st.header("Important Dates")
|
|
|
|
| 180 |
<span class="event"><strong>Submission Due of Participant Papers (draft)</strong>:</span> <span class="date">March 1, 2025</span><br />
|
| 181 |
<span class="event"><strong>Camera-Ready Participant Paper Due</strong>:</span> <span class="date">May 1, 2025</span><br />
|
| 182 |
<span class="event"><strong>NTCIR-18 Conference</strong>:</span> <span class="date">Jun 10-13 2025</span><br /></p>
|
| 183 |
+
""",unsafe_allow_html=True)
|
| 184 |
elif page == "Evaluation Measures":
|
| 185 |
st.header("Evaluation Measures")
|
| 186 |
st.markdown("""
|
|
|
|
| 188 |
- **Kendall's tau:** Measures the ordinal association between two ranked variables.
|
| 189 |
|
| 190 |
$$
|
| 191 |
+
\\tau=\\frac{C-D}{\\frac{1}{2}n(n-1)}
|
| 192 |
$$
|
| 193 |
|
| 194 |
where:
|
|
|
|
| 197 |
- n is the number of pairs.
|
| 198 |
- **Spearman's Rank Correlation Coefficient:** Measures the strength and direction of the association between two ranked variables.
|
| 199 |
$$
|
| 200 |
+
\\rho = 1 - \\frac{6 \sum d_i^2}{n(n^2 - 1)}
|
| 201 |
$$
|
| 202 |
where:
|
| 203 |
- $d_i$ is the difference between the ranks of corresponding elements in the two lists,
|
| 204 |
- $n$ is the number of elements.
|
| 205 |
+
""",unsafe_allow_html=True)
|
| 206 |
elif page == "Data and File format":
|
| 207 |
st.header("Data and File format")
|
| 208 |
st.markdown("""
|
|
|
|
| 215 |
<li>the fourth column is score (index the score to the answer given by participants)</li>
|
| 216 |
<li>the fifth column is rank (index the rank of the answer within all answers to the same question)</li>
|
| 217 |
</ol>
|
| 218 |
+
""",unsafe_allow_html=True)
|
| 219 |
elif page == "Submit":
|
| 220 |
st.header("Submit")
|
| 221 |
st.markdown("""
|
|
|
|
| 301 |
<em>Qingyao Ai</em> [aiqy@tsinghua.edu.cn] (Tsinghua University)<br />
|
| 302 |
<em>Junjie Chen</em> [chenjj826@gmail.com] (Tsinghua University) <br />
|
| 303 |
<em>Zhumin Chu</em> [chuzm19@mails.tsinghua.edu.cn] (Tsinghua University)<br />
|
| 304 |
+
<em>Haitao Li</em> [liht22@mails.tsinghua.edu.cn] (Tsinghua University)""",unsafe_allow_html=True)
|
| 305 |
elif page == "References":
|
| 306 |
st.header("References")
|
| 307 |
st.markdown("""TAB""")
|