Publications

SFB 1102Publications
8 entries
Nguyen, Dai Quoc; Nguyen, Dat Quoc; Modi, Ashutosh; Thater, Stefan; Pinkal, Manfred

A Mixture Model for Learning Multi-Sense Word Embeddings Inproceedings

Association for Computational Linguistics, pp. 121-127, Vancouver, Canada, 2017.

Word embeddings are now a standard technique for inducing meaning representations for words. For getting good representations, it is important to take into account different senses of a word. In this paper, we propose a mixture model for learning multi-sense word embeddings.

Our model generalizes the previous works in that it allows to induce different weights of different senses of a word. The experimental results show that our model outperforms previous models on standard evaluation tasks.

@inproceedings{nguyen-EtAl:2017:starSEM,
title = {A Mixture Model for Learning Multi-Sense Word Embeddings},
author = {Dai Quoc Nguyen and Dat Quoc Nguyen and Ashutosh Modi and Stefan Thater and Manfred Pinkal},
url = {http://www.aclweb.org/anthology/S17-1015},
year = {2017},
date = {2017},
pages = {121-127},
publisher = {Association for Computational Linguistics},
address = {Vancouver, Canada},
abstract = {Word embeddings are now a standard technique for inducing meaning representations for words. For getting good representations, it is important to take into account different senses of a word. In this paper, we propose a mixture model for learning multi-sense word embeddings. Our model generalizes the previous works in that it allows to induce different weights of different senses of a word. The experimental results show that our model outperforms previous models on standard evaluation tasks.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Projects:   A2 A3

Nguyen, Dai Quoc; Nguyen, Dat Quoc; Chu, Cuong Xuan; Thater, Stefan; Pinkal, Manfred

Sequence to Sequence Learning for Event Prediction Inproceedings

Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers), Asian Federation of Natural Language Processing, pp. 37-42, Taipei, Taiwan, 2017.

This paper presents an approach to the task of predicting an event description from a preceding sentence in a text. Our approach explores sequence-to-sequence learning using a bidirectional multi-layer recurrent neural network. Our approach substantially outperforms previous work in terms of the BLEU score on two datasets derived from WikiHow and DeScript respectively.

Since the BLEU score is not easy to interpret as a measure of event prediction, we complement our study with a second evaluation that exploits the rich linguistic annotation of gold paraphrase sets of events.

@inproceedings{nguyen-EtAl:2017:I17-2,
title = {Sequence to Sequence Learning for Event Prediction},
author = {Dai Quoc Nguyen and Dat Quoc Nguyen and Cuong Xuan Chu and Stefan Thater and Manfred Pinkal},
url = {http://www.aclweb.org/anthology/I17-2007},
year = {2017},
date = {2017-10-17},
booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)},
pages = {37-42},
publisher = {Asian Federation of Natural Language Processing},
address = {Taipei, Taiwan},
abstract = {This paper presents an approach to the task of predicting an event description from a preceding sentence in a text. Our approach explores sequence-to-sequence learning using a bidirectional multi-layer recurrent neural network. Our approach substantially outperforms previous work in terms of the BLEU score on two datasets derived from WikiHow and DeScript respectively. Since the BLEU score is not easy to interpret as a measure of event prediction, we complement our study with a second evaluation that exploits the rich linguistic annotation of gold paraphrase sets of events.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Projects:   A3 A2

Wanzare, Lilian Diana Awuor; Zarcone, Alessandra; Thater, Stefan; Pinkal, Manfred

Inducing Script Structure from Crowdsourced Event Descriptions via Semi-Supervised Clustering Inproceedings

Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics, Association for Computational Linguistics, pp. 1-11, Valencia, Spain, 2017.

We present a semi-supervised clustering approach to induce script structure from crowdsourced descriptions of event sequences by grouping event descriptions into paraphrase sets (representing event types) and inducing their temporal order. Our approach exploits semantic and positional similarity and allows for flexible event order, thus overcoming the rigidity of previous approaches. We incorporate crowdsourced alignments as prior knowledge and show that exploiting a small number of alignments results in a substantial improvement in cluster quality over state-of-the-art models and provides an appropriate basis for the induction of temporal order. We also show a coverage study to demonstrate the scalability of our approach.

