Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Pararth Shah"'
Publikováno v:
COLING
Motivated by the needs of resource constrained dialog policy learning, we introduce dialog policy via differentiable inductive logic (DILOG). We explore the tasks of one-shot learning and zero-shot domain transfer with DILOG on SimDial and MultiWoZ.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::aa5f146d0b4f1c254fd0c53458a2c2da
https://doi.org/10.18653/v1/2020.coling-main.597
https://doi.org/10.18653/v1/2020.coling-main.597
Publikováno v:
COLING
We study an end-to-end approach for conversational recommendation that dynamically manages and reasons over users’ past (offline) preferences and current (online) requests through a structured and cumulative user memory knowledge graph. This formul
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a027afb1658d5f82744672e74cfced9c
Publikováno v:
EMNLP/IJCNLP (3)
We demonstrate a conversational system which engages the user through a multi-modal, multi-turn dialog over the user’s memories. The system can perform QA over memories by responding to user queries to recall specific attributes and associated medi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9c5f9eaa9e7fc8b795c059f33d9291f0
https://doi.org/10.18653/v1/d19-3025
https://doi.org/10.18653/v1/d19-3025
Publikováno v:
CoNLL
We introduce Episodic Memory QA, the task of answering personal user questions grounded on memory graph (MG), where episodic memories and related entity nodes are connected via relational edges. We create a new benchmark dataset first by generating s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6e649daf78ff60f66248232d8f038b99
https://doi.org/10.18653/v1/k19-1068
https://doi.org/10.18653/v1/k19-1068
Publikováno v:
ACL (1)
We study a conversational reasoning model that strategically traverses through a large-scale common fact knowledge graph (KG) to introduce engaging and contextually diverse entities and attributes. For this study, we collect a new Open-ended Dialog K
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cc80d23ad976eca313be17874194b6ff
https://doi.org/10.18653/v1/p19-1081
https://doi.org/10.18653/v1/p19-1081
Publikováno v:
SLT
We introduce end-to-end neural network based models for simulating users of task-oriented dialogue systems. User simulation in dialogue systems is crucial from two different perspectives: (i) automatic evaluation of different dialogue models, and (ii
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c5c9a283d1700211f0f0fa3d6041f69a
https://doi.org/10.1109/slt.2018.8639652
https://doi.org/10.1109/slt.2018.8639652
Publikováno v:
NAACL-HLT
In this work, we present a hybrid learning method for training task-oriented dialogue systems through online user interactions. Popular methods for learning task-oriented dialogues include applying reinforcement learning with user feedback on supervi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5bed47108b60c324f5be0dff568b283c
http://arxiv.org/abs/1804.06512
http://arxiv.org/abs/1804.06512
Publikováno v:
NAACL-HLT (3)
End-to-end neural models show great promise towards building conversational agents that are trained from data and on-line experience using supervised and reinforcement learning. However, these models require a large corpus of dialogues to learn effec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8c2c9b760229296b52482801512d5020
https://doi.org/10.18653/v1/n18-3006
https://doi.org/10.18653/v1/n18-3006
Publikováno v:
CODS
Recently Kulkarni et al. [20] proposed an approach for collective disambiguation of entity mentions occurring in natural language text. Their model achieves disambiguation by efficiently computing exact MAP inference in a binary labeled Markov Random
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4750162d7ccdd533d7305a985e4656d8
https://doi.org/10.1145/2888451.2888454
https://doi.org/10.1145/2888451.2888454
Autor:
Martin Raison, Rohan Puttagunta, Arijit Banerjee, Pararth Shah, Jure Leskovec, Yonathan Perez, Rok Sosic
Publikováno v:
Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data.
We present Ringo, a system for analysis of large graphs. Graphs provide a way to represent and analyze systems of interacting objects (people, proteins, webpages) with edges between the objects denoting interactions (friendships, physical interaction
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::39688c26579ca708ca23051dde60e40c
https://doi.org/10.1145/2723372.2735369
https://doi.org/10.1145/2723372.2735369