Filters








29,462 Hits in 9.8 sec

A Natural Language Corpus of Common Grounding under Continuous and Partially-Observable Context

Takuma Udagawa, Akiko Aizawa
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In this paper, we propose a minimal dialogue task which requires advanced skills of common grounding under continuous and partially-observable context.  ...  Based on this task formulation, we collected a largescale dataset of 6,760 dialogues which fulfills essential requirements of natural language corpora.  ...  Therefore, we conclude that introducing continuity and partially-observability to the context is a critical solution to add natural difficulty in terms of common grounding.  ... 
doi:10.1609/aaai.v33i01.33017120 fatcat:to2ufev7u5derggzm36biasjha

An Annotated Corpus of Reference Resolution for Interpreting Common Grounding

Takuma Udagawa, Akiko Aizawa
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
However, interpreting the process of common grounding is a challenging task, especially under continuous and partially-observable context where complex ambiguity, uncertainty, partial understandings and  ...  Common grounding is the process of creating, repairing and updating mutual understandings, which is a fundamental aspect of natural language conversation.  ...  Acknowledgements This work was supported by JSPS KAKENHI Grant Number 18H03297 and NEDO SIP-2 "Big-data and AI-enabled Cyberspace Technologies."  ... 
doi:10.1609/aaai.v34i05.6442 fatcat:wexhbkjrrjewtkhmbbkwp6zdpm

An Annotated Corpus of Reference Resolution for Interpreting Common Grounding [article]

Takuma Udagawa, Akiko Aizawa
2019 arXiv   pre-print
However, interpreting the process of common grounding is a challenging task, especially under continuous and partially-observable context where complex ambiguity, uncertainty, partial understandings and  ...  Common grounding is the process of creating, repairing and updating mutual understandings, which is a fundamental aspect of natural language conversation.  ...  Acknowledgements This work was supported by JSPS KAKENHI Grant Number 18H03297 and NEDO SIP-2 "Big-data and AI-enabled Cyberspace Technologies.  ... 
arXiv:1911.07588v1 fatcat:r2itbnbbtnhd5alu6nsp4hjauu

Maintaining Common Ground in Dynamic Environments

Takuma Udagawa, Akiko Aizawa
2021 Transactions of the Association for Computational Linguistics  
While various task settings have been proposed in existing literature, they mostly focus on creating common ground under a static context and ignore the aspect of maintaining them overtime under dynamic  ...  Common grounding is the process of creating and maintaining mutual understandings, which is a critical aspect of sophisticated human communication.  ...  Acknowledgments We are grateful to our action editor, Michel Galley, and the three anonymous reviewers for  ... 
doi:10.1162/tacl_a_00409 fatcat:ifrzbkqcfra6zcd56cuhhotdpe

A Linguistic Analysis of Visually Grounded Dialogues Based on Spatial Expressions [article]

Takuma Udagawa, Takato Yamazaki, Akiko Aizawa
2020 arXiv   pre-print
To address this problem, we make two design choices: first, we focus on OneCommon Corpus , a simple yet challenging common grounding dataset which contains minimal bias by design.  ...  Overall, we propose a novel framework and resource for investigating fine-grained language understanding in visually grounded dialogues.  ...  Acknowledgements This work was supported by JSPS KAKENHI Grant Number 18H03297 and NEDO SIP-2 "Bigdata and AI-enabled Cyberspace Technologies."  ... 
arXiv:2010.03127v1 fatcat:s3bsa7qb6fdalopkntel2szdpa

Subsequence similarity language models

Juan M. Huerta
2011 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
As a language model, S2-LM generates scores based on the closest matching string given a very large corpus.  ...  In this paper we describe the properties and advantages of our approach and describe efficient methods to carry out its computation.  ...  partially, regardless of length. 2.  ... 
doi:10.1109/icassp.2011.5947624 dblp:conf/icassp/Huerta11 fatcat:tzjz44ulbzbd5j2kga5censam4

CORPUS-BASED METHOD IN TEACHING VOCABULARY

LILIT MOVSESYAN
2021 Bulletin of Yerevan Brusov State University of Languages and Social Sciences. Pedagogy and Social Sciences  
It utilizes a large and principled collection of natural texts, known as a corpus, as the basis for analysis.  ...  And to make good use of corpus resources one needs a modest orientation to the routines involved in retrieving information from the corpus, and most importantly training and experience in how to evaluate  ...  It utilizes a large and principled collection of natural texts, known as a corpus, as the basis for analysis.  ... 
doi:10.51307/182931072015233260/21.2-128 fatcat:e662xzwenrfffekdv5pafqxwjy

Probabilistic Modeling of Joint-context in Distributional Similarity

Oren Melamud, Ido Dagan, Jacob Goldberger, Idan Szpektor, Deniz Yuret
2014 Proceedings of the Eighteenth Conference on Computational Natural Language Learning  
In this work we introduce a novel generic distributional similarity scheme under which the power of probabilistic models can be leveraged to effectively model joint contexts.  ...  Following this, we propose our scheme as a framework for future semantic similarity models leveraging the substantial body of work that exists in probabilistic language modeling.  ...  Programme (FP7/2007(FP7/ -2013 under grant agreement no. 287923 (EXCITEMENT) and the Scientific and Technical Research Council of Turkey (TÜBİTAK, Grant Number 112E277).  ... 
doi:10.3115/v1/w14-1619 dblp:conf/conll/MelamudDGSY14 fatcat:btuxmhghanfzrgxxnlkg2eivpy

