The DOI matches its Crossref record; 40 of the 40 references it cites were found in a registry or an index.
From Group to Individual Labels Using Deep Features
Abstract
In many classification problems labels are relatively scarce. One context in which this occurs is where we have labels for groups of instances but not for the instances themselves, as in multi-instance learning. Past work on this problem has typically focused on learning classifiers to make predictions at the group level. In this paper we focus on the problem of learning classifiers to make predictions at the instance level. To achieve this we propose a new objective function that encourages smoothness of inferred instance-level labels based on instance-level similarity, while at the same time respecting group-level label constraints. We apply this approach to the problem of predicting labels for sentences given labels for reviews, using a convolutional neural network to infer sentence similarity. The approach is evaluated using three large review data sets from IMDB, Yelp, and Amazon, and we demonstrate the proposed approach is both accurate and scalable compared to various alternatives.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Glove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071
Efficient Estimation of Word Representations in Vector Space
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1301.3781 · Cited by 26,568
Distributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533 · cited 1×
“More recent work has shown that the semantic relationships of words can be effec-tively captured using the geometry of a continuous embedding space [6, 24, 23, 26].”
BackgroundAdvances in Neural Information Processing Systems 14: Proceedings of the 2001 Conference
(2002) · The MIT Press eBooks · doi:10.7551/mitpress/1120.001.0001 · Cited by 8,890
Learning Word Vectors for Sentiment Analysis
Maas, A. L., Daly, R. E., Pham, P. T., Huang, D., Ng, A. Y., & Potts, C. (2011) · Cited by 6,961
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C. D., Ng, A., & Potts, C. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1170 · Cited by 6,878
Natural Language Processing (almost) from Scratch
Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., & Kuksa, P. P. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1103.0398 · Cited by 4,962
Distributed Representations of Sentences and Documents
Le, Q. V., & Mikolov, T. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1405.4053 · Cited by 4,934
Neural Information Processing Systems
(2018) · The Deep Learning Revolution · doi:10.7551/mitpress/11474.003.0014 · Cited by 3,730
Solving the multiple instance problem with axis-parallel rectangles
Dietterich, T. G., Lathrop, R. H., & Lozano-Pérez, T. (1997) · Artificial Intelligence · doi:10.1016/s0004-3702(96)00034-3 · Cited by 2,866 · cited 2×
“For example, in multi-instance learning (MIL), where groups of instances are referred to as“bags,” a common assumption is that all negatively-labeled bags contain only negative instances and all positively-labeled bags contain at least 1 positive instance [8].”
BackgroundA neural probabilistic language model
BengioYoshua, DucharmeRéjean, VincentPascal, & JanvinChristian (2003) · Journal of Machine Learning Research · doi:10.5555/944919.944966 · Cited by 2,644
Natural language processing: an introduction
Nadkarni, P. M., Ohno-Machado, L., & Chapman, W. W. (2011) · Journal of the American Medical Informatics Association · doi:10.1136/amiajnl-2011-000464 · Cited by 1,975
Hidden factors and hidden topics: understanding rating dimensions with review text
McAuley, J., & Leskovec, J. (2013) · Proceedings of the 7th ACM conference on Recommender systems · doi:10.1145/2507157.2507163 · Cited by 1,564
Support Vector Machines for Multiple-Instance Learning
Andrews, S. J., Tsochantaridis, I., & Hofmann, T. (2002) · neural information processing systems · Cited by 1,401
Uncertainty in Artificial Intelligence
Kanal, L. N., Lemmer, J. F., & Sage, A. P. (1987) · IEEE Transactions on Systems, Man, and Cybernetics · doi:10.1109/tsmc.1987.4309045 · Cited by 938
Learning distributed representations of concepts.
