Upload 2 files
Browse files- app.py +49 -0
- requirements.txt +4 -3
app.py
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
os.environ["STREAMLIT_BROWSER_GATHER_USAGE_STATS"] = "false"
|
3 |
+
|
4 |
+
import streamlit as st
|
5 |
+
import spacy
|
6 |
+
import benepar
|
7 |
+
from nltk import Tree
|
8 |
+
import nltk
|
9 |
+
|
10 |
+
# Setup NLTK and benepar
|
11 |
+
nltk.download('punkt')
|
12 |
+
benepar.download('benepar_en3')
|
13 |
+
|
14 |
+
nlp = spacy.load("en_core_web_sm")
|
15 |
+
if "benepar" not in nlp.pipe_names:
|
16 |
+
nlp.add_pipe("benepar", config={"model": "benepar_en3"})
|
17 |
+
|
18 |
+
st.set_page_config(page_title="Syntax Parser Comparison Tool", layout="wide")
|
19 |
+
st.title("🌐 Syntax Parser Comparison Tool")
|
20 |
+
st.write("This tool compares Dependency Parsing, Constituency Parsing, and a simulated Abstract Syntax Representation (ASR).")
|
21 |
+
|
22 |
+
sentence = st.text_input("Enter a sentence:", "John eats an apple.")
|
23 |
+
|
24 |
+
if sentence:
|
25 |
+
doc = nlp(sentence)
|
26 |
+
sent = list(doc.sents)[0]
|
27 |
+
|
28 |
+
col1, col2, col3 = st.columns(3)
|
29 |
+
|
30 |
+
with col1:
|
31 |
+
st.header("Dependency Parsing")
|
32 |
+
for token in sent:
|
33 |
+
st.write(f"{token.text} --> {token.dep_} --> {token.head.text}")
|
34 |
+
st.code(" ".join(f"({token.text}, {token.dep_}, {token.head.text})" for token in sent))
|
35 |
+
|
36 |
+
with col2:
|
37 |
+
st.header("Constituency Parsing")
|
38 |
+
tree = sent._.parse_string
|
39 |
+
st.text(tree)
|
40 |
+
st.code(Tree.fromstring(tree).pformat())
|
41 |
+
|
42 |
+
with col3:
|
43 |
+
st.header("Simulated ASR Output")
|
44 |
+
st.write("Combining phrase structure with dependency head annotations:")
|
45 |
+
for token in sent:
|
46 |
+
if token.dep_ in ("nsubj", "obj", "det", "ROOT"):
|
47 |
+
st.write(f"[{token.text}] - {token.dep_} --> {token.head.text} ({token.pos_})")
|
48 |
+
st.markdown("_(ASR is simulated by combining POS tags, dependency heads, and phrase information.)_")
|
49 |
+
st.code(" ".join(f"[{token.text}: {token.dep_} → {token.head.text}]({token.pos_})" for token in sent))
|
requirements.txt
CHANGED
@@ -1,3 +1,4 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
|
|
|
1 |
+
streamlit==1.32.2
|
2 |
+
spacy
|
3 |
+
nltk
|
4 |
+
benepar
|