Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Rajen Subba"'
Autor:
Rajen Subba, Seungwhan Moon, Eunjoon Cho, Zhiguang Wang, Zhenpeng Zhou, Bing Liu, Zhaojiang Lin, Paul A. Crook, Andrea Madotto, Zhou Yu
Publikováno v:
NAACL-HLT
Zero-shot cross-domain dialogue state tracking (DST) enables us to handle unseen domains without the expense of collecting in-domain data. In this paper, we propose a slot descriptions enhanced generative approach for zero-shot cross-domain DST. Spec
Autor:
Shivani Poddar, Theodore Levin, Paul A. Crook, David Whitney, Satwik Kottur, Seungwhan Moon, Ankita De, Ahmad Beirami, Rajen Subba, Eunjoon Cho, Daniel Difranco, Alborz Geramifard
Publikováno v:
COLING
Next generation virtual assistants are envisioned to handle multimodal inputs (e.g., vision, memories of previous interactions, in addition to the user's utterances), and perform multimodal actions (e.g., displaying a route in addition to generating
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.
Publikováno v:
Scopus-Elsevier
Kartikeya Upasani
ACL (1)
Kartikeya Upasani
ACL (1)
Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems. Avenues like the E2E NLG Challenge have encouraged the development of neural approaches, particularly se
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5d812b5b65c1a172e1ae45861ae901ce
http://arxiv.org/abs/1906.07220
http://arxiv.org/abs/1906.07220
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
Publikováno v:
NAACL-HLT (2)
Neural approaches to Natural Language Generation (NLG) have been promising for goal-oriented dialogue. One of the challenges of productionizing these approaches, however, is the ability to control response quality, and ensure that generated responses
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
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
Autor:
Rajen Subba, Andreas Stolcke, Michael Levit, Sarangarajan Parthasarathy, Shuangyu Chang, Benoit Dumoulin, T. Anastasakos, S. Xie
Publikováno v:
INTERSPEECH
We continue our investigations of Word-Phrase-Entity (WPE) Language Models that unify words, phrases and classes, such as named entities, into a single probabilistic framework for the purpose of language modeling. In the present study we show how WPE
Publikováno v:
ICSC
Short posts on micro-blogs are characterized by high ambiguity and non-standard language. We focus on detecting life events from such micro-blogs, a type of event which have not been paid much attention so far. We discuss the corpus we assembled and