Neal Caren commited on
Commit
2a3fed6
1 Parent(s): 353fc7a
Files changed (3) hide show
  1. app.py +3 -2
  2. emerac.png +0 -0
  3. requirements.txt +0 -1
app.py CHANGED
@@ -47,7 +47,7 @@ def load_data(url):
47
  return df
48
 
49
 
50
- st.title('Sociology Paragraph Search')
51
 
52
  st.write('This project is a work-in-progress that searches the text of recently-published articles from a few sociology journals and retrieves the most relevant paragraphs.')
53
 
@@ -70,7 +70,7 @@ notes = f'''Notes:
70
  * The most relevant paragraph to your search is returned first, along with up to four other related paragraphs from that article.
71
  * The most relevant sentence within each paragraph, as determined by math, is displayed. Click on it to see the full paragraph.
72
  * The results are not exhaustive, and seem to drift off even when you suspect there are more relevant articles :man-shrugging:.
73
- * The dataset currently includes articles published in the last five years in *Mobilization*, *Social Forces*, *Social Problems*, *Sociology of Race and Ethnicity*, *Gender and Society*, *Socius*, *JHSB*, *Annual Review of Sociology*, and the *American Sociological Review*.
74
  * Behind the scenes, the semantic search uses [text embeddings](https://www.sbert.net) with a [retrieve & re-rank](https://colab.research.google.com/github/UKPLab/sentence-transformers/blob/master/examples/applications/retrieve_rerank/retrieve_rerank_simple_wikipedia.ipynb) process to find the best matches.
75
  * Let [me](mailto:neal.caren@unc.edu) know what you think or it looks broken.
76
  '''
@@ -167,3 +167,4 @@ if search_query!='':
167
  bi_encoder = sent_trans_load()
168
  cross_encoder = sent_cross_load()
169
  search(search_query)
 
 
47
  return df
48
 
49
 
50
+ st.title('Sociology EMERAC')
51
 
52
  st.write('This project is a work-in-progress that searches the text of recently-published articles from a few sociology journals and retrieves the most relevant paragraphs.')
53
 
 
70
  * The most relevant paragraph to your search is returned first, along with up to four other related paragraphs from that article.
71
  * The most relevant sentence within each paragraph, as determined by math, is displayed. Click on it to see the full paragraph.
72
  * The results are not exhaustive, and seem to drift off even when you suspect there are more relevant articles :man-shrugging:.
73
+ * The dataset currently includes {no_of_graphs:,} paragraphs from {no_of_articles:,} published in the last five years in *Mobilization*, *Social Forces*, *Social Problems*, *Sociology of Race and Ethnicity*, *Gender and Society*, *Socius*, *JHSB*, *Annual Review of Sociology*, and the *American Sociological Review*.
74
  * Behind the scenes, the semantic search uses [text embeddings](https://www.sbert.net) with a [retrieve & re-rank](https://colab.research.google.com/github/UKPLab/sentence-transformers/blob/master/examples/applications/retrieve_rerank/retrieve_rerank_simple_wikipedia.ipynb) process to find the best matches.
75
  * Let [me](mailto:neal.caren@unc.edu) know what you think or it looks broken.
76
  '''
 
167
  bi_encoder = sent_trans_load()
168
  cross_encoder = sent_cross_load()
169
  search(search_query)
170
+ st.markdown('![EMERAC](emerac.png)')
emerac.png ADDED
requirements.txt CHANGED
@@ -3,4 +3,3 @@ torch
3
  pandas
4
  nltk
5
  gdown
6
- streamlit
 
3
  pandas
4
  nltk
5
  gdown