Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Angeliki Metallinou"'
Publikováno v:
AAAI
Task oriented dialog agents provide a natural language interface for users to complete their goal. Dialog State Tracking (DST), which is often a core component of these systems, tracks the system's understanding of the user's goal throughout the conv
Autor:
Minmin Shen, Vincent Auvray, Shuyang Gao, Nehal Belgamwar, Qing Liu, Rahul Goel, Sanchit Agarwal, Chien-Wei Lin, Peter Ku, Arijit Biswas, Vishal Ishwar Naik, Yi Pan, Abhishek Sethi, Prakash Krishnan, Eddie Wang, Abhay Jha, Tagyoung Chung, Raefer Gabriel, Jiun-Yu Kao, Arindam Mandal, Jan Jezabek, Shubhra Chandra, Dilek Hakkani-Tur, Angeliki Metallinou, Nikko Strom, Anish Acharya, Anuj Goyal, Vittorio Perera, Shachi Paul, Maryam Fazel-Zarandi, Suranjit Adhikari
Publikováno v:
NAACL-HLT (Demonstrations)
Traditional goal-oriented dialogue systems rely on various components such as natural language understanding, dialogue state tracking, policy learning and response generation. Training each component requires annotations which are hard to obtain for
Publikováno v:
NAACL-HLT (1)
Knowledge graph based simple question answering (KBSQA) is a major area of research within question answering. Although only dealing with simple questions, i.e., questions that can be answered through a single knowledge base (KB) fact, this task is n
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2c82417876729b9bc9d2d07604f6d0df
http://arxiv.org/abs/1904.04049
http://arxiv.org/abs/1904.04049
Autor:
Angeliki Metallinou, Shuyang Gao, Abhishek Sethi, Nikolaos Malandrakis, Minmin Shen, Anuj Goyal
Publikováno v:
NGT@EMNLP-IJCNLP
Data availability is a bottleneck during early stages of development of new capabilities for intelligent artificial agents. We investigate the use of text generation techniques to augment the training data of a popular commercial artificial agent acr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3b38ebe667c6ee7e0d4bc8e536d19fa6
Publikováno v:
ICMI
This paper presents an introduction to the "Human-Habitat for Health (H3): Human-habitat multimodal interaction for promoting health and well-being in the Internet of Things era" workshop, which was held at the 20th ACM International Conference on Mu
Publikováno v:
Speech Communication. 73:14-27
DNN-HMMs outperform GMM-HMMs by a large margin for all spoken assessment tasks.Open-ended tasks benefit far more than constrained tasks from the use of DNN-HMMs.For open-ended tasks, DNN-HMMs can take full advantage of increasing training data.The pe
Autor:
Chandra Khatri, Anirudh Raju, Angeliki Metallinou, Linda Liu, Anu Venkatesh, Behnam Hedayatnia, Ankur Gandhe, Ariya Rastrow
Publikováno v:
INTERSPEECH
Statistical language models (LM) play a key role in Automatic Speech Recognition (ASR) systems used by conversational agents. These ASR systems should provide a high accuracy under a variety of speaking styles, domains, vocabulary and argots. In this
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::725d0bd3aecd6383ca354c6e4a78e77a
http://arxiv.org/abs/1806.10215
http://arxiv.org/abs/1806.10215
Publikováno v:
NAACL-HLT (3)
Fast expansion of natural language functionality of intelligent virtual agents is critical for achieving engaging and informative interactions. However, developing accurate models for new natural language domains is a time and data intensive process.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3197263ece6afba6cde794bca5f111a1
http://arxiv.org/abs/1805.01542
http://arxiv.org/abs/1805.01542
Publikováno v:
Scopus-Elsevier
AAAI
AAAI
Deep learning models have become state of the art for natural language processing (NLP) tasks, however deploying these models in production system poses significant memory constraints. Existing compression methods are either lossy or introduce signif
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cbcaab0baf6a7e6aac80c87d1f94f114
Publikováno v:
AAAI
User interaction with voice-powered agents generates large amounts of unlabeled utterances. In this paper, we explore techniques to efficiently transfer the knowledge from these unlabeled utterances to improve model performance on Spoken Language Und
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2b69c1497af91b8c9001e68b40ccf0e7