The paper describes an experimental system for generating 3D-printable models inspired by arbitra... more The paper describes an experimental system for generating 3D-printable models inspired by arbitrary textual input. Utilizing a transliteration pipeline, the system pivots on Natural Language Understanding technologies and 3D data available via online repositories to result in a bag of retrieved 3D models that are then concatenated in order to produce original designs. Such artefacts celebrate a post-digital kind of objecthood, as they are concretely physical while, at the same time, incorporate the cybernetic encodings of their own making. Twelve individuals were asked to reflect on some of the 3D-printed, physical artefacts. Their responses suggest that the created artefacts succeed in triggering imagination, and in accelerating moods and narratives of various sorts.
The paper investigates how well poetry can be generated to contain a specific sentiment, and whet... more The paper investigates how well poetry can be generated to contain a specific sentiment, and whether readers of the poetry experience the intended sentiment. The poetry generator consists of a bi-directional Long ShortTerm Memory (LSTM) model, combined with rhyme pair generation, rule-based word prediction methods, and tree search for extending generation possibilities. The LSTM network was trained on a set of English poetry written and published by users on a public website. Human judges evaluated poems generated by the system, both with a positive and negative sentiment. The results indicate that while there are some weaknesses in the system compared to other state-of-the-art solutions, it is fully capable of generating poetry with an inherent sentiment that is perceived by readers.
Advances in Intelligent Systems and Computing, 2019
The paper tackles the question of evolvable media repositories, i.e., local pools of media files ... more The paper tackles the question of evolvable media repositories, i.e., local pools of media files that are retrieved over the Internet and that are ever-renovated with new, related files in an evolutionary fashion. The herein proposed method encodes genotypic space by virtue of simple undirected graphs of natural language tokens that represent web queries without employing fitness functions or other evaluation/selection schemata. Once a first population is seeded, a series of modular crawlers query the particular World Wide Web repositories of interest for both media content and assorted meta-data. Then, a series of attached intelligent comprehenders analyse the retrieved content in order to eventually generate new genetic representations, and the cycle is repeated. Such a method is generic, scalable and modular, and can be made fit the purposes of a wide array of applications in all sorts of disparate contextual and functional scenarios. The paper features a formal description of the method, gives implementation guidelines, and presents example usages.
International Journal on Artificial Intelligence Tools, 2020
Sentiment analysis is a circumstantial analysis of text, identifying the social sentiment to bett... more Sentiment analysis is a circumstantial analysis of text, identifying the social sentiment to better understand the source material. The article addresses sentiment analysis of an English-Hindi and English-Bengali code-mixed textual corpus collected from social media. Code-mixing is an amalgamation of multiple languages, which previously mainly was associated with spoken language. However, social media users also deploy it to communicate in ways that tend to be somewhat casual. The coarse nature of social media text poses challenges for many language processing applications. Here, the focus is on the low predictive nature of traditional machine learners when compared to Deep Learning counterparts, including the contextual language representation model BERT (Bidirectional Encoder Representations from Transformers), on the task of extracting user sentiment from code-mixed texts. Three deep learners (a BiLSTM CNN, a Double BiLSTM and an Attention-based model) attained accuracy 20–60% gr...
This article addresses language identification at the word level in Indian social media corpora t... more This article addresses language identification at the word level in Indian social media corpora taken from Facebook, Twitter and WhatsApp posts that exhibit code-mixing between English-Hindi, English-Bengali, as well as a blend of both language pairs. Code-mixing is a fusion of multiple languages previously mainly associated with spoken language, but which social media users also deploy when communicating in ways that tend to be rather casual. The coarse nature of code-mixed social media text makes language identification challenging. Here, the performance of deep learning on this task is compared to feature-based learning, with two Recursive Neural Network techniques, Long Short Term Memory (LSTM) and bidirectional LSTM, being contrasted to a Conditional Random Fields (CRF) classifier. The results show the deep learners outscoring the CRF, with the bidirectional LSTM demonstrating the best language identification performance.
