Noriko Tomuro


2024

pdf bib
Enhanced Coherence-Aware Network with Hierarchical Disentanglement for Aspect-Category Sentiment Analysis
Jin Cui | Fumiyo Fukumoto | Xinfeng Wang | Yoshimi Suzuki | Jiyi Li | Noriko Tomuro | Wanzeng Kong
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Aspect-category-based sentiment analysis (ACSA), which aims to identify aspect categories and predict their sentiments has been intensively studied due to its wide range of NLP applications. Most approaches mainly utilize intrasentential features. However, a review often includes multiple different aspect categories, and some of them do not explicitly appear in the review. Even in a sentence, there is more than one aspect category with its sentiments, and they are entangled intra-sentence, which makes the model fail to discriminately preserve all sentiment characteristics. In this paper, we propose an enhanced coherence-aware network with hierarchical disentanglement (ECAN) for ACSA tasks. Specifically, we explore coherence modeling to capture the contexts across the whole review and to help the implicit aspect and sentiment identification. To address the issue of multiple aspect categories and sentiment entanglement, we propose a hierarchical disentanglement module to extract distinct categories and sentiment features. Extensive experimental and visualization results show that our ECAN effectively decouples multiple categories and sentiments entangled in the coherence representations and achieves state-of-the-art (SOTA) performance. Our codes and data are available online: https://github.com/cuijin-23/ECAN.

2021

pdf bib
Relation Classification with Cognitive Attention Supervision
Erik McGuire | Noriko Tomuro
Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics

Many current language models such as BERT utilize attention mechanisms to transform sequence representations. We ask whether we can influence BERT’s attention with human reading patterns by using eye-tracking and brain imaging data. We fine-tune BERT for relation extraction with auxiliary attention supervision in which BERT’s attention weights are supervised by cognitive data. Through a variety of metrics we find that this attention supervision can be used to increase similarity between model attention distributions over sequences and the cognitive data without significantly affecting classification performance while making unique errors from the baseline. In particular, models with cognitive attention supervision more often correctly classified samples misclassified by the baseline.

2014

pdf bib
Combining Visual and Textual Features for Information Extraction from Online Flyers
Emilia Apostolova | Noriko Tomuro
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

2012

pdf bib
Domain Adaptation of Coreference Resolution for Radiology Reports
Emilia Apostolova | Noriko Tomuro | Pattanasak Mongkolwat | Dina Demner-Fushman
BioNLP: Proceedings of the 2012 Workshop on Biomedical Natural Language Processing

2011

pdf bib
Automatic Extraction of Lexico-Syntactic Patterns for Detection of Negation and Speculation Scopes
Emilia Apostolova | Noriko Tomuro | Dina Demner-Fushman
Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies

2010

pdf bib
Exploring Surface-Level Heuristics for Negation and Speculation Discovery in Clinical Texts
Emilia Apostolova | Noriko Tomuro
Proceedings of the 2010 Workshop on Biomedical Natural Language Processing

pdf bib
Djangology: A Light-weight Web-based Tool for Distributed Collaborative Text Annotation
Emilia Apostolova | Sean Neilan | Gary An | Noriko Tomuro | Steven Lytinen
Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)

Manual text annotation is a resource-consuming endeavor necessary for NLP systems when they target new tasks or domains for which there are no existing annotated corpora. Distributing the annotation work across multiple contributors is a natural solution to reduce and manage the effort required. Although there are a few publicly available tools which support distributed collaborative text annotation, most of them have complex user interfaces and require a significant amount of involvement from the annotators/contributors as well as the project developers and administrators. We present a light-weight web application for highly distributed annotation projects - Djangology. The application takes advantage of the recent advances in web framework architecture that allow rapid development and deployment of web applications thus minimizing development time for customization. The application's web-based interface gives project administrators the ability to easily upload data, define project schemas, assign annotators, monitor progress, and review inter-annotator agreement statistics. The intuitive web-based user interface encourages annotator participation as contributors are not burdened by tool manuals, local installation, or configuration. The system has achieved a user response rate of 70% in two annotation projects involving more than 250 medical experts from various geographic locations.

2009

pdf bib
Construction of Disambiguated Folksonomy Ontologies Using Wikipedia
Noriko Tomuro | Andriy Shepitsen
Proceedings of the 2009 Workshop on The People’s Web Meets NLP: Collaboratively Constructed Semantic Resources (People’s Web)

2008

pdf bib
The “Close-Distant” Relation of Adjectival Concepts Based on Self-Organizing Map
Kyoko Kanzaki | Noriko Tomuro | Hitoshi Isahara
Coling 2008: Proceedings of the Workshop on Cognitive Aspects of the Lexicon (COGALEX 2008)

pdf bib
Extraction of Attribute Concepts from Japanese Adjectives
Kyoko Kanzaki | Francis Bond | Noriko Tomuro | Hitoshi Isahara
Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08)

We describe various syntactic and semantic conditions for finding abstractnouns which refer to concepts of adjectives from a text, in an attempt to explore the creation of a thesaurus from text. Depending on usages, six kinds of syntactic patterns are shown. In the syntactic and semantic conditions an omission of an abstract noun is mainly used, but in addition, various linguistic clues are needed. We then compare our results with synsets of Japanese WordNet. From a viewpoint of Japanese WordNet, the degree of agreement of ?Attribute? between our data and Japanese WordNet was 22%. On the other hand, the total number of differences of obtained abstract nouns was 267. From a viewpoint of our data,the degree of agreement of abstract nouns between our data and Japanese WordNet was 54%.

2003

pdf bib
Interrogative Reformulation Patterns and Acquisition of Question Paraphrases
Noriko Tomuro
Proceedings of the Second International Workshop on Paraphrasing

2002

pdf bib
Question Terminology and Representation for Question Type Classification
Noriko Tomuro
COLING-02: COMPUTERM 2002: Second International Workshop on Computational Terminology

2001

pdf bib
Tree-Cut and a Lexicon Based on Systematic Polysemy
Noriko Tomuro
Second Meeting of the North American Chapter of the Association for Computational Linguistics

pdf bib
Nonminimal Derivations in Unification-Based Parsing
Noriko Tomuro | Steven L. Lytinen
Computational Linguistics, Volume 27, Number 2, June 2001

2000

pdf bib
Automatic Extraction of Systematic Polysemy Using Tree-cut
Noriko Tomuro
NAACL-ANLP 2000 Workshop: Syntactic and Semantic Complexity in Natural Language Processing Systems

1998

pdf bib
Semi-automatic Induction of Systematic Polysemy from WordNet
Noriko Tomuro
Usage of WordNet in Natural Language Processing Systems

1996

pdf bib
Maximizing Top-down Constraints for Unification-based Systems
Noriko Tomuro
34th Annual Meeting of the Association for Computational Linguistics