Filters








12,215 Hits in 2.4 sec

Discourse Constraints for Document Compression

James Clarke, Mirella Lapata
2010 Computational Linguistics  
In this article we present a discourse-informed model which is capable of producing document compressions that are coherent and informative.  ...  Sentence compression holds promise for many applications ranging from summarization to subtitle generation.  ...  Acknowledgments We are grateful to Ryan McDonald for his help with the re-implementation of his system, and our annotators Vasilis Karaiskos and Sarah Luger.  ... 
doi:10.1162/coli_a_00004 fatcat:simocvdacrehhledvugtuq7bga

Learning-Based Single-Document Summarization with Compression and Anaphoricity Constraints [article]

Greg Durrett, Taylor Berg-Kirkpatrick, Dan Klein
2016 arXiv   pre-print
We present a discriminative model for single-document summarization that integrally combines compression and anaphoricity constraints.  ...  Our model selects textual units to include in the summary based on a rich set of sparse features whose weights are learned on a large corpus.  ...  Thanks to Tsutomu Hirao for providing assistance with our reimplementation of the Tree Knapsack model, and thanks the anonymous reviewers for their helpful comments.  ... 
arXiv:1603.08887v2 fatcat:vipceszlrjh3hoopxhpxqhatnu

Learning-Based Single-Document Summarization with Compression and Anaphoricity Constraints

Greg Durrett, Taylor Berg-Kirkpatrick, Dan Klein
2016 Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
We present a discriminative model for single-document summarization that integrally combines compression and anaphoricity constraints.  ...  Our model selects textual units to include in the summary based on a rich set of sparse features whose weights are learned on a large corpus.  ...  Thanks to Tsutomu Hirao for providing assistance with our reimplementation of the Tree Knapsack model, and thanks the anonymous reviewers for their helpful comments.  ... 
doi:10.18653/v1/p16-1188 dblp:conf/acl/DurrettBK16 fatcat:szc7xxo3cbeancsu4z3fgk3mhu

Single Document Summarization based on Nested Tree Structure

Yuta Kikuchi, Tsutomu Hirao, Hiroya Takamura, Manabu Okumura, Masaaki Nagata
2014 Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)  
Many methods of text summarization combining sentence selection and sentence compression have recently been proposed.  ...  The method of Filippova and Strube (2008) allows the model to extract non-rooted subtrees in sentence compression tasks that compress a single sentence with a given compression ratio.  ...  Constraints (6)-(10) allow the model to extract subtrees that have an arbitrary root node. Constraint (6) guarantees that there is only one root per selected sentence.  ... 
doi:10.3115/v1/p14-2052 dblp:conf/acl/KikuchiHTON14 fatcat:phk6s34lefhtxjgtkxyi763a6u

Page 39 of Computational Linguistics Vol. 18, Issue 1 [page]

1992 Computational Linguistics  
It captures local tactic constraints by sheer force of numbers, but the more well-protected bastions of semantic, pragmatic, and discourse constraint and even morphological and global syntactic constraint  ...  The cross-entropy we report here is just the base two logarithm of the char- acter perplexity of a sample of text with respect to a language model.  ... 

Linguistic challenges in automatic summarization technology

Elke Diedrichsen
2017 Journal of Computer-Assisted Linguistic Research  
We will pay particular attention to current methods of sentence extraction and compression for single and multi-document summarization, as these applications are based on theories of syntax and discourse  ...  An abstraction-based summary can compress, fuse or paraphrase sections of the source document. As of today, most summarization systems are extractive.  ...  Clarke and Lapata use Centering Theory in their model for Sentence Compression with Discourse Constraints.  ... 
doi:10.4995/jclr.2017.7787 fatcat:xl2gzccpj5ft7dngtrztrkfrlu

Global Inference for Sentence Compression: An Integer Linear Programming Approach

J. Clarke, M. Lapata
2008 The Journal of Artificial Intelligence Research  
We show how previous formulations of sentence compression can be recast as ILPs and extend these models with novel global constraints.  ...  Our work views sentence compression as an optimization problem and uses integer linear programming (ILP) to infer globally optimal compressions in the presence of linguistically motivated constraints.  ...  , Sig: significance model, Sig+Constr: significance model with constraints, McD: McDonald's (2006) compression model, McD+Constr: McDonald's (2006) compression model with constraints).  ... 
doi:10.1613/jair.2433 fatcat:e54yv3mtcrfdrah75f5hx43g4i

Message size constraints on discourse planning in synchronous computer-mediated communication

