Publications

SFB 1102Publications
69 entries
Sayeed, Asad; Demberg, Vera; Shkadzko, Pavel

An Exploration of Semantic Features in an Unsupervised Thematic Fit Evaluation Framework Conference

IJCoL: Emerging Topics at the First Italian Conference on Computational Linguistics, 1, 2015.

Thematic fit is the extent to which an entity fits a thematic role in the semantic frame of an event, e.g., how well humans would rate “knife” as an instrument of an event of cutting. We explore the use of the SENNA semantic role-labeller in defining a distributional space in order to build an unsupervised model of event-entity thematic fit judgements. We test a number of ways of extracting features from SENNA-labelled versions of the ukWaC and BNC corpora and identify tradeoffs. Some of our Distributional Memory models outperform an existing syntax-based model (TypeDM) that uses hand-crafted rules for role inference on a previously tested data set. We combine the results of a selected SENNA-based model with TypeDM’s results and find that there is some amount of complementarity in what a syntactic and a semantic model will cover. In the process, we create a broad-coverage semantically-labelled corpus.

@conference{sayeed:demberg:shkadzko:2015:IJCOL,
title = {An Exploration of Semantic Features in an Unsupervised Thematic Fit Evaluation Framework},
author = {Asad Sayeed and Vera Demberg and Pavel Shkadzko},
url = {https://journals.openedition.org/ijcol/298},
year = {2015},
date = {2015},
booktitle = {IJCoL: Emerging Topics at the First Italian Conference on Computational Linguistics},
abstract = {

Thematic fit is the extent to which an entity fits a thematic role in the semantic frame of an event, e.g., how well humans would rate “knife” as an instrument of an event of cutting. We explore the use of the SENNA semantic role-labeller in defining a distributional space in order to build an unsupervised model of event-entity thematic fit judgements. We test a number of ways of extracting features from SENNA-labelled versions of the ukWaC and BNC corpora and identify tradeoffs. Some of our Distributional Memory models outperform an existing syntax-based model (TypeDM) that uses hand-crafted rules for role inference on a previously tested data set. We combine the results of a selected SENNA-based model with TypeDM’s results and find that there is some amount of complementarity in what a syntactic and a semantic model will cover. In the process, we create a broad-coverage semantically-labelled corpus.

},
pubstate = {published},
type = {conference}
}

Copy BibTeX to Clipboard

Project:   B2

Demberg, Vera; Torabi Asr, Fatemeh; Rohde, Hannah

Discourse Expectations Raised by Contrastive Connectives Inproceedings

Conference on Discourse Expectations: Theoretical, Experimental, and Computational Perspectives (DETEC), 2015.

Markers of negative polarity discourse relations, such as but, although and on the one hand… on the other hand have been shown to induce more processing difficulty than additive or causal markers (e.g., Murray, 1995), and to facilitate the processing of upcoming content (e.g., Köhne & Demberg, 2013). These markers have been argued to shape comprehenders‘ discourse expectations in a way that differs from what comprehenders would expect in the absence of such markers (Murray, 1995; Köhne & Demberg, 2013; Xiang & Kuperberg, 2014). Here, we present two studies on the nature of the expectations elicited by negative polarity connectives, addressing three primary questions: (i) How specific are the expectations elicited by ambiguous connectors such as but and although? (ii) Do the discourse expectations raised by a connective like on the one hand target any contrast or specifically on the other hand? (iii) Are expectations sensitive to discourse structure?

@inproceedings{demberg2015contrastive,
title = {Discourse Expectations Raised by Contrastive Connectives},
author = {Vera Demberg and Fatemeh Torabi Asr and Hannah Rohde},
url = {https://detec2015.files.wordpress.com/2015/05/demberg.pdf},
year = {2015},
date = {2015},
booktitle = {Conference on Discourse Expectations: Theoretical, Experimental, and Computational Perspectives (DETEC)},
abstract = {Markers of negative polarity discourse relations, such as but, although and on the one hand... on the other hand have been shown to induce more processing difficulty than additive or causal markers (e.g., Murray, 1995), and to facilitate the processing of upcoming content (e.g., K{\"o}hne & Demberg, 2013). These markers have been argued to shape comprehenders' discourse expectations in a way that differs from what comprehenders would expect in the absence of such markers (Murray, 1995; K{\"o}hne & Demberg, 2013; Xiang & Kuperberg, 2014). Here, we present two studies on the nature of the expectations elicited by negative polarity connectives, addressing three primary questions: (i) How specific are the expectations elicited by ambiguous connectors such as but and although? (ii) Do the discourse expectations raised by a connective like on the one hand target any contrast or specifically on the other hand? (iii) Are expectations sensitive to discourse structure?},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Project:   B2

