s478815/SystemyDialogowe
1
1
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

add nlg

Browse Source
This commit is contained in:
Adrian 2022-06-07 23:26:14 +02:00
parent e5fecb5716
commit 00f9c09e0a
12 changed files with 955 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

303
.ipynb_checkpoints/AJN-checkpoint.ipynb Normal file
View File

@ -0,0 +1,303 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"![Logo 1](https://git.wmi.amu.edu.pl/AITech/Szablon/raw/branch/master/Logotyp_AITech1.jpg)\n",
"<div class=\"alert alert-block alert-info\">\n",
"<h1> Systemy Dialogowe </h1>\n",
"<h2> 7. <i>Parsing semantyczny z wykorzystaniem gramatyk</i> [laboratoria]</h2> \n",
"<h3> Marek Kubis (2021)</h3>\n",
"</div>\n",
"\n",
"![Logo 2](https://git.wmi.amu.edu.pl/AITech/Szablon/raw/branch/master/Logotyp_AITech2.jpg)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Parsing semantyczny z wykorzystaniem gramatyk\n",
"=============================================\n",
"\n",
"Wartości slotów możemy wydobywać z wypowiedzi użytkownika korzystając z takich technik, jak:\n",
"\n",
" - wyszukiwanie słów kluczowych w tekście,\n",
"\n",
" - dopasowywanie wzorców zbudowanych przy użyciu wyrażeń regularnych,\n",
"\n",
" - parsery regułowe (temat dzisiejszych zajęć),\n",
"\n",
" - uczenie maszynowe (temat kolejnych zajęć)."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Przykłady parserów regułowych\n",
"-----------------------------\n",
"\n",
" - [Phoenix](http://wiki.speech.cs.cmu.edu/olympus/index.php/Phoenix_Server) — parser gramatyk\n",
" bezkontekstowych whodzący w skład systemu dialogowego [Olympus](http://wiki.speech.cs.cmu.edu/olympus/index.php/Olympus)\n",
"\n",
" - Parsery [DCG](https://www.swi-prolog.org/pldoc/man?section=DCG) (Definite Clause Grammars) języka [Prolog](https://www.swi-prolog.org/)\n",
"\n",
" - [JSpeech Grammar Format](https://www.w3.org/TR/jsgf/) (JSGF)\n",
"\n",
"Przykład\n",
"--------\n",
"Zapiszmy w JSGF gramatykę semantyczną dla aktu dialogowego reprezentującego zamiar rezerwacji\n",
"stolika w restauracji."
]
},
{
"cell_type": "code",
"execution_count": 51,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Overwriting book.jsgf\n"
]
}
],
"source": [
"%%writefile book.jsgf\n",
"#JSGF V1.0 UTF-8 pl;\n",
"\n",
"grammar book;\n",
"\n",
"public <rezerwuj> = chciałbym zarezerwować <ilosc_biletow> <tytul_filmu> [<dzien_rezerwacji>] [<godzina_rezerwacji>];\n",
"\n",
"<ilosc_biletow> = <liczba> {ilosc} (bilety | biletów);\n",
"\n",
"<liczba> = dwa | trzy | cztery |1|2|3|4|5|6;\n",
"\n",
"<tytul_filmu> = na [film] <tytul> {tytul};\n",
"\n",
"<tytul> = Batman | Uncharted | Pitbull;\n",
"\n",
"<dzien_rezerwacji> = na <dzien> {dzien};\n",
"\n",
"<dzien> = dzisiaj | jutro | poniedziałek | wtorek | środę | czwartek | piątek | sobotę | niedzielę;\n",
"\n",
"<godzina_rezerwacji> = na [godzinę] <godzina_z_minutami> {godzina};\n",
"\n",
"<godzina_z_minutami> = <godzina> [<minuty>];\n",
"\n",
"<godzina> = dziewiątą | dziesiątą | jedenastą | dwunastą;\n",
"\n",
"<minuty> = pietnaście | trzydzieści;\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Parser akceptujący powyższą gramatykę utworzymy korzystając z biblioteki [pyjsgf](https://github.com/Danesprite/pyjsgf)."
]
},
{
"cell_type": "code",
"execution_count": 52,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Grammar(version=1.0, charset=UTF-8, language=pl, name=book)"
]
},
"execution_count": 52,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import jsgf\n",
"\n",
"book_grammar = jsgf.parse_grammar_file('book.jsgf')\n",
"book_grammar"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Wykorzystajmy gramatykę `book.jsgf` do analizy następującej wypowiedzi"
]
},
{
"cell_type": "code",
