Towards Universal Dialog State Tracking

Transcript

1. Towards Universal Dialogue State Tracking ੉઱ഘ (ML Engineer, Pingpong)
2. Towards Universal Dialogue State Tracking Overview • “Towards Universal Dialogue State Tracking” • Liliang Ren, Kaige Xie, Lu Chen and Kai Yu (Shanghai Jiao Tong University) • EMNLP 2018 Oral • Contributions • Dialogue State Trackingਸ ਤೠ “StateNet” ઁউ • DSTC2, WoZ datasetীࢲ state-of-the-art ࢿמ
3. 1. Introduction Towards Universal Dialogue State Tracking, (Ren et al., 2018)
4. Dialogue System 1. Introduction Natural Language Understanding (NLU) Dialogue Management (DM) Natural Language Generation (NLG) Response Query
5. Dialogue System 1. Introduction Natural Language Understanding (NLU) Dialogue Management (DM) Natural Language Generation (NLG) Response Query Dialogue Management (DM)
6. Dialogue Management 1. Introduction • DM਷ ௼ѱ 2о૑ ޷࣌ਸ ыҊ ੓਺ 1. Dialogue State Tracking (DST) • അ੤ ؀ചо যڌѱ ൗ۞оҊ ੓ח૑ ౵ঈ • ૑Әө૑ ؀ചܳ ా೧ ঳਷ ੿ࠁܳ ӝ߈ਵ۽ ࢚కܳ ҳೞҊ ਬ૑ 2. Decision Making • അ੤ ࢚కী ঌݏ਷ ঘ࣌ਸ Policyী ٮۄ Ѿ੿
7. Dialogue State Tracking 1. Introduction • ؀ച੄ ࢚కܳ ୶੸ೞח NLP, Dialogue ࠙ঠ੄ ؀಴੸ੋ ޙઁ • Task-oriented Dialogueܳ ੹੤۽ ೣ • ݾ੸ = User੄ Goalী ب׳ೞҊ Requestܳ ೧Ѿ೧઱ח Ѫ • Ex. ۨझషی ୶ୌਸ ਤೠ ؀ച दझమ • ݾ੸ = Userо ਗೞח ۨझషی੄ ઑѤਸ ଺ইղח Ѫ • DSTח ੉۠ Goalਸ ੜ ଺ইоח૑ ݒ ఢ݃׮ ഛੋೞח Ѫ
8. Dialogue State Tracking Challenge 2 (DSTC2) 1. Introduction • Target Label = (act, slot, value) • act = {inform, request} • slot of inform = {food, pricerange, name, area} • food = {korean, chinese, japanese, french, halal, …} # 91ѐ • pricerange = {cheap, moderate, expensive} • name = {оѱ ੉ܴ} # 113ѐ • area = {north, south, east, west, centre} • slot of request = slot of inform + {addr, phone, postcode, signature} • Evaluation Metric = (Joint) Accuracy
9. Limitations of Previous Works 1. Introduction • Slot੄ Valuesо ز੸ਵ۽ ߸ೞח ജ҃ীࢲ ੜ ੘زೞ૑ ঋ਺ • ҙҟ ੿ࠁ दझమী ࢜۽਍ Value(ۨझషی, ഐభ ١)੉ ୶оؼ ࣻ ੓਺ • Slot੄ ѐࣻী ࠺۹೧ࢲ ݽ؛ ౵ۄ޷ఠ ௼ӝо ழ૗ • Slot݃׮ ݽ؛ਸ ݅ٞ • Hand-crafted Lexicon Featureܳ ӝ߈ਵ۽ ೣ • ী۞ ੹౵, ࣘب ੷ೞ
10. 2. Method Towards Universal Dialogue State Tracking, (Ren et al., 2018)
11. StateNet: A Universal Dialogue State Tracker 2. Method Utterance Machine Act Slot Values for Slot Probability Distribution of Values
12. StateNet: A Universal Dialogue State Tracker 2. Method “ೠध੉ જਸ Ѫ эই” request(food) food {ೠध, ઺ध, …} [ೠध: 0.8, ઺ध: 0.1 …]
