Filters








5,785 Hits in 8.4 sec

The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models [article]

Ian Tenney, James Wexler, Jasmijn Bastings, Tolga Bolukbasi, Andy Coenen, Sebastian Gehrmann, Ellen Jiang, Mahima Pushkarna, Carey Radebaugh, Emily Reif, Ann Yuan
2020 arXiv   pre-print
We present the Language Interpretability Tool (LIT), an open-source platform for visualization and understanding of NLP models.  ...  LIT supports a wide range of models--including classification, seq2seq, and structured prediction--and is highly extensible through a declarative, framework-agnostic API.  ...  With this in mind, we introduce the Language Interpretability Tool (LIT), a toolkit and browserbased user interface (UI) for NLP model understanding.  ... 
arXiv:2008.05122v1 fatcat:3psi3vbxafhjvcpwph3jqkgsmm

The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models

Ian Tenney, James Wexler, Jasmijn Bastings, Tolga Bolukbasi, Andy Coenen, Sebastian Gehrmann, Ellen Jiang, Mahima Pushkarna, Carey Radebaugh, Emily Reif, Ann Yuan
2020 Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations   unpublished
We present the Language Interpretability Tool (LIT), an open-source platform for visualization and understanding of NLP models.  ...  LIT supports a wide range of models-including classification, seq2seq, and structured predictionand is highly extensible through a declarative, framework-agnostic API.  ...  We also thank our anonymous reviewers for their helpful feedback, and Pere Lluis, Luke Gessler, and Kevin Robinson for their contributions to the open-source code.  ... 
doi:10.18653/v1/2020.emnlp-demos.15 fatcat:iqpoecsvyraenlko5ef5hm5mve

Storyteller: Visual Analytics of Perspectives on Rich Text Interpretations

Maarten van Meersbergen, Piek Vossen, Janneke van der Zwaan, Antske Fokkens, Willem van Hage, Inger Leemans, Isa Maks
2017 Proceedings of the 2017 EMNLP Workshop: Natural Language Processing meets Journalism  
We show that we can abstract from different data models for events and emotions to a single data model that can show the complex relations in four dimensions.  ...  The visualization has been applied to analyze 1) dynamic developments in how people both conceive and express emotions in theater plays and 2) how stories are told from the perspective of their sources  ...  Acknowledgment The authors would like to thank the Netherlands Organisation for Scientific Research (NWO) and the Netherlands eScience Center for sponsoring this research.  ... 
doi:10.18653/v1/w17-4207 dblp:conf/emnlp/MeersbergenVZFH17 fatcat:bwshnpzzivgctejciulz26regm

Text-to-picture tools, systems, and approaches: a survey

Jezia Zakraoui, Moutaz Saleh, Jihad Al Ja'am
2019 Multimedia tools and applications  
These systems interpret a natural language text and transform it into a visual format as pictures or images that are either static or dynamic.  ...  For instance, the authors in [58] built the SPRINT system that generates 3D geometric models from natural language descriptions of a scene using spatial constraints extracted from the text.  ...  , and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.  ... 
doi:10.1007/s11042-019-7541-4 fatcat:7n7gix2qdfgo7jllick5mb6via

Semantic Web Tools and Decision-Making [chapter]

Francisco Antunes, Manuela Freire, João Paulo Costa
2014 Lecture Notes in Business Information Processing  
In this paper the general objectives of the semantic web tools are reviewed and characterized, as well as the categories of decision support tools, in order to establish an intersection of utility and  ...  We also elaborate on actual and foreseen possibilities for a deeper integration, considering the actual implementation, opportunities and constraints in the decision-making context.  ...  analysis; (6) Models and model evolution; and (7) Sharing decisions.  ... 
doi:10.1007/978-3-319-07179-4_31 fatcat:fkgidorpdnedvp6ztslcqvyhf4

Visual Tools for Natural Language Processing

R. GAIZAUSKAS, P.J. RODGERS, K. HUMPHREYS
2001 Journal of Visual Languages and Computing  
We describe GATE, the General Architecture for Text Engineering, an integrated visual development environment to support the visual assembly, execution and analysis of modular natural language processing  ...  The underlying model we have adopted for a visual NLP system is that of data flow program graphs [11] .  ...  They would also like to thank Shaaron Ainsworth, Hamish Cunningham, and Yorick Wilks for comments on drafts of this paper.  ... 
doi:10.1006/jvlc.2000.0203 fatcat:ltizwiyzavdlboakwioxtx4twq

An Interactive Tool for Natural Language Processing on Clinical Text [article]

Gaurav Trivedi, Phuong Pham, Wendy Chapman, Rebecca Hwa, Janyce Wiebe, Harry Hochheiser
2017 arXiv   pre-print
Our tool combines multiple visualizations to help the users understand these results and make any necessary corrections, thus forming a feedback loop and helping improve the accuracy of the NLP models.  ...  We present a prototype tool that allows end users to visualize and review the outputs of an NLP system that extracts binary variables from clinical text.  ...  Ateev Mehrotra for providing the colonoscopy reports dataset. This research was supported by NIH grant 5R01LM010964.  ... 
arXiv:1707.01890v2 fatcat:hjcakwhenfexhdmnrrpg3hetoy

Tools Exhibits [chapter]