"execution_count": 53,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[Rule(name='rezerwuj', visible=True, expansion=Sequence(Literal('chciałbym zarezerwować'), NamedRuleRef('ilosc_biletow'), NamedRuleRef('tytul_filmu'), OptionalGrouping(NamedRuleRef('dzien_rezerwacji')), OptionalGrouping(NamedRuleRef('godzina_rezerwacji'))))]"
]
},
"execution_count": 53,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"utterance = 'chciałbym zarezerwować 1 biletów na film Pitbull'\n",
"matched = book_grammar.find_matching_rules(utterance)\n",
"matched"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Reprezentację znaczenia można wydobyć ze sparsowanej wypowiedzi na wiele sposobów. My do\n",
"wydobywania slotów wykorzystamy mechanizm tagów JSGF a za nazwę aktu dialogowego przyjmiemy nazwę\n",
"gramatyki. Wzorując się na [DSTC2](https://github.com/matthen/dstc) wynikową ramę zapiszemy korzystając ze słownika o polach `act` i `slots`."
]
},
{
"cell_type": "code",
"execution_count": 54,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'act': 'book',\n",
" 'slots': [('ilosc', '1'),\n",
" ('tytul', 'Pitbull'),\n",
" ('dzien', None),\n",
" ('godzina', None)]}"
]
},
"execution_count": 54,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def get_dialog_act(rule):\n",
" slots = []\n",
" get_slots(rule.expansion, slots)\n",
" return {'act': rule.grammar.name, 'slots': slots}\n",
"\n",
"def get_slots(expansion, slots):\n",
" if expansion.tag != '':\n",
" slots.append((expansion.tag, expansion.current_match))\n",
" return\n",
"\n",
" for child in expansion.children:\n",
" get_slots(child, slots)\n",
"\n",
" if not expansion.children and isinstance(expansion, jsgf.NamedRuleRef):\n",
" get_slots(expansion.referenced_rule.expansion, slots)\n",
"\n",
"get_dialog_act(matched[0])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Łącząc powyższe funkcje możemy zbudować prosty moduł NLU."
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'act': 'null', 'slots': []}"
]
},
"execution_count": 41,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def nlu(utterance):\n",
" matched = book_grammar.find_matching_rules(utterance)\n",
"\n",
" if matched:\n",
" return get_dialog_act(matched[0])\n",
" else:\n",
" return {'act': 'null', 'slots': []}\n",
"\n",
"nlu('chciałbym zarezerwować dwa bilety na film Pitbull')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Problemy\n",
"--------\n",
"\n",
" - Co z normalizacją wyrażeń liczbowych takich, jak godziny, daty czy numery telefonów?\n",
"\n",
" - Co w przypadku gdy więcej niż jedna reguła zostanie dopasowana?"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Zadanie\n",
"-------\n",
"Zaimplementować analizator języka naturalnego (NLU) na potrzeby realizowanego agenta dialogowego.\n",
"\n",
"Moduł powinien być zbudowany z wykorzystaniem parsingu regułowego i/lub technik uczenia maszynowego.\n",
"\n",
"Przygotować skrypt `evaluate.py` wyznaczający *dokładność* (ang. accuracy) analizatora względem zgromadzonego korpusu eksperymentalnego,\n",
"tj. stosunek liczby wypowiedzi użytkownika, w których akty dialogowe zostały rozpoznane prawidłowo do liczby wszystkich wypowiedzi użytkownika w korpusie.\n",
"\n",
"Analizator języka naturalnego umieścić w gałęzi `master` repozytorium projektowego. Skrypt `evaluate.py` umieścić w katalogu głównym tej gałęzi.\n",
"\n",
"Termin: 4.05.2022, godz. 23:59."
]
}
],
"metadata": {
"author": "Marek Kubis",
"email": "mkubis@amu.edu.pl",
"jupytext": {
"cell_metadata_filter": "-all",
"main_language": "python",
"notebook_metadata_filter": "-all"
},
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"lang": "pl",
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.3"
},
"subtitle": "7.Parsing semantyczny z wykorzystaniem gramatyk[laboratoria]",
"title": "Systemy Dialogowe",
"year": "2021"
},
"nbformat": 4,
"nbformat_minor": 4
}

