Zobrazeno 1 - 10
of 67
pro vyhledávání: '"Timothy J. Hazen"'
Publikováno v:
First Monday; Volume 27, Number 2-7 February 2022
Past research shows that users benefit from systems that support them in their writing and exploration tasks. The autosuggestion feature of Web search engines is an example of such a system: It helps users in formulating their queries by offering a l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9a7ba6ffed6fb287a963c6c09cff8946
http://arxiv.org/abs/2007.05039
http://arxiv.org/abs/2007.05039
Publikováno v:
ArgMining@ACL
In data ranking applications, pairwise annotation is often more consistent than cardinal annotation for learning ranking models. We examine this in a case study on ranking text passages for argument convincingness. Our task is to choose text passages
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::84efae2b6c7952e297f5645331cda049
https://doi.org/10.18653/v1/w19-4517
https://doi.org/10.18653/v1/w19-4517
Autor:
Timothy J. Hazen, Soroush Mehri, Yadollah Yaghoobzadeh, Remi Tachet des Combes, Alessandro Sordoni
Publikováno v:
Scopus-Elsevier
EACL
EACL
Neural NLP models tend to rely on spurious correlations between labels and input features to perform their tasks. Minority examples, i.e., examples that contradict the spurious correlations present in the majority of data points, have been shown to i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::faea1beec554e106d2c85ff9d40e6119
Autor:
Timothy J. Hazen, Marc-Antoine Rondeau
Publikováno v:
QA@ACL
We analyzed the outputs of multiple question answering (QA) models applied to the Stanford Question Answering Dataset (SQuAD) to identify the core challenges for QA systems on this data set. Through an iterative process, challenging aspects were hypo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5d8c8159b10545a1e2fca48047709230
https://doi.org/10.18653/v1/w18-2602
https://doi.org/10.18653/v1/w18-2602
Autor:
Timothy J. Hazen
Publikováno v:
IEEE Transactions on Audio, Speech, and Language Processing. 19:2451-2460
In this paper, we discuss the use of minimum classification error (MCE) training as a means for improving traditional approaches to topic identification such as naive Bayes classifiers and support vector machines. A key element of our new MCE trainin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::523055baedf60121aec2b165afe173c6
https://doi.org/10.1109/tasl.2011.2139207
https://doi.org/10.1109/tasl.2011.2139207
Publikováno v:
IEEE Signal Processing Magazine. 25:39-49
Ever-increasing computing power and connectivity bandwidth, together with falling storage costs, are resulting in an overwhelming amount of data of various types being produced, exchanged, and stored. Consequently, information search and retrieval ha
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::28eeb1649d8ce9140edf41becb3794e7
https://doi.org/10.1109/msp.2008.917992
https://doi.org/10.1109/msp.2008.917992
Publikováno v:
IEEE Transactions on Audio, Speech and Language Processing. 15:1711-1723
This paper investigates the problem of speaker identification and verification in noisy conditions, assuming that speech signals are corrupted by environmental noise, but knowledge about the noise characteristics is not available. This research is mo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::74429a9e7e88676567be151cb2deefd7
https://doi.org/10.1109/tasl.2007.899278
https://doi.org/10.1109/tasl.2007.899278
Publikováno v:
IEEE Transactions on Audio, Speech and Language Processing. 15:203-223
The minimum classification error (MCE) framework for discriminative training is a simple and general formalism for directly optimizing recognition accuracy in pattern recognition problems. The framework applies directly to the optimization of hidden
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::aeababe944ac2a2e26f75f7f3add8709
https://doi.org/10.1109/tasl.2006.876778
https://doi.org/10.1109/tasl.2006.876778
Publikováno v:
ICASSP
Recently there has been great interest in the application of word representation techniques to various natural language processing (NLP) scenarios. Word representation features from techniques such as Brown clustering or spectral clustering are gener
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::957cb7e98f58d37cc60f2c9d6140ec6e
https://doi.org/10.1109/icassp.2015.7178984
https://doi.org/10.1109/icassp.2015.7178984
Autor:
Timothy J. Hazen
Publikováno v:
IEEE Transactions on Audio, Speech and Language Processing. 14:1082-1089
This paper presents the design and evaluation of a speaker-independent audio-visual speech recognition (AVSR) system that utilizes a segment-based modeling strategy. The audio and visual feature streams are integrated using a segment-constrained hidd
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0e31917139b734ace3209051561d4bfd
https://doi.org/10.1109/tsa.2005.857572
https://doi.org/10.1109/tsa.2005.857572