Alberto Rodrigues da Silva
2005 Lecture Notes in Computer Science  
UML diagrams accessible for visually impaired programmers", by FNB; (3) "TAU Gen-eration2", by Telelogic; (4) "IBM Rational Rose XDE Products", by Sinfic; and (5) "BridgePoint Development Suite", by Mentor  ...  The tool exhibits session provided an excellent opportunity where participants analysed and viewed relevant UML and MDA related tools in action and discussed these systems with their creators or distributors  ...  One of these tools is the Unified Modelling Language, a language used for modeling across many fields.  ... 
doi:10.1007/978-3-540-31797-5_34 fatcat:i5y34xfiqfertjnmigtfmk4ehm

Different valuable tools for Arabic sentiment analysis: a comparative evaluation

Youssra Zahidi, Yacine El Younoussi, Yassine Al-Amrani
2021 International Journal of Power Electronics and Drive Systems (IJPEDS)  
Arabic Natural language processing (ANLP) is a subfield of artificial intelligence (AI) that tries to build various applications in the Arabic language like Arabic sentiment analysis (ASA) that is the  ...  operation of classifying the feelings and emotions expressed for defining the attitude of the writer (neutral, negative or positive).  ...  The Weka workbench includes a group of algorithms and visualization tools for predictive modeling and data analysis, with graphical user interfaces for easy access to this functionality.  ... 
doi:10.11591/ijece.v11i1.pp753-762 fatcat:65nttve3snd7hdeeud7fu4igje

Survey on Publicly Available Sinhala Natural Language Processing Tools and Research [article]

Nisansa de Silva
2022 arXiv   pre-print
A number of research groups from Sri Lanka have noticed this dearth and the resultant dire need for proper tools and research for Sinhala natural language processing.  ...  However, due to poverty in both linguistic and economic capital, Sinhala, in the perspective of Natural Language Processing tools and research, remains a resource-poor language which has neither the economic  ...  ACKNOWLEDGMENTS The authors would like to thank Romain Egele for checking the examples we have provided in French for their accuracy.  ... 
arXiv:1906.02358v12 fatcat:3bvyvces4zhzzhnvjgaqqacbzy

Managing Second Language Acquisition Data with Natural Language Processing Tools [chapter]

2022 The Open Handbook of Linguistic Data Management  
This interaction is visualized in figure 34 .1. This model reported a marginal R 2 of .281 and a conditional R 2 of .393.  ...  We follow this with a discussion of the analysis and a guide to interpreting NLP results (section 4).  ...  In many cases, the NLP tools in SALAT contain component scores developed using statistical analysis that convert related indices into linearly uncorrelated, aggregated variables.  ... 
doi:10.7551/mitpress/12200.003.0039 fatcat:267wduqjbzfrrcwnnojj27cmqu

Market research for requirements analysis using linguistic tools

Mich Luisa, Franch Mariangela, Novi Inverardi Pierluigi
2004 Requirements Engineering  
in natural language, and (b) to verify the existence of potential demand for such a tool.  ...  To determine the potential demand for such tool, some of the survey questions dealt with the adoption of development methodologies and consequently with models and support tools; other questions referred  ...  will there be a significant growth in the market for CASE tools, repackaged and renamed as object modelling tools or visual modelling tools.  ... 
doi:10.1007/s00766-003-0179-8 fatcat:qa5rsowmsbdgfa6kapfh7il7ve

Interpretable Neural Architectures for Attributing an Ad's Performance to its Writing Style

Reid Pryzant, Sugato Basu, Kazoo Sone
2018 Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP  
The other method leverages residualization to control for confounds and performs interpretation by aggregating over learned word vectors.  ...  One method uses a CNN to encode the text, an adversarial objective function to control for confounders, and projects its weights onto its activations to interpret the importance of each phrase towards  ...  Indeed, it is essential for developing transparent and interpretable machine learning NLP models (Yamamoto, 2012) .  ... 
doi:10.18653/v1/w18-5415 dblp:conf/emnlp/PryzantBS18 fatcat:hq2uiudcrfbn5le4sudhfwagxi

Tools for monitoring, visualizing, and refining collections of noisy documents

Daniel Lopresti, George Nagy
2009 Proceedings of The Third Workshop on Analytics for Noisy Unstructured Text Data - AND '09  
In this paper, we describe tools we are building to help the user view and understand the results of common document analysis procedures.  ...  Developing better systems for document image analysis requires understanding errors, their sources, and their effects.  ...  Beyond the sort of mark-up functionality provided in standard ground-truthing tools for document image analysis, support must also be included for text tagging since this is required by NLP tools for sentence  ... 
doi:10.1145/1568296.1568301 dblp:conf/and/LoprestiN09 fatcat:mcsqebspqrdf3m57bytpout3ya

exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformers Models [article]

Benjamin Hoover, Hendrik Strobelt, Sebastian Gehrmann
2019 arXiv   pre-print
While static analyses of these models lead to targeted insights, interactive tools are more dynamic and can help humans better gain an intuition for the model-internal reasoning process.  ...  We present exBERT, an interactive tool named after the popular BERT language model, that provides insights into the meaning of the contextual representations by matching a human-specified input to similar  ...  Toward that end, visualization tools can offer concise summaries of useful information and allow interaction with large models.  ... 
arXiv:1910.05276v1 fatcat:gxm5w2lj5ncbdbeav37doj4a7q
« Previous Showing results 1 — 15 out of 5,785 results