74
.ipynb_checkpoints/chatbot-checkpoint.ipynb Normal file
View File

@ -0,0 +1,74 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 6,
"id": "978f5cd3-eb2e-45c4-ace8-f105ccd4cb74",
"metadata": {},
"outputs": [
{
"ename": "ModuleNotFoundError",
"evalue": "No module named 'jsgf'",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m~\\AppData\\Local\\Temp/ipykernel_12388/3924194050.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mmodules\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mDST\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mDst\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m \u001b[1;32mfrom\u001b[0m \u001b[0mmodules\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mAJN\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mAjn\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 3\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mD:\\Adi\\Szkoła\\Semestr 8\\Systemy dialogowe\\Projekt\\SystemyDialogowe\\modules\\AJN.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[1;32mimport\u001b[0m \u001b[0mjsgf\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 2\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mos\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mlistdir\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mos\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpath\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0misfile\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mjoin\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5\u001b[0m \u001b[0mmypath\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;34m\"./grammar/\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'jsgf'"
]
}
],
"source": [
"from modules.DST import Dst\n",
"from modules.AJN import Ajn\n",
"\n",
"\n",
"\n",
"if __name__ == \"__main__\":\n",
" nlg = nlg.Nlg()\n",
" nlu = nlu.Nlu()\n",
" dst = dst.Dst()\n",
"\n",
" next_question = dst.get_next_question()\n",
" while (next_question):\n",
" print(next_question)\n",
" response = input()\n",
" res_tokenized = nlu.tokenize(response)\n",
" dst.save_answer(res_tokenized['slots'])\n",
" next_question = dst.get_next_question()\n",
"\n",
" print(dst.checklist)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "bec70f0e-c4e9-488e-8748-6d976a67beae",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.7"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

