File size: 1,947 Bytes
98ffeff b16059e 98ffeff b16059e 98ffeff b16059e 5687e79 b6bbf8d b16059e b6bbf8d b16059e 56359e1 b16059e 98ffeff |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 |
import os
import subprocess
import nltk
import spacy
# Setup NLTK
nltk_data_path = "/tmp/nltk_data"
nltk.download('punkt', download_dir=nltk_data_path)
nltk.download('benepar_en3', download_dir=nltk_data_path)
nltk.data.path.append(nltk_data_path)
# Load spaCy model with fallback
try:
nlp = spacy.load("en_core_web_sm")
except:
subprocess.run(["python", "-m", "spacy", "download", "en_core_web_sm"])
nlp = spacy.load("en_core_web_sm")
if "benepar" not in nlp.pipe_names:
nlp.add_pipe("benepar", config={"model": "benepar_en3"})
st.set_page_config(page_title="Syntax Parser Comparison Tool", layout="wide")
st.title("🌐 Syntax Parser Comparison Tool")
st.write("This tool compares Dependency Parsing, Constituency Parsing, and a simulated Abstract Syntax Representation (ASR).")
sentence = st.text_input("Enter a sentence:", "John eats an apple.")
if sentence:
doc = nlp(sentence)
sent = list(doc.sents)[0]
col1, col2, col3 = st.columns(3)
with col1:
st.header("Dependency Parsing")
for token in sent:
st.write(f"{token.text} --> {token.dep_} --> {token.head.text}")
st.code(" ".join(f"({token.text}, {token.dep_}, {token.head.text})" for token in sent))
with col2:
st.header("Constituency Parsing")
tree = sent._.parse_string
st.text(tree)
st.code(Tree.fromstring(tree).pformat())
with col3:
st.header("Simulated ASR Output")
st.write("Combining phrase structure with dependency head annotations:")
for token in sent:
if token.dep_ in ("nsubj", "obj", "det", "ROOT"):
st.write(f"[{token.text}] - {token.dep_} --> {token.head.text} ({token.pos_})")
st.markdown("_(ASR is simulated by combining POS tags, dependency heads, and phrase information.)_")
st.code(" ".join(f"[{token.text}: {token.dep_} → {token.head.text}]({token.pos_})" for token in sent))
|