The DOI matches its Crossref record; 33 of the 35 references it cites were found in a registry or an index.
Rationale-Augmented Convolutional Neural Networks for Text Classification
Open accessAbstract
We present a new Convolutional Neural Network (CNN) model for text classification that jointly exploits labels on documents and their constituent sentences.Specifically, we consider scenarios in which annotators explicitly mark sentences (or snippets) that support their overall document categorization, i.e., they provide rationales.Our model exploits such supervision via a hierarchical approach in which each document is represented by a linear combination of the vector representations of its component sentences.We propose a sentence-level convolutional model that estimates the probability that a given sentence is a rationale, and we then scale the contribution of each sentence to the aggregate document representation in proportion to these estimates.Experiments on five classification datasets that have document labels and associated rationales demonstrate that our approach consistently outperforms strong baselines.Moreover, our model naturally provides explanations for its predictions.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In this prior work, we predicted whether studies’ results might be at risk of bias using the first version of the Cochrane Risk of Bias tool”
From Trialstreamer: A living, automatically updated database of clinical trial reports (2020) · cites this paper as [15]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Data extraction systems have been created that can automatically retrieve unstructured information on the trial PICO elements,10–12 and risk of bias.13–16”
From Trialstreamer: A living, automatically updated database of clinical trial reports (2020) · cites this paper as [15]
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
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
The Cochrane Collaboration's tool for assessing risk of bias in randomised trials
Higgins, J. P. T., Altman, D. G., Gotzsche, P. C., Juni, P., Moher, D., Oxman, A. D., Savovic, J., Schulz, K. F., Weeks, L., Sterne, J. A. C., et al. (2011) · BMJ · doi:10.1136/bmj.d5928 · Cited by 33,817
(2014) · Cited by 33,419
Dermyshi, E., Wang, Y., Yan, C., Hong, W., Qiu, G., Gong, X., & Zhang, T. (2017) · Neonatology · doi:10.1159/000454668 · Cited by 24,586
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213
Convolutional Neural Networks for Sentence Classification
Kim, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1181 · Cited by 14,831
Text categorization with Support Vector Machines: Learning with many relevant features
Joachims, T. (1998) · Lecture notes in computer science · doi:10.1007/bfb0026683 · Cited by 8,271
Distributed Representations of Sentences and DocumentsPreprint
Le, Q. V., & Mikolov, T. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1405.4053 · Cited by 7,905
ADADELTA: An Adaptive Learning Rate Method
Zeiler, M. D. (2012) · arXiv · doi:10.48550/arxiv.1212.5701 · Cited by 5,322
A unified architecture for natural language processing: deep neural networks with multitask learning
Collobert, R., & Weston, J. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390177 · Cited by 5,058
Hierarchical Attention Networks for Document Classification
Yang, Z., Yang, D., Dyer, C., He, X., Smola, A. J., & Hovy, E. H. (2016) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n16-1174 · Cited by 5,022
Pang, B., & Lee, L. (2004) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.3115/1218955.1218990 · Cited by 3,376
Document Modeling with Gated Recurrent Neural Network for Sentiment Classification
Tang, D., Qin, B., & Liu, T. (2015) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d15-1167 · Cited by 1,563
An Empirical Exploration of Recurrent Network Architectures
Józefowicz, R., Zaremba, W., & Sutskever, I. (2015) · Cited by 1,459
Zhang, Y., & Wallace, B. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1510.03820 · Cited by 1,336
Self-citationA Primer on Neural Network Models for Natural Language Processing
Goldberg, Y. (2016) · Journal of Artificial Intelligence Research · doi:10.1613/jair.4992 · Cited by 1,316
Effective Use of Word Order for Text Categorization with Convolutional Neural Networks
Johnson, R., & Zhang, T. (2015) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.3115/v1/n15-1011 · Cited by 967
A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum CutsPreprint
Pang, B., & Lee, L. (2004) · arXiv (Cornell University) · doi:10.48550/arxiv.cs/0409058 · Cited by 789
Distributional Semantics Resources for Biomedical Text Processing
Pyysalo, S., Ginter, F., Moen, H., Salakoski, T., & Ananiadou, S. (2013) · Research Explorer (The University of Manchester) · Cited by 429