Torabi Asr, Fatemeh; Demberg, Vera

A Discourse Connector's Distribution Determines Its Interpretation Inproceedings

The 28th CUNY Conference on Human Sentence Processing 2015, 2015.

Many connectives, such as but and although, can be used to mark very similar sets of relations, see Table 1. Fraser 1999 proposes that each connective has a core meaning and that a more specific discourse relation will be inferred from the content of the involved clauses. This implies that connectives which can mark the same relations have the same core meaning, and that alternating between two such connectors should not change the meaning of the discourse. A fully distributional account (Asr & Demberg 2013), on the other hand, describes the information content of a connective based on its usage patterns. This means that a connective may even have different meanings in different sentence positions (i.e. when used sentenceinitially vs. between its arguments). This study shows how the fine-grained differences in the distribution of but vs. although vs. sentence-initial although affect text coherence. We created stories consisting of three sentences (see below) and normed them such that the first two sentences were equally acceptable in all conditions. The design was fully counter-balanced.

@inproceedings{asr2015interpretation,
title = {A Discourse Connector's Distribution Determines Its Interpretation},
author = {Fatemeh Torabi Asr and Vera Demberg},
url = {https://www.coli.uni-saarland.de/~fatemeh/CUNY2015_abstract.pdf},
year = {2015},
date = {2015},
booktitle = {The 28th CUNY Conference on Human Sentence Processing 2015},
abstract = {Many connectives, such as but and although, can be used to mark very similar sets of relations, see Table 1. Fraser 1999 proposes that each connective has a core meaning and that a more specific discourse relation will be inferred from the content of the involved clauses. This implies that connectives which can mark the same relations have the same core meaning, and that alternating between two such connectors should not change the meaning of the discourse. A fully distributional account (Asr & Demberg 2013), on the other hand, describes the information content of a connective based on its usage patterns. This means that a connective may even have different meanings in different sentence positions (i.e. when used sentenceinitially vs. between its arguments). This study shows how the fine-grained differences in the distribution of but vs. although vs. sentence-initial although affect text coherence. We created stories consisting of three sentences (see below) and normed them such that the first two sentences were equally acceptable in all conditions. The design was fully counter-balanced.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Project:   B2

Torabi Asr, Fatemeh

An Information Theoretic Approach to Production and Comprehension of Discourse Markers PhD Thesis

Saarland University, Saarbruecken, Germany, 2015.

Discourse relations are the building blocks of a coherent text. The most important linguistic elements for constructing these relations are discourse markers. The presence of a discourse marker between two discourse segments provides information on the inferences that need to be made for interpretation of the two segments as a whole (e.g., because marks a reason).

This thesis presents a new framework for studying human communication at the level of discourse by adapting ideas from information theory. A discourse marker is viewed as a symbol with a measurable amount of relational information. This information is communicated by the writer of a text to guide the reader towards the right semantic decoding. To examine the information theoretic account of discourse markers, we conduct empirical corpus-based investigations, offline crowd-sourced studies and online laboratory experiments. The thesis contributes to computational linguistics by proposing a quantitative meaning representation for discourse markers and showing its advantages over the classic descriptive approaches. For the first time, we show that readers are very sensitive to the fine-grained information encoded in a discourse marker obtained from its natural usage and that writers use explicit marking for less expected relations in terms of linguistic and cognitive predictability. These findings open new directions for implementation of advanced natural language processing systems.

