kenkeiras/lang-model
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

Work in progress.

Browse source 
* Test
 * More debugging
 * Base concept
This commit is contained in:
kenkeiras 2017-05-28 22:39:04 +02:00
parent aa7bee4c8b
commit 9d49d00688
4 changed files with 62 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

40
naive-nlu/tree_nlu/parsing.py
View file

@ -20,6 +20,9 @@ def to_tokens(text):
def make_template(knowledge_base, tokens, parsed):
matcher = list(tokens)
template = list(parsed)
logging.debug(" -- MK TEMPLATE --")
logging.debug("MATCHR: {}".format(matcher))
logging.debug("TEMPLT: {}".format(template))
for i in range(len(matcher)):
word = matcher[i]
if word in template:
@ -56,6 +59,11 @@ def get_lower_levels(parsed):
# TODO: probably optimize this, it creates lots of unnecessary tuples
def replace_position(tree, position, new_element):
logging.debug("REPLACE POSITIONS:")
logging.debug(" TREE : {}".format(tree))
logging.debug("POSITION: {}".format(position))
logging.debug("NEW ELEM: {}".format(new_element))
logging.debug("------------------")
def aux(current_tree, remaining_route):
if len(remaining_route) == 0:
@ -69,7 +77,9 @@ def replace_position(tree, position, new_element):
+ tree[step + 2:]
)
return aux(tree, position)
result = aux(tree, position)
logging.debug("-RESULT: {}".format(result))
return result
def integrate_language(knowledge_base, example):
@ -90,15 +100,23 @@ def integrate_language(knowledge_base, example):
logging.debug("\x1b[1mSelecting\x1b[0m: {}".format(atom))
similar = get_similar_tree(knowledge_base, atom, tokens)
remix, (start_bounds, end_bounds) = build_remix_matrix(knowledge_base, tokens, atom, similar)
_, matcher, result = make_template(knowledge_base, tokens, atom)
logging.debug("Tx: {}".format(tokens))
after_remix = apply_remix(tokens[len(start_bounds):-len(end_bounds)], remix)
logging.debug("--FIND MIX--")
logging.debug("-MIX- | {}".format(remix))
logging.debug("-FRM- | {}".format(tokens))
logging.debug("-AFT- | {}".format(after_remix))
print()
_, matcher, result = make_template(knowledge_base, after_remix, atom)
logging.debug("Tx: {}".format(after_remix))
logging.debug("Mx: {}".format(matcher))
logging.debug("Rx: {}".format(result))
logging.debug("Remix: {}".format(remix))
logging.debug("Sx: {}".format(start_bounds))
logging.debug("Ex: {}".format(end_bounds))
after_remix = apply_remix(tokens[len(start_bounds):-len(end_bounds)], remix)
assert(len(after_remix) + len(start_bounds) + len(end_bounds) == len(tokens))
logging.debug( " +-> {}".format(after_remix))
subquery_type = knowledge_evaluation.get_subquery_type(knowledge_base.knowledge, atom)
@ -115,6 +133,8 @@ def integrate_language(knowledge_base, example):
tokens = new_tokens
resolved_parsed = replace_position(resolved_parsed, position, offset)
logging.debug("RP: {}".format(resolved_parsed))
logging.debug("AT: {}".format(atom))
logging.debug("#########")
@ -382,11 +402,20 @@ def resolve_fit(knowledge, fit, remaining_recursions):
if remixed_tokens is None:
return None
# if len(tokens) == 3 and tokens[2] == 'electricity':
# logging.debug("--UNMIX--")
# logging.debug("-MIX- | {}".format(remixer))
# logging.debug("REMIX | {}".format(tokens))
# logging.debug(" T O | {}".format(remixed_tokens))
# if remixer != [0, 1, 2]:
# return None
minifit = get_fit(knowledge, remixed_tokens, remaining_recursions - 1)
if minifit is None:
return None
minitokens, miniast = minifit
logging.debug(" AST | {}".format(miniast))
subproperty = knowledge_evaluation.resolve(knowledge.knowledge, minitokens, miniast)
fitted.append(subproperty)
@ -424,6 +453,7 @@ def match_fit(knowledge, tokens, matcher, ast, remaining_recursions):
resolved_fits = []
for fit, _ in fully_matched_segments:
print(":::", fit)
resolved_fit = resolve_fit(knowledge, fit, remaining_recursions)
if resolved_fit is not None:
resolved_fits.append(resolved_fit)