The paper describes an experimental system for generating 3D-printable models inspired by arbitra... more The paper describes an experimental system for generating 3D-printable models inspired by arbitrary textual input. Utilizing a transliteration pipeline, the system pivots on Natural Language Understanding technologies and 3D data available via online repositories to result in a bag of retrieved 3D models that are then concatenated in order to produce original designs. Such artefacts celebrate a post-digital kind of objecthood, as they are concretely physical while, at the same time, incorporate the cybernetic encodings of their own making. Twelve individuals were asked to reflect on some of the 3D-printed, physical artefacts. Their responses suggest that the created artefacts succeed in triggering imagination, and in accelerating moods and narratives of various sorts.
The paper investigates how well poetry can be generated to contain a specific sentiment, and whet... more The paper investigates how well poetry can be generated to contain a specific sentiment, and whether readers of the poetry experience the intended sentiment. The poetry generator consists of a bi-directional Long ShortTerm Memory (LSTM) model, combined with rhyme pair generation, rule-based word prediction methods, and tree search for extending generation possibilities. The LSTM network was trained on a set of English poetry written and published by users on a public website. Human judges evaluated poems generated by the system, both with a positive and negative sentiment. The results indicate that while there are some weaknesses in the system compared to other state-of-the-art solutions, it is fully capable of generating poetry with an inherent sentiment that is perceived by readers.
Advances in Intelligent Systems and Computing, 2019
The paper tackles the question of evolvable media repositories, i.e., local pools of media files ... more The paper tackles the question of evolvable media repositories, i.e., local pools of media files that are retrieved over the Internet and that are ever-renovated with new, related files in an evolutionary fashion. The herein proposed method encodes genotypic space by virtue of simple undirected graphs of natural language tokens that represent web queries without employing fitness functions or other evaluation/selection schemata. Once a first population is seeded, a series of modular crawlers query the particular World Wide Web repositories of interest for both media content and assorted meta-data. Then, a series of attached intelligent comprehenders analyse the retrieved content in order to eventually generate new genetic representations, and the cycle is repeated. Such a method is generic, scalable and modular, and can be made fit the purposes of a wide array of applications in all sorts of disparate contextual and functional scenarios. The paper features a formal description of the method, gives implementation guidelines, and presents example usages.
International Journal on Artificial Intelligence Tools, 2020
Sentiment analysis is a circumstantial analysis of text, identifying the social sentiment to bett... more Sentiment analysis is a circumstantial analysis of text, identifying the social sentiment to better understand the source material. The article addresses sentiment analysis of an English-Hindi and English-Bengali code-mixed textual corpus collected from social media. Code-mixing is an amalgamation of multiple languages, which previously mainly was associated with spoken language. However, social media users also deploy it to communicate in ways that tend to be somewhat casual. The coarse nature of social media text poses challenges for many language processing applications. Here, the focus is on the low predictive nature of traditional machine learners when compared to Deep Learning counterparts, including the contextual language representation model BERT (Bidirectional Encoder Representations from Transformers), on the task of extracting user sentiment from code-mixed texts. Three deep learners (a BiLSTM CNN, a Double BiLSTM and an Attention-based model) attained accuracy 20–60% gr...
This article addresses language identification at the word level in Indian social media corpora t... more This article addresses language identification at the word level in Indian social media corpora taken from Facebook, Twitter and WhatsApp posts that exhibit code-mixing between English-Hindi, English-Bengali, as well as a blend of both language pairs. Code-mixing is a fusion of multiple languages previously mainly associated with spoken language, but which social media users also deploy when communicating in ways that tend to be rather casual. The coarse nature of code-mixed social media text makes language identification challenging. Here, the performance of deep learning on this task is compared to feature-based learning, with two Recursive Neural Network techniques, Long Short Term Memory (LSTM) and bidirectional LSTM, being contrasted to a Conditional Random Fields (CRF) classifier. The results show the deep learners outscoring the CRF, with the bidirectional LSTM demonstrating the best language identification performance.
Uploads
Papers by Björn Gambäck