@inproceedings{papasarantopoulos-etal-2019-partners,
title = "Partners in Crime: Multi-view Sequential Inference for Movie Understanding",
author = "Papasarantopoulos, Nikos and
Frermann, Lea and
Lapata, Mirella and
Cohen, Shay B.",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1212",
doi = "10.18653/v1/D19-1212",
pages = "2057--2067",
abstract = "Multi-view learning algorithms are powerful representation learning tools, often exploited in the context of multimodal problems. However, for problems requiring inference at the token-level of a sequence (that is, a separate prediction must be made for every time step), it is often the case that single-view systems are used, or that more than one views are fused in a simple manner. We describe an incremental neural architecture paired with a novel training objective for incremental inference. The network operates on multi-view data. We demonstrate the effectiveness of our approach on the problem of predicting perpetrators in crime drama series, for which our model significantly outperforms previous work and strong baselines. Moreover, we introduce two tasks, crime case and speaker type tagging, that contribute to movie understanding and demonstrate the effectiveness of our model on them.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="papasarantopoulos-etal-2019-partners">
<titleInfo>
<title>Partners in Crime: Multi-view Sequential Inference for Movie Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikos</namePart>
<namePart type="family">Papasarantopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lea</namePart>
<namePart type="family">Frermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mirella</namePart>
<namePart type="family">Lapata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shay</namePart>
<namePart type="given">B</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multi-view learning algorithms are powerful representation learning tools, often exploited in the context of multimodal problems. However, for problems requiring inference at the token-level of a sequence (that is, a separate prediction must be made for every time step), it is often the case that single-view systems are used, or that more than one views are fused in a simple manner. We describe an incremental neural architecture paired with a novel training objective for incremental inference. The network operates on multi-view data. We demonstrate the effectiveness of our approach on the problem of predicting perpetrators in crime drama series, for which our model significantly outperforms previous work and strong baselines. Moreover, we introduce two tasks, crime case and speaker type tagging, that contribute to movie understanding and demonstrate the effectiveness of our model on them.</abstract>
<identifier type="citekey">papasarantopoulos-etal-2019-partners</identifier>
<identifier type="doi">10.18653/v1/D19-1212</identifier>
<location>
<url>https://aclanthology.org/D19-1212</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>2057</start>
<end>2067</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Partners in Crime: Multi-view Sequential Inference for Movie Understanding
%A Papasarantopoulos, Nikos
%A Frermann, Lea
%A Lapata, Mirella
%A Cohen, Shay B.
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F papasarantopoulos-etal-2019-partners
%X Multi-view learning algorithms are powerful representation learning tools, often exploited in the context of multimodal problems. However, for problems requiring inference at the token-level of a sequence (that is, a separate prediction must be made for every time step), it is often the case that single-view systems are used, or that more than one views are fused in a simple manner. We describe an incremental neural architecture paired with a novel training objective for incremental inference. The network operates on multi-view data. We demonstrate the effectiveness of our approach on the problem of predicting perpetrators in crime drama series, for which our model significantly outperforms previous work and strong baselines. Moreover, we introduce two tasks, crime case and speaker type tagging, that contribute to movie understanding and demonstrate the effectiveness of our model on them.
%R 10.18653/v1/D19-1212
%U https://aclanthology.org/D19-1212
%U https://doi.org/10.18653/v1/D19-1212
%P 2057-2067
Markdown (Informal)
[Partners in Crime: Multi-view Sequential Inference for Movie Understanding](https://aclanthology.org/D19-1212) (Papasarantopoulos et al., EMNLP-IJCNLP 2019)
ACL
- Nikos Papasarantopoulos, Lea Frermann, Mirella Lapata, and Shay B. Cohen. 2019. Partners in Crime: Multi-view Sequential Inference for Movie Understanding. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 2057–2067, Hong Kong, China. Association for Computational Linguistics.