Claude G. Čech, Sherri L. Condon
1998 Behavoir research methods, instruments & computers  
constraints on message size.  ...  Thus, the results also support a claim that size of the text window may result in different discourse management strategies and may influence an initial discourse-planning stage.  ...  to the schematic discourse-processing model presented earlier.  ... 
doi:10.3758/bf03200653 fatcat:rd6ydfazn5gfrhdpugtvtz65gm

Reluctant Paraphrase: Textual Restructuring under an Optimisation Model [article]

Mark Dras
1997 arXiv   pre-print
This paper develops a computational model of paraphrase under which text modification is carried out reluctantly; that is, there are external constraints, such as length or readability, on an otherwise  ...  , and a model incorporating mathematical optimisation techniques is outlined.  ...  text compression.  ... 
arXiv:cmp-lg/9707001v1 fatcat:tcvzvr6q4vfrlcwpttlqtftc2q

A utility framework for the automatic generation of audio-visual skims

Hari Sundaram, Lexing Xie, Shih-Fu Chang
2002 Proceedings of the tenth ACM international conference on Multimedia - MULTIMEDIA '02  
The user study results indicate that the optimal skims show statistically significant differences with other skims with compression rates up to 90%.  ...  There are three key aspects to our approach: (a) visual complexity and grammar, (b) robust audio segmentation and (c) an utility model for skim generation.  ...  We formulate the problem of skim generation in terms of utility maximization with constraints. We model the skim comprehensibility in terms of audio and video utility functions.  ... 
doi:10.1145/641007.641042 dblp:conf/mm/SundaramXC02 fatcat:bbsab3e7sve4vd5p3e46k5nkee

A utility framework for the automatic generation of audio-visual skims

Hari Sundaram, Lexing Xie, Shih-Fu Chang
2002 Proceedings of the tenth ACM international conference on Multimedia - MULTIMEDIA '02  
The user study results indicate that the optimal skims show statistically significant differences with other skims with compression rates up to 90%.  ...  There are three key aspects to our approach: (a) visual complexity and grammar, (b) robust audio segmentation and (c) an utility model for skim generation.  ...  We formulate the problem of skim generation in terms of utility maximization with constraints. We model the skim comprehensibility in terms of audio and video utility functions.  ... 
doi:10.1145/641039.641042 fatcat:why6imrphbcfxbud5qb5uonzgy

Page 262 of Behavior Research Methods Vol. 30, Issue 2 [page]

1998 Behavior Research Methods  
to the schematic discourse-processing model presented earlier.  ...  Similarly, the change in average message size from the 4-line condi¬ tion to the 18-line window condition, coupled with the similarity in proportions of discourse functions fitting the discourse plan schema  ... 

Semantic role based sentence compression

Fatemeh Pourgholamali, Mohsen Kahani
2012 2012 2nd International eConference on Computer and Knowledge Engineering (ICCKE)  
In this paper, a new unsupervised sentence compression method is proposed. Sentences are tagged with Part Of Speech tags and semantic role labels.  ...  Moreover, in the process of compression, other sentences in the context are taken into account. The approach is applied in the context of multi-document summarization.  ...  is repeated for all sentences in the discourse.  ... 
doi:10.1109/iccke.2012.6395380 fatcat:o2ovzozpybbznh5zjdve27iyy4

Linguistic coherence

Diane J. Litman
1986 Proceedings of the 24th annual meeting on Association for Computational Linguistics -  
Relationships are formulated as discourse plans, which allows their representation in terms of planning operators and their computation via a plan recognition process.  ...  Although the identification of sets of utterance relationships forms the basis for many theories of discourse, the formalization and recognition of such relationships has proven to be an extremely difficult  ...  System, add hobby role to Person, compress the concept Person, next edit step, edit plan).  ... 
doi:10.3115/981131.981161 dblp:conf/acl/Litman86 fatcat:rh3emddsvrbf7oer3zz3mug7bq

Agency, structure, institutions, discourse (ASID) in urban and regional development

Frank Moulaert, Bob Jessop, Abid Mehmood
2016 International Journal of Urban Sciences  
overall agency, structure, institutions, discourse (ASID) heuristic.  ...  The paper concludes with an eightfold typology of particular combinations of ASID features to guide analyses of socio-economic development in all its (dis-) junctural complexity. ARTICLE HISTORY  ...  Ontology The ASID model works with a multi-level critical realist ontology.  ... 
doi:10.1080/12265934.2016.1182054 fatcat:jlf4t5vrgjbdrnbxssnhem6jda
« Previous Showing results 1 — 15 out of 12,215 results