@phdthesis{BentPhd05,
title = {An Information Theoretic Approach to Production and Comprehension of Discourse Markers},
author = {Fatemeh Torabi Asr},
url = {https://publikationen.sulb.uni-saarland.de/handle/20.500.11880/26688},
year = {2015},
date = {2015},
school = {Saarland University},
address = {Saarbruecken, Germany},
abstract = {Discourse relations are the building blocks of a coherent text. The most important linguistic elements for constructing these relations are discourse markers. The presence of a discourse marker between two discourse segments provides information on the inferences that need to be made for interpretation of the two segments as a whole (e.g., because marks a reason). This thesis presents a new framework for studying human communication at the level of discourse by adapting ideas from information theory. A discourse marker is viewed as a symbol with a measurable amount of relational information. This information is communicated by the writer of a text to guide the reader towards the right semantic decoding. To examine the information theoretic account of discourse markers, we conduct empirical corpus-based investigations, offline crowd-sourced studies and online laboratory experiments. The thesis contributes to computational linguistics by proposing a quantitative meaning representation for discourse markers and showing its advantages over the classic descriptive approaches. For the first time, we show that readers are very sensitive to the fine-grained information encoded in a discourse marker obtained from its natural usage and that writers use explicit marking for less expected relations in terms of linguistic and cognitive predictability. These findings open new directions for implementation of advanced natural language processing systems.},
pubstate = {published},
type = {phdthesis}
}

Copy BibTeX to Clipboard

Project:   B2

Sayeed, Asad

Representing the Effort in Resolving Ambiguous Scope Inproceedings

Sinn und Bedeutung 20, Tübingen, Germany, 2015.
This work proposes a way to formally model online scope interpretation in terms of recent experimental results. Specifically, it attempts to reconcile underspecified representations of semantic processing with results that show that there are higher-order dependencies between relative quantifier scope orderings that the processor may assert. It proposes a constrained data structure and movement operator that provides just enough specification to allow these higher-order dependencies to be represented. The operation reflects regression probabilities in one of the cited experiments.

@inproceedings{SuB2015,
title = {Representing the Effort in Resolving Ambiguous Scope},
author = {Asad Sayeed},
url = {https://ojs.ub.uni-konstanz.de/sub/index.php/sub/article/view/284},
year = {2015},
date = {2015},
booktitle = {Sinn und Bedeutung 20},
address = {T{\"u}bingen, Germany},
abstract = {

This work proposes a way to formally model online scope interpretation in terms of recent experimental results. Specifically, it attempts to reconcile underspecified representations of semantic processing with results that show that there are higher-order dependencies between relative quantifier scope orderings that the processor may assert. It proposes a constrained data structure and movement operator that provides just enough specification to allow these higher-order dependencies to be represented. The operation reflects regression probabilities in one of the cited experiments.
},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Project:   B2

Torabi Asr, Fatemeh; Demberg, Vera

A Distributional Account of Discourse Connectives and its Effect on Fine-grained Inferences Inproceedings

Text-link Conference, Louvain, Belgium, 2015.

@inproceedings{asr2015distributionalApproach,
title = {A Distributional Account of Discourse Connectives and its Effect on Fine-grained Inferences},
author = {Fatemeh Torabi Asr and Vera Demberg},
year = {2015},
date = {2015},
booktitle = {Text-link Conference},
address = {Louvain, Belgium},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Project:   B2

Torabi Asr, Fatemeh; Demberg, Vera

Uniform Information Density at the Level of Discourse Relations: Negation Markers and Discourse Connective Omission Inproceedings

IWCS 2015, pp. 118, 2015.

About half of the discourse relations annotated in Penn Discourse Treebank (Prasad et al., 2008) are not explicitly marked using a discourse connective. But we do not have extensive theories of when or why a discourse relation is marked explicitly or when the connective is omitted. Asr and Demberg (2012a) have suggested an information-theoretic perspective according to which discourse connectives are more likely to be omitted when they are marking a relation that is expected or predictable. This account is based on the Uniform Information Density theory (Levy and Jaeger, 2007), which suggests that speakers choose among alternative formulations that are allowed in their language the ones that achieve a roughly uniform rate of information transmission. Optional discourse markers should thus be omitted if they would lead to a trough in information density, and be inserted in order to avoid peaks in information density. We here test this hypothesis by observing how far a specific cue, negation in any form, affects the discourse relations that can be predicted to hold in a text, and how the presence of this cue in turn affects the use of explicit discourse connectives.