326
.ipynb_checkpoints/eliza-checkpoint.py Normal file
View File

@ -0,0 +1,326 @@
from nltk.chat.util import Chat, reflections
pairs = (
(
r"I need (.*)",
(
"Why do you need %1?",
"Would it really help you to get %1?",
"Are you sure you need %1?",
),
),
(
r"who created you (.*)",
(
"ELIZA was invented in 1966 by Weizenbaum. Why %1?",
),
),
(
r"Why don\'t you (.*)",
(
"Do you really think I don't %1?",
"Perhaps eventually I will %1.",
"Do you really want me to %1?",
),
),
(
r"Why can\'t I (.*)",
(
"Do you think you should be able to %1?",
"If you could %1, what would you do?",
"I don't know -- why can't you %1?",
"Have you really tried?",
),
),
(
r"I can\'t (.*)",
(
"How do you know you can't %1?",
"Perhaps you could %1 if you tried.",
"What would it take for you to %1?",
),
),
(
r"I am (.*)",
(
"Did you come to me because you are %1?",
"How long have you been %1?",
"How do you feel about being %1?",
),
),
(
r"I\'m (.*)",
(
"How does being %1 make you feel?",
"Do you enjoy being %1?",
"Why do you tell me you're %1?",
"Why do you think you're %1?",
),
),
(
r"Are you (.*)",
(
"Why does it matter whether I am %1?",
"Would you prefer it if I were not %1?",
"Perhaps you believe I am %1.",
"I may be %1 -- what do you think?",
),
),
(
r"What (.*)",
(
"Why do you ask?",
"How would an answer to that help you?",
"What do you think?",
),
),
(
r"How (.*)",
(
"How do you suppose?",
"Perhaps you can answer your own question.",
"What is it you're really asking?",
),
),
(
r"Because (.*)",
(
"Is that the real reason?",
"What other reasons come to mind?",
"Does that reason apply to anything else?",
"If %1, what else must be true?",
),
),
(
r"(.*) sorry (.*)",
(
"There are many times when no apology is needed.",
"What feelings do you have when you apologize?",
),
),
(
r"Hello(.*)",
(
"Hello... I'm glad you could drop by today.",
"Hi there... how are you today?",
"Hello, how are you feeling today?",
),
),
(
r"I think (.*)",
("Do you doubt %1?", "Do you really think so?", "But you're not sure %1?"),
),
(
r"(.*) friend (.*)",
(
"Tell me more about your friends.",
"When you think of a friend, what comes to mind?",
"Why don't you tell me about a childhood friend?",
),
),
(r"Yes", ("You seem quite sure.", "OK, but can you elaborate a bit?")),
(
r"(.*) computer(.*)",
(
"Are you really talking about me?",
"Does it seem strange to talk to a computer?",
"How do computers make you feel?",
"Do you feel threatened by computers?",
),
),
(
r"Is it (.*)",
(
"Do you think it is %1?",
"Perhaps it's %1 -- what do you think?",
"If it were %1, what would you do?",
"It could well be that %1.",
),
),
(
r"It is (.*)",
(
"You seem very certain.",
"If I told you that it probably isn't %1, what would you feel?",
),
),
(
r"Can you (.*)",
(
"What makes you think I can't %1?",
"If I could %1, then what?",
"Why do you ask if I can %1?",
),
),
(
r"Czy mogę (.*)",
(
"Być może nie chcesz %1.",
"Czy chcesz mieć możliwość %1?",
"Gdybyś mógł %1, czy byś?",
),
),
(
r"Ty jesteś (.*)",
(
"Jak myślisz, dlaczego jestem %1?",
"Czy cieszy cię myśl, że jestem %1?",
"Być może chciałbyś, żebym był %1.",
"Może naprawdę mówisz o sobie?",
),
),
(
r"Jesteś (.*)",
(
"Dlaczego mówisz, że jestem %1?",
"Jak myślisz, dlaczego jestem %1?",
"Mówimy o tobie, czy o mnie?",
),
),
(
r"Ja nie (.*)",
("Czy naprawdę nie %1?", "Dlaczego nie %1?", "Czy chcesz %1?"),
),
(
r"Ja czuję (.*)",
(
"Dobrze, powiedz mi więcej o tych uczuciach.",
"Czy często czujesz %1?",
"Kiedy zwykle czujesz %1?",
"Kiedy czujesz % 1, co robisz?",
),
),
(
r"Mam (.*)",
(
"Dlaczego mówisz mi, że masz %1?",
"Czy naprawdę masz %1?",
"Teraz, kiedy masz %1, co zrobisz dalej?",
),
),
(
r"Ja chcę (.*)",
(
"Czy możesz wyjaśnić, dlaczego chcesz %1?",
"Dlaczego %1?",
"Kto jeszcze wie, że chcesz %1?",
),
),
(
r"Jest (.*)",
(
"Myślisz, że jest %1?",
"Prawdopodobnie istnieje %1.",
"Czy chciałbyś, aby był %1?",
),
),
(
r"Mój (.*)",
(
"Rozumiem, twój %1.",
"Dlaczego mówisz, że twój %1?",
"Kiedy Twój %1, jak się czujesz?",
),
),
(
r"Ty (.*)",
(
"Powinniśmy rozmawiać o Tobie, nie o mnie.",
"Dlaczego tak o mnie mówisz?",
"Dlaczego obchodzi cię, czy ja %1?",
),
),
(r"Dlaczego (.*)", ("Powiedz mi dlaczego %1?", "Wydaje ci się że, %1?")),
(
r"Ja chcę (.*)",
(
"Co by dla ciebie znaczyło, gdybyś dostał %1?",
"Dlaczego chcesz %1?",
"Co byś zrobił, gdybyś dostał %1?",
"Jeśli masz %1, co byś zrobił?",
),
),
(
r"(.*) mother(.*)",
(
"Tell me more about your mother.",
"What was your relationship with your mother like?",
"How do you feel about your mother?",
"How does this relate to your feelings today?",
"Good family relations are important.",
),
),
(
r"(.*) father(.*)",
(
"Tell me more about your father.",
"How did your father make you feel?",
"How do you feel about your father?",
"Does your relationship with your father relate to your feelings today?",
"Do you have trouble showing affection with your family?",
),
),
(
r"(.*) child(.*)",
(
"Did you have close friends as a child?",
"What is your favorite childhood memory?",
"Do you remember any dreams or nightmares from childhood?",
"Did the other children sometimes tease you?",
"How do you think your childhood experiences relate to your feelings today?",
),
),
(
r"(.*)\?",
(
"Why do you ask that?",
"Please consider whether you can answer your own question.",
"Perhaps the answer lies within yourself?",
"Why don't you tell me?",
),
),
(
r"quit",
(
"Thank you for talking with me.",
"Good-bye.",
"Thank you, that will be $150. Have a good day!",
),
),
(
r"(.*)",
(
"Please tell me more.",
"Let's change focus a bit... Tell me about your family.",
"Can you elaborate on that?",
"Why do you say that %1?",
"I see.",
"Very interesting.",
"%1.",
"I see. And what does that tell you?",
"How does that make you feel?",
"How do you feel when you say that?",
),
),
)
eliza_chatbot = Chat(pairs, reflections)
def eliza_chat():
print("Psychiatrist\n---------")
print("Talk to the program by typing in plain English, using normal upper-")
print('and lower-case letters and punctuation. Enter "quit" when done.')
print("=" * 72)
print("Hello. My name is Eliza.\nHow are you feeling today?")
eliza_chatbot.converse()
def demo():
eliza_chat()
if __name__ == "__main__":
demo()