Semi-supervised Convolutional Neural Networks for Text Categorization via Region Embedding
Johnson, R., & Zhang, T. (2015) · PubMed · doi:10.48550/arxiv.1504.01255 · Cited by 334
RobotReviewer: evaluation of a system for automatically assessing bias in clinical trials
Marshall, I. J., Kuiper, J., & Wallace, B. C. (2016) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocv044 · Cited by 317
Self-citationLearning from labeled features using generalized expectation criteria
Druck, G., Mann, G., & McCallum, A. (2008) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/1390334.1390436 · Cited by 254
Using “annotator rationales” to improve machine learning for text categorization
Zaidan, O. F., Eisner, J. M., & Piatko, C. (2007) · Cited by 252
Generalized Expectation Criteria for Semi-Supervised Learning with Weakly Labeled Data
Mann, G., & McCallum, A. (2010) · ScholarWorks@UMassAmherst (University of Massachusetts Amherst) · doi:10.5555/1756006.1756038 · Cited by 175
Settles, B. (2011) · Cited by 167
MGNC-CNN: A Simple Approach to Exploiting Multiple Word Embeddings for Sentence Classification
Zhang, Y., Roller, S., & Wallace, B. (2016) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n16-1178 · Cited by 116
Self-citationZaidan, O. F., & Eisner, J. M. (2008) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/1613715.1613721 · Cited by 100
Why Is That Relevant? Collecting Annotator Rationales for Relevance Judgments
McDonnell, T., Lease, M., Kutlu, M., & Elsayed, T. (2016) · Proceedings of the AAAI Conference on Human Computation and Crowdsourcing · doi:10.1609/hcomp.v4i1.13287 · Cited by 86
Automatically Generating Annotator Rationales to Improve Sentiment Classification
Yessenalina, A., Choi, Y., & Cardie, C. (2010) · Cited by 65
Automating Risk of Bias Assessment for Clinical Trials
Marshall, I. J., Kuiper, J., & Wallace, B. C. (2015) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2015.2431314 · Cited by 59
Self-citationThe Constrained Weight Space SVM: Learning with Ranked Features
Small, K., Wallace, B., Trikalinos, T. A., & Brodley, C. E. (2011) · Cited by 38
Self-citationJapanese probabilistic information retrieval using location and category information
Murata, M., Ma, Q., Uchimoto, K., Ozaku, H., Utiyama, M., & Isahara, H. (2000) · International Workshop on Information Retrieval with Asian Languages (IRAL) · doi:10.1145/355214.355226 · Cited by 30
Automatic text categorization using the importance of sentences
Ko, Y., Park, J., & Seo, J. (2002) · International Conference on Computational Linguistics · doi:10.3115/1072228.1072331 · Cited by 29
Cited by
Sorted by citations
Jain, S., & Wallace, B. (2019) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n19-1357 · Cited by 1,133
Self-citationMarshall, I. J., & Wallace, B. C. (2019) · Systematic Reviews · doi:10.1186/s13643-019-1074-9 · Cited by 638
“Many state-of-the-art systems use more complex models than logistic regression (and in particular more sophisticated methods for representing documents [13], obtaining coefficients [14], or both [15]).”
BackgroundResultSelf-citationAttention in Natural Language Processing
Galassi, A., Lippi, M., & Torroni, P. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3019893 · Cited by 726
ERASER: A Benchmark to Evaluate Rationalized NLP Models
DeYoung, J., Jain, S., Rajani, N. F., Lehman, E., Xiong, C., Socher, R., & Wallace, B. C. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.408 · Cited by 561
Self-citationRight for the Right Reasons: Training Differentiable Models by Constraining their Explanations
Ross, A. S., Hughes, M. C., & Doshi-Velez, F. (2017) · Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/371 · Cited by 515
Metadata
- Authors
- Zhang, Y., Marshall, I., & Wallace, B. C.
- Affiliations
- The University of Texas at Austin (US)
- King's College London (GB)
- Northeastern University (US)
- Venue
- Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
- Published
- 2016
- Volume
- 2016
- Pages
- 795-804
- PMC
- PMC5300751
- OpenAlex
- W2963082289
- Cited by
- 249
- References
- 35
- Citations by year
- 2026: 3 · 2025: 6 · 2024: 18 · 2023: 25 · 2022: 40 · 2021: 46 · 2020: 33 · 2019: 37 · 2018: 22 · 2017: 15 · 2016: 4
- FWCI
- 14.01
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- University of Texas at Austin
- National Institutes of Health (5r01lm012086-08)
- Medical Research Council (MR/N015185/1)
- U.S. National Library of Medicine (R01-LM012086)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Text and Document Classification Technologies
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- text classification, rationales, explainable classification
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