@inproceedings{asr2015uniform,
title = {Uniform Information Density at the Level of Discourse Relations: Negation Markers and Discourse Connective Omission},
author = {Fatemeh Torabi Asr and Vera Demberg},
url = {https://www.semanticscholar.org/paper/Uniform-Information-Density-at-the-Level-of-Markers-Asr-Demberg/cee6437e3aba3e772ef8cc7e9aaf3d7ba1114d8b},
year = {2015},
date = {2015},
booktitle = {IWCS 2015},
pages = {118},
abstract = {About half of the discourse relations annotated in Penn Discourse Treebank (Prasad et al., 2008) are not explicitly marked using a discourse connective. But we do not have extensive theories of when or why a discourse relation is marked explicitly or when the connective is omitted. Asr and Demberg (2012a) have suggested an information-theoretic perspective according to which discourse connectives are more likely to be omitted when they are marking a relation that is expected or predictable. This account is based on the Uniform Information Density theory (Levy and Jaeger, 2007), which suggests that speakers choose among alternative formulations that are allowed in their language the ones that achieve a roughly uniform rate of information transmission. Optional discourse markers should thus be omitted if they would lead to a trough in information density, and be inserted in order to avoid peaks in information density. We here test this hypothesis by observing how far a specific cue, negation in any form, affects the discourse relations that can be predicted to hold in a text, and how the presence of this cue in turn affects the use of explicit discourse connectives.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Project:   B2

Sayeed, Asad; Fischer, Stefan; Demberg, Vera

To What Extent Do We Adapt Spoken Word Durations to a Domain? Inproceedings

Architectures and mechanisms for language processing (AMLaP), Malta, 2015.

@inproceedings{AMLaP2015a,
title = {To What Extent Do We Adapt Spoken Word Durations to a Domain?},
author = {Asad Sayeed and Stefan Fischer and Vera Demberg},
url = {https://www.bibsonomy.org/bibtex/ddebcecc8adb8f40a0abf87294b11a02},
year = {2015},
date = {2015},
booktitle = {Architectures and mechanisms for language processing (AMLaP)},
address = {Malta},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Project:   B2

Greenberg, Clayton; Demberg, Vera; Sayeed, Asad

Verb Polysemy and Frequency Effects in Thematic Fit Modeling Inproceedings

Proceedings of the 6th Workshop on Cognitive Modeling and Computational Linguistics, Association for Computational Linguistics, pp. 48-57, Denver, Colorado, 2015.

While several data sets for evaluating thematic fit of verb-role-filler triples exist, they do not control for verb polysemy. Thus, it is unclear how verb polysemy affects human ratings of thematic fit and how best to model that. We present a new dataset of human ratings on high vs. low-polysemy verbs matched for verb frequency, together with high vs. low-frequency and well-fitting vs. poorly-fitting patient rolefillers. Our analyses show that low-polysemy verbs produce stronger thematic fit judgements than verbs with higher polysemy. Rolefiller frequency, on the other hand, had little effect on ratings. We show that these results can best be modeled in a vector space using a clustering technique to create multiple prototype vectors representing different “senses” of the verb.

@inproceedings{greenberg-demberg-sayeed:2015:CMCL,
title = {Verb Polysemy and Frequency Effects in Thematic Fit Modeling},
author = {Clayton Greenberg and Vera Demberg and Asad Sayeed},
url = {http://www.aclweb.org/anthology/W15-1106},
year = {2015},
date = {2015-06-01},
booktitle = {Proceedings of the 6th Workshop on Cognitive Modeling and Computational Linguistics},
pages = {48-57},
publisher = {Association for Computational Linguistics},
address = {Denver, Colorado},
abstract = {While several data sets for evaluating thematic fit of verb-role-filler triples exist, they do not control for verb polysemy. Thus, it is unclear how verb polysemy affects human ratings of thematic fit and how best to model that. We present a new dataset of human ratings on high vs. low-polysemy verbs matched for verb frequency, together with high vs. low-frequency and well-fitting vs. poorly-fitting patient rolefillers. Our analyses show that low-polysemy verbs produce stronger thematic fit judgements than verbs with higher polysemy. Rolefiller frequency, on the other hand, had little effect on ratings. We show that these results can best be modeled in a vector space using a clustering technique to create multiple prototype vectors representing different “senses” of the verb.},
pubstate = {published},
type = {inproceedings}
}

Copy BibTeX to Clipboard

Projects:   B2 B4

Successfully