4
AJN.ipynb
View File

@ -277,7 +277,7 @@
"notebook_metadata_filter": "-all" "notebook_metadata_filter": "-all"
}, },
"kernelspec": { "kernelspec": {
"display_name": "Python 3", "display_name": "Python 3 (ipykernel)",
"language": "python", "language": "python",
"name": "python3" "name": "python3"
}, },
@ -292,7 +292,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.7.3" "version": "3.7.13"
}, },
"subtitle": "7.Parsing semantyczny z wykorzystaniem gramatyk[laboratoria]", "subtitle": "7.Parsing semantyczny z wykorzystaniem gramatyk[laboratoria]",
"title": "Systemy Dialogowe", "title": "Systemy Dialogowe",

163
chatbot.ipynb Normal file
View File

@ -0,0 +1,163 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"id": "encouraging-december",
"metadata": {},
"outputs": [
{
"name": "stdin",
"output_type": "stream",
"text": [
">>> chce 2 bilety\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"tytul\n",
"{'ilosc': '2', 'tytul': None, 'dzien': None, 'godzina': None}\n",
"Na jaki film ma zostać dokonana rezerwacja?\n"
]
},
{
"name": "stdin",
"output_type": "stream",
"text": [
">>> chce na film batman\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"ilosc\n",
"{'ilosc': None, 'tytul': 'Batman', 'dzien': None, 'godzina': None}\n",
"Ile biletów ma zostać zarezerwowanych?\n"
]
},
{
"name": "stdin",
"output_type": "stream",
"text": [
">>> chce 2 bilety\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"tytul\n",
"{'ilosc': '2', 'tytul': None, 'dzien': None, 'godzina': None}\n",
"Na jaki film ma zostać dokonana rezerwacja?\n"
]
},
{
"name": "stdin",
"output_type": "stream",
"text": [
">>> chce 2 bilety na film batman\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"dzien\n",
"{'ilosc': '2', 'tytul': 'Batman', 'dzien': None, 'godzina': None}\n",
"Na który dzień ma być dokonana rezerwacja?\n"
]
},
{
"name": "stdin",
"output_type": "stream",
"text": [
">>> chce na jutro\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"ilosc\n",
"{'ilosc': None, 'tytul': None, 'dzien': 'jutro', 'godzina': None}\n",
"Ile biletów ma zostać zarezerwowanych?\n"
]
},
{
"ename": "KeyboardInterrupt",
"evalue": "Interrupted by user",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-2-0b584a7b5a30>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 12\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 13\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 14\u001b[0;31m \u001b[0mtext\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0minput\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'>>>'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 15\u001b[0m \u001b[0mframe\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0majn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtext\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 16\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/ipykernel/kernelbase.py\u001b[0m in \u001b[0;36mraw_input\u001b[0;34m(self, prompt)\u001b[0m\n\u001b[1;32m 849\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_parent_ident\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 850\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_parent_header\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 851\u001b[0;31m \u001b[0mpassword\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 852\u001b[0m )\n\u001b[1;32m 853\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/ipykernel/kernelbase.py\u001b[0m in \u001b[0;36m_input_request\u001b[0;34m(self, prompt, ident, parent, password)\u001b[0m\n\u001b[1;32m 890\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mKeyboardInterrupt\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 891\u001b[0m \u001b[0;31m# re-raise KeyboardInterrupt, to truncate traceback\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 892\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mKeyboardInterrupt\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Interrupted by user\"\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 893\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 894\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlog\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwarning\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Invalid Message:\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mexc_info\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mKeyboardInterrupt\u001b[0m: Interrupted by user"
]
}
],
"source": [
"from DST import Dst\n",
"from AJN import *\n",
"from NLG import nlg\n",
"\n",
"\n",
"\n",
"if __name__ == \"__main__\":\n",
" \n",
" dst = Dst()\n",
" next_question = dst.get_next_question()\n",
" while (next_question):\n",
" \n",
" \n",
" text = input('>>>')\n",
" frame = ajn(text)\n",
" \n",
" dst.save_answer(frame['slots'])\n",
" \n",
" next_question = dst.get_next_question()\n",
" print(next_question)\n",
" print(dst.checklist)\n",
"# print(frame['act'])\n",
" nlg(next_question)\n",
"\n",
" \n",
" \n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "yellow-acquisition",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

