To highlight the challenges of achieving representation disentanglement for text domain in an unsupervised setting, in this paper we select a representative set of successfully applied models from the image domain. We evaluate these models on 6 disentanglement metrics, as well as on downstream classification tasks and homotopy. To facilitate the evaluation, we propose two synthetic datasets with known generative factors. Our experiments highlight the existing gap in the text domain and illustrate that certain elements such as representation sparsity (as an inductive bias), or representation coupling with the decoder could impact disentanglement. To the best of our knowledge, our work is the first attempt on the intersection of unsupervised representation disentanglement and text, and provides the experimental framework and datasets for examining future developments in this direction.
@inproceedings{zhang-etal-2021-unsupervised-representation, title = "Unsupervised Representation Disentanglement of Text: An Evaluation on Synthetic Datasets", author = "Zhang, Lan and Prokhorov, Victor and Shareghi, Ehsan", editor = "Rogers, Anna and Calixto, Iacer and Vuli{\'c}, Ivan and Saphra, Naomi and Kassner, Nora and Camburu, Oana-Maria and Bansal, Trapit and Shwartz, Vered", booktitle = "Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)", month = aug, year = "2021", address = "Online", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2021.repl4nlp-1.14/", doi = "10.18653/v1/2021.repl4nlp-1.14", pages = "128--140", abstract = "To highlight the challenges of achieving representation disentanglement for text domain in an unsupervised setting, in this paper we select a representative set of successfully applied models from the image domain. We evaluate these models on 6 disentanglement metrics, as well as on downstream classification tasks and homotopy. To facilitate the evaluation, we propose two synthetic datasets with known generative factors. Our experiments highlight the existing gap in the text domain and illustrate that certain elements such as representation sparsity (as an inductive bias), or representation coupling with the decoder could impact disentanglement. To the best of our knowledge, our work is the first attempt on the intersection of unsupervised representation disentanglement and text, and provides the experimental framework and datasets for examining future developments in this direction."}
<?xml version="1.0" encoding="UTF-8"?><modsCollection xmlns="http://www.loc.gov/mods/v3"><mods ID="zhang-etal-2021-unsupervised-representation"> <titleInfo> <title>Unsupervised Representation Disentanglement of Text: An Evaluation on Synthetic Datasets</title> </titleInfo> <name type="personal"> <namePart type="given">Lan</namePart> <namePart type="family">Zhang</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Victor</namePart> <namePart type="family">Prokhorov</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Ehsan</namePart> <namePart type="family">Shareghi</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <originInfo> <dateIssued>2021-08</dateIssued> </originInfo> <typeOfResource>text</typeOfResource> <relatedItem type="host"> <titleInfo> <title>Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)</title> </titleInfo> <name type="personal"> <namePart type="given">Anna</namePart> <namePart type="family">Rogers</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Iacer</namePart> <namePart type="family">Calixto</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Ivan</namePart> <namePart type="family">Vulić</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Naomi</namePart> <namePart type="family">Saphra</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Nora</namePart> <namePart type="family">Kassner</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Oana-Maria</namePart> <namePart type="family">Camburu</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Trapit</namePart> <namePart type="family">Bansal</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Vered</namePart> <namePart type="family">Shwartz</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <originInfo> <publisher>Association for Computational Linguistics</publisher> <place> <placeTerm type="text">Online</placeTerm> </place> </originInfo> <genre authority="marcgt">conference publication</genre> </relatedItem> <abstract>To highlight the challenges of achieving representation disentanglement for text domain in an unsupervised setting, in this paper we select a representative set of successfully applied models from the image domain. We evaluate these models on 6 disentanglement metrics, as well as on downstream classification tasks and homotopy. To facilitate the evaluation, we propose two synthetic datasets with known generative factors. Our experiments highlight the existing gap in the text domain and illustrate that certain elements such as representation sparsity (as an inductive bias), or representation coupling with the decoder could impact disentanglement. To the best of our knowledge, our work is the first attempt on the intersection of unsupervised representation disentanglement and text, and provides the experimental framework and datasets for examining future developments in this direction.</abstract> <identifier type="citekey">zhang-etal-2021-unsupervised-representation</identifier> <identifier type="doi">10.18653/v1/2021.repl4nlp-1.14</identifier> <location> <url>https://aclanthology.org/2021.repl4nlp-1.14/</url> </location> <part> <date>2021-08</date> <extent unit="page"> <start>128</start> <end>140</end> </extent> </part></mods></modsCollection>
%0 Conference Proceedings%T Unsupervised Representation Disentanglement of Text: An Evaluation on Synthetic Datasets%A Zhang, Lan%A Prokhorov, Victor%A Shareghi, Ehsan%Y Rogers, Anna%Y Calixto, Iacer%Y Vulić, Ivan%Y Saphra, Naomi%Y Kassner, Nora%Y Camburu, Oana-Maria%Y Bansal, Trapit%Y Shwartz, Vered%S Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)%D 2021%8 August%I Association for Computational Linguistics%C Online%F zhang-etal-2021-unsupervised-representation%X To highlight the challenges of achieving representation disentanglement for text domain in an unsupervised setting, in this paper we select a representative set of successfully applied models from the image domain. We evaluate these models on 6 disentanglement metrics, as well as on downstream classification tasks and homotopy. To facilitate the evaluation, we propose two synthetic datasets with known generative factors. Our experiments highlight the existing gap in the text domain and illustrate that certain elements such as representation sparsity (as an inductive bias), or representation coupling with the decoder could impact disentanglement. To the best of our knowledge, our work is the first attempt on the intersection of unsupervised representation disentanglement and text, and provides the experimental framework and datasets for examining future developments in this direction.%R 10.18653/v1/2021.repl4nlp-1.14%U https://aclanthology.org/2021.repl4nlp-1.14/%U https://doi.org/10.18653/v1/2021.repl4nlp-1.14%P 128-140
[Unsupervised Representation Disentanglement of Text: An Evaluation on Synthetic Datasets](https://aclanthology.org/2021.repl4nlp-1.14/) (Zhang et al., RepL4NLP 2021)