Hinton, G. E. (1989) · eScholarship (California Digital Library) · Cited by 827
Semi-Supervised Classification by Low Density Separation
Chapelle, O., Zien, A., & Ghahramani, R. C. Z. (2005) · Cited by 765
Multiple-Instance Learning for Natural Scene Classification
Maron, O., & Ratan, A. L. (1998) · Cited by 572
Gärtner, T., Flach, P. A., Kowalczyk, A., & Smola, A. J. (2002) · Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft) · Cited by 464
Multi-instance learning by treating instances as non-I.I.D. samples
Zhou, Z.-H., Sun, Y.-Y., & Li, Y.-F. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553534 · Cited by 396
A review of multi-instance learning assumptions
Foulds, J., & Frank, E. (2010) · The Knowledge Engineering Review · doi:10.1017/s026988890999035x · Cited by 387
Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS)
Shrivastava, A., & Li, P. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1405.5869 · Cited by 242
Logistic Regression and Boosting for Labeled Bags of Instances
Xu, X., & Frank, E. (2004) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-24775-3_35 · Cited by 218
Multiple instance learning for sparse positive bags
Bunescu, R. C., & Mooney, R. J. (2007) · Proceedings of the 24th international conference on Machine learning · doi:10.1145/1273496.1273510 · Cited by 184
Estimating Labels from Label Proportions
Quadrianto, N., Smola, A. J., Caetano, T. S., & Le, Q. V. (2009) · doi:10.5555/1577069.1755865 · Cited by 172
A Two-Level Learning Method for Generalized Multi-instance Problems
Weidmann, N. B., Frank, E., & Pfahringer, B. (2003) · Lecture notes in computer science · doi:10.1007/978-3-540-39857-8_42 · Cited by 166
On the relation between multi-instance learning and semi-supervised learning
Zhou, Z., & Xu, J.-M. (2007) · International Conference on Machine Learning · doi:10.1145/1273496.1273643 · Cited by 163
Attacks on privacy and deFinetti's theorem
Kifer, D. (2009) · Proceedings of the 2009 ACM SIGMOD International Conference on Management of data · doi:10.1145/1559845.1559861 · Cited by 162
Extraction of Salient Sentences from Labelled DocumentsPreprint
Denil, M., Demiraj, A., & de Freitas, N. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.6815 · Cited by 138
Self-citationKey Instance Detection in Multi-Instance Learning
Liu, G., Wu, J., & Zhou, Z. (2012) · DR-NTU (Nanyang Technological University) · Cited by 116
A Convex Method for Locating Regions of Interest with Multi-instance Learning
Li, Y., Kwok, J. T.-Y., Tsang, I. W.-H., & Zhou, Z. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-04174-7_2 · Cited by 95
SVM for learning with label proportionsPreprint
Yu, F. X., Liu, D., Kumar, S., et al. (2013) · Cited by 89
Conference on artificial intelligence
(1987) · Computers in Biology and Medicine · doi:10.1016/0010-4825(87)90050-3 · Cited by 88
Explaining the Stars: Weighted Multiple-Instance Learning for Aspect-Based Sentiment Analysis
Pappas, N., & Popescu-Belis, A. (2014) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1052 · Cited by 86
Scalable Multi-instance Learning
Wei, X.-S., Wu, J., & Zhou, Z. (2014) · Proceedings · doi:10.1109/icdm.2014.16 · Cited by 67
Patrini, G., Nock, R., Rivera, P., & Caetano, T. S. (2014) · ANU Open Research (Australian National University) · Cited by 66
Uncertainty in Artificial Intelligence
Bauters, K., Liu, W., Hong, J. S., Carles Sierra, A., & Godo, L. (2014) · Cited by 50
$\propto$SVM for learning with label proportionsPreprint
Yu, F. X., Liu, D., Kumar, S., et al. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1306.0886 · Cited by 36
On classification with bags, groups and sets
Cheplygina, V., Tax, D. M. J., & Loog, M. (2015) · Pattern Recognition Letters · doi:10.1016/j.patrec.2015.03.008 · Cited by 34
A Constrained Semi-supervised Learning Approach to Data Association
Kück, H., Carbonetto, P. S., & de Freitas, N. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-24672-5_1 · Cited by 20
Cited by
Finetuned Language Models Are Zero-Shot Learners
Wei, J., Bosma, M., Zhao, V. Y., Guu, K., Yu, A. W., Lester, B., Du, N., Dai, A. M., & Le, Q. V. (2021) · arXiv · doi:10.48550/arxiv.2109.01652 · Cited by 1,101
Multiple instance learning: A survey of problem characteristics and applications
Carbonneau, M.-A., Cheplygina, V., Granger, E., & Gagnon, G. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2017.10.009 · Cited by 740
“In [40, 125, 129, 130], MIL was used to infer the sentiment expressed in individual sentences based on the labels provided for entire user reviews.”
MethodThe Natural Language Decathlon: Multitask Learning as Question Answering
McCann, B., Keskar, N. S., Xiong, C., & Socher, R. (2018) · arXiv · doi:10.48550/arxiv.1806.08730 · Cited by 448
Semantically Equivalent Adversarial Rules for Debugging NLP models
Ribeiro, M. T., Singh, S., & Guestrin, C. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1079 · Cited by 432
Comparing automated text classification methods
Hartmann, J., Huppertz, J., Schamp, C., & Heitmann, M. (2019) · International Journal of Research in Marketing · doi:10.1016/j.ijresmar.2018.09.009 · Cited by 399
Metadata
- Authors
- Kotzias, D., Denil, M., de Freitas, N., & Smyth, P.
- Venue
- Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
- Publisher
- ACM
- Published
- 2015-08-10
- Pages
- 597-606
- OpenAlex
- W2067624665
- Cited by
- 312
- References
- 40
- FWCI
- 18.94
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.