@inproceedings{wanzare-EtAl:2017:LSDSem,
title = {Inducing Script Structure from Crowdsourced Event Descriptions via Semi-Supervised Clustering},
author = {Lilian Diana Awuor Wanzare and Alessandra Zarcone and Stefan Thater and Manfred Pinkal},
url = {https://www.aclweb.org/anthology/W17-0901},
doi = {https://doi.org/10.18653/v1/W17-0901},
year = {2017},
date = {2017},
booktitle = {Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics},
pages = {1-11},
publisher = {Association for Computational Linguistics},
address = {Valencia, Spain},
abstract = {We present a semi-supervised clustering approach to induce script structure from crowdsourced descriptions of event sequences by grouping event descriptions into paraphrase sets (representing event types) and inducing their temporal order. Our approach exploits semantic and positional similarity and allows for flexible event order, thus overcoming the rigidity of previous approaches. We incorporate crowdsourced alignments as prior knowledge and show that exploiting a small number of alignments results in a substantial improvement in cluster quality over state-of-the-art models and provides an appropriate basis for the induction of temporal order. We also show a coverage study to demonstrate the scalability of our approach.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Project:   A2

Wanzare, Lilian Diana Awuor; Zarcone, Alessandra; Thater, Stefan; Pinkal, Manfred

A Crowdsourced Database of Event Sequence Descriptions for the Acquisition of High-quality Script Knowledge Inproceedings

Calzolari, Nicoletta; Choukri, Khalid; Declerck, Thierry; Grobelnik, Marko; Maegaard, Bente; Mariani, Joseph; Moreno, Asuncion; Odijk, Jan; Piperidis, Stelios;  (Ed.): Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), European Language Resources Association (ELRA), Portorož, Slovenia, 2016, ISBN 978-2-9517408-9-1.

Scripts are standardized event sequences describing typical everyday activities, which play an important role in the computational modeling of cognitive abilities (in particular for natural language processing). We present a large-scale crowdsourced collection of explicit linguistic descriptions of script-specific event sequences (40 scenarios with 100 sequences each). The corpus is enriched with crowdsourced alignment annotation on a subset of the event descriptions, to be used in future work as seed data for automatic alignment of event descriptions (for example via clustering). The event descriptions to be aligned were chosen among those expected to have the strongest corrective effect on the clustering algorithm. The alignment annotation was evaluated against a gold standard of expert annotators. The resulting database of partially-aligned script-event descriptions provides a sound empirical basis for inducing high-quality script knowledge, as well as for any task involving alignment and paraphrase detection of events.

@inproceedings{WANZARE16.913,
title = {A Crowdsourced Database of Event Sequence Descriptions for the Acquisition of High-quality Script Knowledge},
author = {Lilian Diana Awuor Wanzare and Alessandra Zarcone and Stefan Thater and Manfred Pinkal},
editor = {Nicoletta Calzolari and Khalid Choukri and Thierry Declerck and Marko Grobelnik and Bente Maegaard and Joseph Mariani and Asuncion Moreno and Jan Odijk and Stelios Piperidis},
url = {https://aclanthology.org/L16-1556/},
year = {2016},
date = {2016},
booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
isbn = {978-2-9517408-9-1},
publisher = {European Language Resources Association (ELRA)},
address = {Portoro{\v{z}, Slovenia},
abstract = {Scripts are standardized event sequences describing typical everyday activities, which play an important role in the computational modeling of cognitive abilities (in particular for natural language processing). We present a large-scale crowdsourced collection of explicit linguistic descriptions of script-specific event sequences (40 scenarios with 100 sequences each). The corpus is enriched with crowdsourced alignment annotation on a subset of the event descriptions, to be used in future work as seed data for automatic alignment of event descriptions (for example via clustering). The event descriptions to be aligned were chosen among those expected to have the strongest corrective effect on the clustering algorithm. The alignment annotation was evaluated against a gold standard of expert annotators. The resulting database of partially-aligned script-event descriptions provides a sound empirical basis for inducing high-quality script knowledge, as well as for any task involving alignment and paraphrase detection of events.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Project:   A2