50
modules/.ipynb_checkpoints/AJN-checkpoint.py Normal file
View File

@ -0,0 +1,50 @@
import jsgf
from os import listdir
from os.path import isfile, join
mypath = "./grammar/"
onlyfiles = [f for f in listdir(mypath) if isfile(join(mypath, f))]
grammars = []
for grammarFile in onlyfiles:
grammar = jsgf.parse_grammar_file(mypath + grammarFile)
grammars.append(grammar)
class Ajn:
def __init__(self, grammars = None):
self.grammars = grammars
def get_dialog_act(rule):
slots = []
get_slots(rule.expansion, slots)
return {'act': rule.grammar.name, 'slots': slots}
def get_slots(expansion, slots):
if expansion.tag != '':
slots.append((expansion.tag, expansion.current_match))
return
for child in expansion.children:
get_slots(child, slots)
if not expansion.children and isinstance(expansion, jsgf.NamedRuleRef):
get_slots(expansion.referenced_rule.expansion, slots)
def nlu(utterance):
matched = None
for grammar in grammars:
matched = grammar.find_matching_rules(utterance)
if matched:
break
if matched:
return get_dialog_act(matched[0])
else:
return {'act': 'null', 'slots': []}
ajn = Ajn()

27
modules/.ipynb_checkpoints/DST-checkpoint.py Normal file
View File

@ -0,0 +1,27 @@
class Dst:
def __init__(self):
self.messages = []
self.checklist = {
"ilosc": None,
"tytul": None,
"dzien": None,
"godzina": None
}
self.history = []
def store(self, message):
self.messages.append(message)
def get_messages(self):
return self.messages
def get_next_question(self):
for key, value in self.checklist.items():
if value == None:
return key
def save_answer(self, slots):
for slot in slots:
self.checklist[slot[0]] = slot[1]
self.messages.append(slots)

10
modules/NLG.py Normal file
View File

@ -0,0 +1,10 @@
def nlg(query):
if query == 'dzien':
print("Na który dzień ma być dokonana rezerwacja?")
if query == 'godzina':
print("Na którą godzinę ma być dokonana rezerwacja?")
if query == 'ilosc':
print("Ile biletów ma zostać zarezerwowanych?")
if query == 'tytul':
print("Na jaki film ma zostać dokonana rezerwacja?")

BIN
modules/__pycache__/AJN.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
modules/__pycache__/AJN.cpython-39.pyc Normal file
View File

Binary file not shown.

BIN
modules/__pycache__/DST.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
modules/__pycache__/DST.cpython-39.pyc Normal file
View File

Binary file not shown.