Learning Document-Level Semantic Properties from Free-Text Annotations
This paper presents a new method for inferring the semantic properties of documents by leveraging free-text keyphrase annotations. Such annotations are becoming increasingly abundant due to the recent dramatic growth in semi-structured, user-generated online content. One especially relevant domain i...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
AI Access Foundation
2011
|
| Online Access: | http://hdl.handle.net/1721.1/64415 https://orcid.org/0000-0002-2921-8201 |
| _version_ | 1826210586729381888 |
|---|---|
| author | Branavan, Satchuthanan R. Chen, Harr Eisenstein, Jacob Barzilay, Regina |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Branavan, Satchuthanan R. Chen, Harr Eisenstein, Jacob Barzilay, Regina |
| author_sort | Branavan, Satchuthanan R. |
| collection | MIT |
| description | This paper presents a new method for inferring the semantic properties of documents by leveraging free-text keyphrase annotations. Such annotations are becoming increasingly abundant due to the recent dramatic growth in semi-structured, user-generated online content. One especially relevant domain is product reviews, which are often annotated by their authors with pros/cons keyphrases such as ``a real bargain'' or ``good value.'' These annotations are representative of the underlying semantic properties; however, unlike expert annotations, they are noisy: lay authors may use different labels to denote the same property, and some labels may be missing. To learn using such noisy annotations, we find a hidden paraphrase structure which clusters the keyphrases. The paraphrase structure is linked with a latent topic model of the review texts, enabling the system to predict the properties of unannotated documents and to effectively aggregate the semantic properties of multiple reviews. Our approach is implemented as a hierarchical Bayesian model with joint inference. We find that joint inference increases the robustness of the keyphrase clustering and encourages the latent topics to correlate with semantically meaningful properties. Multiple evaluations demonstrate that our model substantially outperforms alternative approaches for summarizing single and multiple documents into a set of semantically salient keyphrases. |
| first_indexed | 2024-09-23T14:52:20Z |
| format | Article |
| id | mit-1721.1/64415 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T14:52:20Z |
| publishDate | 2011 |
| publisher | AI Access Foundation |
| record_format | dspace |
| spelling | mit-1721.1/644152022-09-29T11:06:24Z Learning Document-Level Semantic Properties from Free-Text Annotations Branavan, Satchuthanan R. Chen, Harr Eisenstein, Jacob Barzilay, Regina Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Barzilay, Regina Branavan, Satchuthanan R. Chen, Harr Eisenstein, Jacob Barzilay, Regina This paper presents a new method for inferring the semantic properties of documents by leveraging free-text keyphrase annotations. Such annotations are becoming increasingly abundant due to the recent dramatic growth in semi-structured, user-generated online content. One especially relevant domain is product reviews, which are often annotated by their authors with pros/cons keyphrases such as ``a real bargain'' or ``good value.'' These annotations are representative of the underlying semantic properties; however, unlike expert annotations, they are noisy: lay authors may use different labels to denote the same property, and some labels may be missing. To learn using such noisy annotations, we find a hidden paraphrase structure which clusters the keyphrases. The paraphrase structure is linked with a latent topic model of the review texts, enabling the system to predict the properties of unannotated documents and to effectively aggregate the semantic properties of multiple reviews. Our approach is implemented as a hierarchical Bayesian model with joint inference. We find that joint inference increases the robustness of the keyphrase clustering and encourages the latent topics to correlate with semantically meaningful properties. Multiple evaluations demonstrate that our model substantially outperforms alternative approaches for summarizing single and multiple documents into a set of semantically salient keyphrases. 2011-06-13T15:46:45Z 2011-06-13T15:46:45Z 2009-04 2008-07 Article http://purl.org/eprint/type/JournalArticle 1076-9757 1943-5037 http://hdl.handle.net/1721.1/64415 Branavan, S. R. K., Harr Chen, Jacob Eisenstein and Regina Barzilay (2009) "Learning Document-Level Semantic Properties from Free-Text Annotations", Journal of Artificial Intelligence Research, 34, 2009 pages 569-603. ©2009 AI Access Foundation. https://orcid.org/0000-0002-2921-8201 en_US http://www.jair.org/media/2633/live-2633-4380-jair.pdf Journal of Artificial Intelligence Research Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf AI Access Foundation JAIR |
| spellingShingle | Branavan, Satchuthanan R. Chen, Harr Eisenstein, Jacob Barzilay, Regina Learning Document-Level Semantic Properties from Free-Text Annotations |
| title | Learning Document-Level Semantic Properties from Free-Text Annotations |
| title_full | Learning Document-Level Semantic Properties from Free-Text Annotations |
| title_fullStr | Learning Document-Level Semantic Properties from Free-Text Annotations |
| title_full_unstemmed | Learning Document-Level Semantic Properties from Free-Text Annotations |
| title_short | Learning Document-Level Semantic Properties from Free-Text Annotations |
| title_sort | learning document level semantic properties from free text annotations |
| url | http://hdl.handle.net/1721.1/64415 https://orcid.org/0000-0002-2921-8201 |
| work_keys_str_mv | AT branavansatchuthananr learningdocumentlevelsemanticpropertiesfromfreetextannotations AT chenharr learningdocumentlevelsemanticpropertiesfromfreetextannotations AT eisensteinjacob learningdocumentlevelsemanticpropertiesfromfreetextannotations AT barzilayregina learningdocumentlevelsemanticpropertiesfromfreetextannotations |