Zarcone, Alessandra; Padó, Sebastian; Lenci, Alessandro

Same Same but Different: Type and Typicality in a Distributional Model of Complement Coercion Inproceedings

Word Structure and Word Usage. Proceedings of the NetWordS Final Conference. Pisa, March 30-April 1, 2015, pp. 91-94, Pisa, Italy, 2015.
We aim to model the results from a selfpaced reading experiment, which tested the effect of semantic type clash and typicality on the processing of German complement coercion. We present two distributional semantic models to test if they can model the effect of both type and typicality in the psycholinguistic study. We show that one of the models, without explicitly representing type information, can account both for the effect of type and typicality in complement coercion.

@inproceedings{zarcone2015same,
title = {Same Same but Different: Type and Typicality in a Distributional Model of Complement Coercion},
author = {Alessandra Zarcone and Sebastian Padó and Alessandro Lenci},
url = {https://www.researchgate.net/publication/282740292_Same_same_but_different_Type_and_typicality_in_a_distributional_model_of_complement_coercion},
year = {2015},
date = {2015},
booktitle = {Word Structure and Word Usage. Proceedings of the NetWordS Final Conference. Pisa, March 30-April 1, 2015},
pages = {91-94},
address = {Pisa, Italy},
abstract = {

We aim to model the results from a selfpaced reading experiment, which tested the effect of semantic type clash and typicality on the processing of German complement coercion. We present two distributional semantic models to test if they can model the effect of both type and typicality in the psycholinguistic study. We show that one of the models, without explicitly representing type information, can account both for the effect of type and typicality in complement coercion.
},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Projects:   A2 A3

Batiukova, Olga; Bertinetto, Pier Marco; Lenci, Alessandro; Zarcone, Alessandra

Identifying Actional Features Through Semantic Priming: Cross-Romance Comparison Incollection

Taming the TAME systems. Cahiers Chronos 27, Rodopi, pp. 161-187, Amsterdam/Philadelphia, 2015.
This paper reports four semantic priming experiments in Italian and Spanish, whose goal was to verify the psychological reality of two aspectual features, resultativity and durativity. In the durativity task, the participants were asked whether the verb referred to a durable situation, in the resultativity task if it denoted a situation with a clear outcome. The results prove that both features are involved in online processing of the verb meaning: achievements ([+resultative, -durative]) and activities ([-resultative, +durative]) were processed faster in certain priming contexts. The priming patterns in the Romance languages present some striking similarities (only achievements were primed in the resultativity task) alongside some intriguing differences, and interestingly contrast with the behaviour of another language tested, Russian, whose aspectual system differs in significant ways.

@incollection{batiukova2015identifying,
title = {Identifying Actional Features Through Semantic Priming: Cross-Romance Comparison},
author = {Olga Batiukova and Pier Marco Bertinetto and Alessandro Lenci and Alessandra Zarcone},
url = {https://brill.com/display/book/edcoll/9789004292772/B9789004292772-s010.xml},
year = {2015},
date = {2015},
booktitle = {Taming the TAME systems. Cahiers Chronos 27},
pages = {161-187},
publisher = {Rodopi},
address = {Amsterdam/Philadelphia},
abstract = {

This paper reports four semantic priming experiments in Italian and Spanish, whose goal was to verify the psychological reality of two aspectual features, resultativity and durativity. In the durativity task, the participants were asked whether the verb referred to a durable situation, in the resultativity task if it denoted a situation with a clear outcome. The results prove that both features are involved in online processing of the verb meaning: achievements ([+resultative, -durative]) and activities ([-resultative, +durative]) were processed faster in certain priming contexts. The priming patterns in the Romance languages present some striking similarities (only achievements were primed in the resultativity task) alongside some intriguing differences, and interestingly contrast with the behaviour of another language tested, Russian, whose aspectual system differs in significant ways.
},
pubstate = {published},
type = {incollection}
}

Copy BibTeX to Clipboard

Projects:   A2 A3

Kampmann, Alexander; Thater, Stefan; Pinkal, Manfred

A Case-Study of Automatic Participant Labeling Inproceedings

Proceedings of the International Conference of the German Society for Computational Linguistics and Language Technology (GSCL 2015), 2015.

