This page lists all of my publications. Alternatively, you can visit my profiles on Google Scholar, SemanticScholar, and Tilburg University. Since the field of computational linguistics is conference-driven, most of my work is published through proceedings in the ACL Anthology.
You can download my PhD thesis here.
2016
van Miltenburg, Emiel; Timmermans, Benjamin; Aroyo, Lora
The VU Sound Corpus: Adding More Fine-grained Annotations to the Freesound Database Proceedings Article
In: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC 2016), European Language Resources Association (ELRA), 2016, ISBN: 9782951740891.
@inproceedings{7353623bf2c74539a868c8d7702d9482,
title = {The VU Sound Corpus: Adding More Fine-grained Annotations to the Freesound Database},
author = {Emiel van Miltenburg and Benjamin Timmermans and Lora Aroyo},
url = {https://aclanthology.org/L16-1337/},
isbn = {9782951740891},
year = {2016},
date = {2016-01-01},
urldate = {2016-01-01},
booktitle = {Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC 2016)},
publisher = {European Language Resources Association (ELRA)},
abstract = {This paper presents a collection of annotations (tags or keywords) for a set of 2,133 environmental sounds taken from the Freesound database (www.freesound.org). The annotations are acquired through an open-ended crowd-labeling task, in which participants were asked to provide keywords for each of three sounds. The main goal of this study is to find out (i) whether it is feasible to collect keywords for a large collection of sounds through crowdsourcing, and (ii) how people talk about sounds, and what information they can infer from hearing a sound in isolation. Our main finding is that it is not only feasible to perform crowd-labeling for a large collection of sounds, it is also very useful to highlight different aspects of the sounds that authors may fail to mention. Our data is freely available, and can be used to ground semantic models, improve search in audio databases, and to study the language of sound.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper presents a collection of annotations (tags or keywords) for a set of 2,133 environmental sounds taken from the Freesound database (www.freesound.org). The annotations are acquired through an open-ended crowd-labeling task, in which participants were asked to provide keywords for each of three sounds. The main goal of this study is to find out (i) whether it is feasible to collect keywords for a large collection of sounds through crowdsourcing, and (ii) how people talk about sounds, and what information they can infer from hearing a sound in isolation. Our main finding is that it is not only feasible to perform crowd-labeling for a large collection of sounds, it is also very useful to highlight different aspects of the sounds that authors may fail to mention. Our data is freely available, and can be used to ground semantic models, improve search in audio databases, and to study the language of sound.
Miltenburg, Emiel
Wordnet-based similarity metrics for adjectives Proceedings Article
In: Proceedings of the 8th Global WordNet Conference, pp. 414–418, Global WordNet Association, 2016.
@inproceedings{737d93ba2f8343669b02b58d31f2f317,
title = {Wordnet-based similarity metrics for adjectives},
author = {Emiel Miltenburg},
url = {https://aclanthology.org/2016.gwc-1.58/},
year = {2016},
date = {2016-01-01},
urldate = {2016-01-01},
booktitle = {Proceedings of the 8th Global WordNet Conference},
pages = {414–418},
publisher = {Global WordNet Association},
abstract = {Le and Fokkens (2015) recently showed that taxonomy-based approaches are more reliable than corpus-based approaches in estimating human similarity ratings. On the other hand, distributional models provide much better coverage. The lack of an established similarity metric for adjectives in WordNet is a case in point. I present initial work to establish such a metric, and propose ways to move forward by looking at extensions to WordNet. I show that the shortest path distance between derivationally related forms provides a reliable estimate of adjective similarity. Furthermore, I find that a hybrid method combining this measure with vector-based similarity estimations gives us the best of both worlds: more reliable similarity estimations than vectors alone, but with the same coverage as corpus-based methods.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Le and Fokkens (2015) recently showed that taxonomy-based approaches are more reliable than corpus-based approaches in estimating human similarity ratings. On the other hand, distributional models provide much better coverage. The lack of an established similarity metric for adjectives in WordNet is a case in point. I present initial work to establish such a metric, and propose ways to move forward by looking at extensions to WordNet. I show that the shortest path distance between derivationally related forms provides a reliable estimate of adjective similarity. Furthermore, I find that a hybrid method combining this measure with vector-based similarity estimations gives us the best of both worlds: more reliable similarity estimations than vectors alone, but with the same coverage as corpus-based methods.
2015
Lopopolo, Alessandro; Miltenburg, Emiel
Sound-based distributional models Proceedings Article
In: Proceedings of the 11th International Conference on Computational Semantics, pp. 70–75, Association for Computational Linguistics, 2015.
@inproceedings{ecef5e612aad4e33949ab2a77187f82c,
title = {Sound-based distributional models},
author = {Alessandro Lopopolo and Emiel Miltenburg},
url = {https://aclanthology.org/W15-0110/},
year = {2015},
date = {2015-04-00},
urldate = {2015-04-00},
booktitle = {Proceedings of the 11th International Conference on Computational Semantics},
pages = {70–75},
publisher = {Association for Computational Linguistics},
abstract = {Following earlier work in multimodal distributional semantics, we present the first results of our efforts to build a perceptually grounded semantic model. Rather than using images, our models are built on sound data collected from freesound.org. We compare three models: one bag-of-words model based on user-provided tags, a model based on audio features, using a ‘bag-of-audio-words’ approach and a model that combines the two. Our results show that the models are able to capture semantic relatedness, with the tag-based model scoring higher than the sound-based model and the combined model. However, capturing semantic relatedness is biased towards language-based models. Future work will focus on improving the sound-based model, finding ways to combine linguistic and acoustic information, and creating more reliable evaluation data.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Following earlier work in multimodal distributional semantics, we present the first results of our efforts to build a perceptually grounded semantic model. Rather than using images, our models are built on sound data collected from freesound.org. We compare three models: one bag-of-words model based on user-provided tags, a model based on audio features, using a ‘bag-of-audio-words’ approach and a model that combines the two. Our results show that the models are able to capture semantic relatedness, with the tag-based model scoring higher than the sound-based model and the combined model. However, capturing semantic relatedness is biased towards language-based models. Future work will focus on improving the sound-based model, finding ways to combine linguistic and acoustic information, and creating more reliable evaluation data.
Miltenburg, Emiel
Exploring and visualizing distributional models using graphs Conference
2015, (Advances in Distributional Semantics (collocated with IWCS) ; Conference date: 14-04-2015 Through 14-04-2015).
@conference{0a562a97095a47b996870225910bb230,
title = {Exploring and visualizing distributional models using graphs},
author = {Emiel Miltenburg},
url = {https://research.tilburguniversity.edu/en/publications/exploring-and-visualizing-distributional-models-using-graphs},
year = {2015},
date = {2015-01-01},
urldate = {2015-01-01},
note = {Advances in Distributional Semantics (collocated with IWCS) ; Conference date: 14-04-2015 Through 14-04-2015},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}