Multimodal estimation and communication of latent semantic knowledge for robust execution of robot instructions

Jacob Arkin, Daehyung Park, Subhro Roy, Matthew R Walter, Nicholas Roy, Thomas M Howard, Rohan Paul
2020 The international journal of robotics research  
The goal of this article is to enable robots to perform robust task execution following human instructions in partially observable environments.  ...  We introduce a probabilistic model that fuses linguistic knowledge with visual and haptic observations into a cumulative belief over latent world attributes to infer the meaning of instructions and execute  ...  Toyota Research Institute (TRI) Award Number LP-C000765-SR, and Lockheed Martin Co.. We thank Michael Noseworthy for valuable feedback on this manuscript.  ... 
doi:10.1177/0278364920917755 fatcat:u2w3o7h4svea5gdryo6bfe5xae

Prosodic forms and pragmatic meanings: The case of the discourse marker 'no' in Slovak

Stefan Benus
2012 2012 IEEE 3rd International Conference on Cognitive Infocommunications (CogInfoCom)  
This paper provides a first analysis of the Slovak word [no] that is extremely ambiguous in terms of pragmatic and discourse functions and can correspond to 'okay', 'yes', 'well', 'mhm', 'so', and others  ...  We report that the function of backchannel/continuer is the most easily disambiguated by the pitch contour, duration, and other features.  ...  RESULTS A. Descriptive observations There are 644 tokens of no in the corpus, hence on average 107 for each session.  ... 
doi:10.1109/coginfocom.2012.6421961 fatcat:vdjnz7ed5raqnbhpklprm3a7ni

An empirical generative framework for computational modeling of language acquisition

Heidi R. Waterfall, Ben Sandbank, Luca Onnis, Shimon Edelman
2010 Journal of Child Language  
A B S T R A C T This paper reports progress in developing a computer model of language acquisition in the form of (1) a generative grammar that is (2) algorithmically learnable from realistic corpus data  ...  Next, we summarize findings from recent longitudinal and experimental work that suggests how certain statistically prominent structural properties of child-directed speech may facilitate language acquisition  ...  The need for a realistic corpus of language data In order to integrate computational and behavioral approaches to language acquisition, it is necessary to use a common corpus of recorded language that  ... 
doi:10.1017/s0305000910000024 pmid:20420744 fatcat:272iidhhyzaqdhaofqxamyj54u

Probabilistic Modeling [chapter]

Bart Nicolaï, Nico Scheerlinck, Maarten Hertog
2006 Food Science and Technology  
In this work we introduce a novel generic distributional similarity scheme under which the power of probabilistic models can be leveraged to effectively model joint contexts.  ...  Following this, we propose our scheme as a framework for future semantic similarity models leveraging the substantial body of work that exists in probabilistic language modeling.  ...  Programme (FP7/2007(FP7/ -2013 under grant agreement no. 287923 (EXCITEMENT) and the Scientific and Technical Research Council of Turkey (TÜBİTAK, Grant Number 112E277).  ... 
doi:10.1201/9781420015072.ch8 fatcat:t5hk2r4w6rgpzglicehzc5irsa

We went to look for meaning and all we got were these lousy representations: aspects of meaning representation for computational semantics [article]

Simon Dobnik, Robin Cooper, Adam Ek, Bill Noble, Staffan Larsson, Nikolai Ilinykh, Vladislav Maraev, Vidya Somashekarappa
2021 arXiv   pre-print
In this paper we examine different meaning representations that are commonly used in different natural language applications today and discuss their limits, both in terms of the aspects of the natural  ...  language meaning they are modelling and in terms of the aspects of the application for which they are used.  ...  Acknowledgments The research reported in this paper was supported by a grant from the Swedish Research Council (VR project 2014-39) for the establishment of the Centre for Linguistic Theory and Studies  ... 
arXiv:2109.04949v1 fatcat:am723u3rtraknip6lw6rn5xu2a

Experience Grounds Language [article]

Yonatan Bisk, Ari Holtzman, Jesse Thomason, Jacob Andreas, Yoshua Bengio, Joyce Chai, Mirella Lapata, Angeliki Lazaridou, Jonathan May, Aleksandr Nisnevich, Nicolas Pinto, Joseph Turian
2020 arXiv   pre-print
Natural language processing is a diverse field, and progress throughout its development has come from new representational theories, modeling techniques, data collection paradigms, and tasks.  ...  We posit that the present success of representation learning approaches trained on large, text-only corpora requires the parallel tradition of research on the broader physical and social context of language  ...  But, a large and noisy text corpus is still a text corpus.  ... 
arXiv:2004.10151v3 fatcat:adz5yefshjbzhmypcr7anigu5a

Grounding Conversations with Improvised Dialogues [article]

Hyundong Cho, Jonathan May
2020 arXiv   pre-print
Improvisational theater (improv) intrinsically contains a high proportion of dialogue focused on building common ground, and makes use of the yes-and principle, a strong grounding speech act, to establish  ...  Modern dialogue systems are not explicitly trained to build common ground, and therefore overlook this important aspect of communication.  ...  Acknowledgments Many thanks to Nanyun Peng and Xinyu Wang for key contributions in a preliminary study, to Paul F.  ... 
arXiv:2004.09544v2 fatcat:kxprozmobnbrrn35n6ygfsynre
« Previous Showing results 1 — 15 out of 29,462 results