Knowlegde about stereotypical activities like visiting a restaurant or checking in at the airport is an important component to model text-understanding. We report on a case study of automatically relating texts to scripts representing such stereotypical knowledge. We focus on the subtask of mapping noun phrases in a text to participants in the script. We analyse the effect of various similarity measures and show that substantial positive results can be achieved on this complex task, indicating that the general problem is principally solvable.

@inproceedings{kampmann2015case,
title = {A Case-Study of Automatic Participant Labeling},
author = {Alexander Kampmann and Stefan Thater and Manfred Pinkal},
url = {https://www.bibsonomy.org/bibtex/256c2839962cccb21f7a2d41b3a83267?postOwner=sfb1102&intraHash=132779a64f2563005c65ee9cc14beb5f},
year = {2015},
date = {2015},
booktitle = {Proceedings of the International Conference of the German Society for Computational Linguistics and Language Technology (GSCL 2015)},
abstract = {Knowlegde about stereotypical activities like visiting a restaurant or checking in at the airport is an important component to model text-understanding. We report on a case study of automatically relating texts to scripts representing such stereotypical knowledge. We focus on the subtask of mapping noun phrases in a text to participants in the script. We analyse the effect of various similarity measures and show that substantial positive results can be achieved on this complex task, indicating that the general problem is principally solvable.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Project:   A2

Rohrbach, Marcus; Rohrbach, Anna; Regneri, Michaela; Amin, Sikandar; Andriluka, Mykhaylo; Pinkal, Manfred; Schiele, Bernt

Recognizing Fine-Grained and Composite Activities using Hand-Centric Features and Script Data Journal Article

International Journal of Computer Vision, pp. 1-28, 2015.

Activity recognition has shown impressive progress in recent years. However, the challenges of detecting fine-grained activities and understanding how they are combined into composite activities have been largely overlooked. In this work we approach both tasks and present a dataset which provides detailed annotations to address them. The first challenge is to detect fine-grained activities, which are defined by low inter-class variability and are typically characterized by fine-grained body motions. We explore how human pose and hands can help to approach this challenge by comparing two pose-based and two hand-centric features with state-of-the-art holistic features. To attack the second challenge, recognizing composite activities, we leverage the fact that these activities are compositional and that the essential components of the activities can be obtained from textual descriptions or scripts. We show the benefits of our hand-centric approach for fine-grained activity classification and detection. For composite activity recognition we find that decomposition into attributes allows sharing information across composites and is essential to attack this hard task. Using script data we can recognize novel composites without having training data for them.

@article{rohrbach2015recognizing,
title = {Recognizing Fine-Grained and Composite Activities using Hand-Centric Features and Script Data},
author = {Marcus Rohrbach and Anna Rohrbach and Michaela Regneri and Sikandar Amin and Mykhaylo Andriluka and Manfred Pinkal and Bernt Schiele},
url = {https://link.springer.com/article/10.1007/s11263-015-0851-8},
year = {2015},
date = {2015},
journal = {International Journal of Computer Vision},
pages = {1-28},
abstract = {

Activity recognition has shown impressive progress in recent years. However, the challenges of detecting fine-grained activities and understanding how they are combined into composite activities have been largely overlooked. In this work we approach both tasks and present a dataset which provides detailed annotations to address them. The first challenge is to detect fine-grained activities, which are defined by low inter-class variability and are typically characterized by fine-grained body motions. We explore how human pose and hands can help to approach this challenge by comparing two pose-based and two hand-centric features with state-of-the-art holistic features. To attack the second challenge, recognizing composite activities, we leverage the fact that these activities are compositional and that the essential components of the activities can be obtained from textual descriptions or scripts. We show the benefits of our hand-centric approach for fine-grained activity classification and detection. For composite activity recognition we find that decomposition into attributes allows sharing information across composites and is essential to attack this hard task. Using script data we can recognize novel composites without having training data for them.
},
pubstate = {published},
type = {article}
}

Copy BibTeX to Clipboard

Project:   A2

Successfully