13. StateNet: A Universal Dialogue State Tracker 2. Method Contextual Modeling
14. Utterance Representation 2. Method • Multi-scale Receptors Layerܳ ా೧ n-gram ӝ߈੄ repr ࢤࢿ
 = 1-gram, 2-gram, …, n-gram੄ reprܳ ׮ Sumೠ Ѫ • K-gram੄ Representation • kѐ ױਤ੄ seq of wordsܳ ҳࢿೞח word vector ೤ • ਤ੄ word vector ೤ਸ ݽف concat • Concat ӝ߈੉ӝ ٸޙী kী ٮۄࢲ ߭ఠ ӡ੉о ׳ۄઉࢲ Linear కਕࢲ ӡ੉ ݏ୺
15. Machine Act Representation 2. Method • Machine Actח ૒੹ दझమ ߊച੄ ӝ߈੉ غח Dialogue Act • e.g., welcomemsg, request, canthelp, inform, offer ١ • ਤ੄ ױয(pre-defined)ী ؀೧ࢲ Bag-of-words۽ ಴അ • ੉റ ো࢑ਸ ਤ೧ Linear కਕࢲ ରਗਸ Utterance Representationҗ ݏ୺
16. Slot Information Decoding 2. Method • Slotী ؀ೠ ੿ࠁܳ ೣԋ ֍যષ • Slot੄ ੉ܴ ੗୓ী ؀ೠ pre-trained word embeddingਸ ഝਊ • ৉द ରਗਸ ݏ୾઱ӝ ਤ೧ Linear క਑
17. Turn-level Feature Vector 2. Method • খࢲ ҳೠ Utterance, Machine Act, Slotਸ ઙ೤ೠ Vector • Utterance৬ Machine Actח concatೞҊ
 Ӓ Ѿҗী Slotਸ point-wise multiplicationೣ • ୭ઙ੸ਵ۽ ҳೠ Turn-level Feature Vectorח LSTM੄ Input੉ ؽ
18. 2-Norm Distance 2. Method • LSTM੄ output, ૊ Context৬ Slotਸ Ҋ۰ೠ reprਸ ҳೣ • ੉ী ؀೧ࢲ оמೠ ݽٚ Valueٜҗ੄ ਬࢎب(L2)ܳ ҳೣ • Ѿҗী ؀೧ࢲ Softmax ஂ೧ࢲ ୭ઙ Slotী ؀ೠ Value Prediction • Slotী ؀ೠ Valueо (ই૒) হਸ ࣻ ੓ӝী “None”ਸ Value Setী ୶о • ૑Әө૑੄ җ੿ਸ п ఢ݃׮ ݽٚ Slot(inform)ী ؀೧ ૓೯ [ೠध: 0.8, ઺ध: 0.1 …] {ೠध, ઺ध, …} food Context
19. 3. Experiments Towards Universal Dialogue State Tracking, (Ren et al., 2018)
20. Performance: Joint Goal Accuracy 3. Experiments
21. Performance: Joint Goal Accuracy 3. Experiments • Parameter Sharing among the Different Slots • ੉੹ োҳח Slot݃׮ ݽ؛ਸ ٜ݅঻חؘ ੉ܳ ӓࠂ • Initialization with a Pre-trained Model • ೞա੄ Slotী ؀೧ࢲ Pre-trainingਸ ೞҊ, 
 Ѿҗ Weight۽ ݽٚ Slotী ؀ೠ ݽ؛ਸ Initialization
22. Initialization with a Pre-trained Model 3. Experiments • ੹୓ Slot ઺ foodী ؀೧ࢲ pre-trainingਸ ೮ਸ ٸ о੢ જও਺ • ׮ܲ Slotী ࠺೧ foodо о੢ য۵ӝ ٸޙী pre-trainingী ؀ೠ
 ੉ٙ੉ о੢ ௾ ѱ ইקө ୶ஏ • ੌઙ੄ Weak Slotী ؀ೠ Boosting ѐ֛ਵ۽ ࢤп೧ࠅ ࣻ ੓਺
 (Ӓր ੜ ޅ ݏ୶ח Ѣ(Weakness)ী ؀೧ ೟ण۝ਸ ט۰ࢲ ࢿמਸ ֫ੋ ࣅ = Boosting)
23. 4. Conclusion Towards Universal Dialogue State Tracking, (Ren et al., 2018)
24. Contributions 4. Conclusion • ੉੹ ݽ؛ٜ੄ ೠ҅ܳ ӓࠂೞח StateNet ઁউ • ز੸ਵ۽ Slot੄ Valueо ߸ೡ ٸ ੜ ੘زೞ૑ ঋ਺ • Slotী ٮܲ ѐ߹ ݽ؛۽ ੋೠ ੹୓ ౵ۄ޷ఠ ন ૐо • Hand-crafted Lexicon Feature ࢎਊ • DSTC2, WoZ datasetী ؀೧ࢲ state-of-the-art ࢿמਸ ࠁ੐
25. хࢎ೤פ׮✌ ୶о ૕ޙ ژח ҾӘೠ ੼੉ ੓׮ݶ ঱ઁٚ ইې োۅ୊۽ োۅ ઱ࣁਃ! ੉઱ഘ (ML Engineer, Pingpong) Email. joohong@scatterlab.co.kr Facebook. @roomylee Linked in. @roomylee