DE eng

Search in the Catalogues and Directories

Page: 1 2 3
Hits 1 – 20 of 60

1
Compositional Generalization Requires Compositional Parsers ...
BASE
Show details
2
Learning compositional structures for semantic graph parsing ...
BASE
Show details
3
Learning compositional structures for semantic graph parsing ...
BASE
Show details
4
Aligning Actions Across Recipe Graphs ...
BASE
Show details
5
Script Parsing with Hierarchical Sequence Modelling ...
BASE
Show details
6
Towards the extraction of cross-sentence relations through event extraction and entity coreference
Simova, Iliana. - : Saarländische Universitäts- und Landesbibliothek, 2021
Abstract: Cross-sentence relation extraction deals with the extraction of relations beyond the sentence boundary. This thesis focuses on two of the NLP tasks which are of importance to the successful extraction of cross-sentence relation mentions: event extraction and coreference resolution. The first part of the thesis focuses on addressing data sparsity issues in event extraction. We propose a self-training approach for obtaining additional labeled examples for the task. The process starts off with a Bi-LSTM event tagger trained on a small labeled data set which is used to discover new event instances in a large collection of unstructured text. The high confidence model predictions are selected to construct a data set of automatically-labeled training examples. We present several ways in which the resulting data set can be used for re-training the event tagger in conjunction with the initial labeled data. The best configuration achieves statistically significant improvement over the baseline on the ACE 2005 test set (macro-F1), as well as in a 10-fold cross validation (micro- and macro-F1) evaluation. Our error analysis reveals that the augmentation approach is especially beneficial for the classification of the most under-represented event types in the original data set. The second part of the thesis focuses on the problem of coreference resolution. While a certain level of precision can be reached by modeling surface information about entity mentions, their successful resolution often depends on semantic or world knowledge. This thesis investigates an unsupervised source of such knowledge, namely distributed word representations. We present several ways in which word embeddings can be utilized to extract features for a supervised coreference resolver. Our evaluation results and error analysis show that each of these features helps improve over the baseline coreference system’s performance, with a statistically significant improvement (CoNLL F1) achieved when the proposed features are used jointly. Moreover, all features lead to a reduction in the amount of precision errors in resolving references between common nouns, demonstrating that they successfully incorporate semantic information into the process.
Keyword: ddc:004; ddc:400
URL: http://nbn-resolving.org/urn:nbn:de:bsz:291--ds-352772
https://doi.org/10.22028/D291-35277
BASE
Hide details
7
Fast semantic parsing with well-typedness guarantees ...
BASE
Show details
8
Normalizing Compositional Structures Across Graphbanks ...
BASE
Show details
9
Predicting Coreference in Abstract Meaning Representations ...
BASE
Show details
10
Generating Instructions at Different Levels of Abstraction ...
BASE
Show details
11
Prediction, detection, and correction of misunderstandings in interactive tasks
Villalba, Martin Federico [Verfasser]; Koller, Alexander [Akademischer Betreuer]. - Saarbrücken : Saarländische Universitäts- und Landesbibliothek, 2019
DNB Subject Category Language
Show details
12
Methods for taking semantic graphs apart and putting them back together again
Groschwitz, Jonas. - : Saarländische Universitäts- und Landesbibliothek, 2019
BASE
Show details
13
Prediction, detection, and correction of misunderstandings in interactive tasks
Villalba, Martin Federico. - : Saarländische Universitäts- und Landesbibliothek, 2019
BASE
Show details
14
AMR Dependency Parsing with a Typed Semantic Algebra ...
BASE
Show details
15
Efficient techniques for parsing with tree automata
Groschwitz, Jonas; Koller, Alexander; Johnson, Mark. - : Red Hook, New York : Association for Computational Linguistics, 2016
BASE
Show details
16
Graph parsing with s-graph grammars
Groschwitz, Jonas; Koller, Alexander; Teichmann, Christoph. - : Red Hook, New York : Association for Computational Linguistics, 2015
BASE
Show details
17
Interactive generation of effective discourse in situated context : a planning-based approach
Garoufi, Konstantina [Verfasser]; Koller, Alexander [Akademischer Betreuer]. - Potsdam : Universitätsbibliothek der Universität Potsdam, 2013
DNB Subject Category Language
Show details
18
Report on the Second Second Challenge on Generating Instructions in Virtual Environments (GIVE-2.5)
In: 13th European Workshop on Natural Language Generation ; https://hal.inria.fr/inria-00636498 ; 13th European Workshop on Natural Language Generation, Sep 2011, Nancy, France (2011)
BASE
Show details
19
Automated planning for situated natural language generation
In: Association for Computational Linguistics. Proceedings of the conference. - Stroudsburg, Penn. : ACL 48 (2010) 2, 1573-1582
BLLDB
Show details
20
Learning script knowledge with web experiments
In: Association for Computational Linguistics. Proceedings of the conference. - Stroudsburg, Penn. : ACL 48 (2010) 2, 979-988
BLLDB
Show details

Page: 1 2 3

Catalogues
1
0
2
0
2
0
0
Bibliographies
12
0
0
0
0
0
0
0
1
Linked Open Data catalogues
0
Online resources
1
0
0
0
Open access documents
41
0
1
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern