2,493 Hits in 4.6 sec

Bootstrapping a Semantic Lexicon on Verb Similarities

Shaheen Syed, Marco Spruit, Melania Borit
2016 Proceedings of the 8th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management  
We present a bootstrapping algorithm to create a semantic lexicon from a list of seed words and a corpus that was mined from the web.  ...  We exploit extraction patterns to bootstrap the lexicon and use collocation statistics to dynamically score new lexicon entries.  ...  SAF21 is a project financed under the EU Horizon 2020 Marie Skłodowska-Curie (MSC) ITN -ETN programme (project 642080).  ... 
doi:10.5220/0006036901890196 dblp:conf/ic3k/SyedSB16 fatcat:2v4t5x5y5rc3zdy2kbdpc2sy4m

Automatically Creating a Lexicon of Verbal Polarity Shifters: Mono- and Cross-lingual Methods for German

Marc Schulder, Michael Wiegand, Josef Ruppenhofer
2018 Zenodo  
This lexicon was created by bootstrapping a sample of annotated verbs with a supervised classifier that uses a set of data- and resource-driven features.  ...  Polarity shifters are content words that can move the polarity of a phrase towards its opposite, such as the verb "abandon" in "abandon all hope".  ...  Acknowledgements The authors would like to thank Stephanie Köser for annotating the German gold standard lexicon presented in this paper.  ... 
doi:10.5281/zenodo.3365693 fatcat:nelik4ltwvel7m5q23awfe3lnm

Semantic relations in bilingual lexicons

Yves Peirsman, Sebastian Padó
2011 ACM Transactions on Speech and Language Processing  
The first one concerns the creation of these lexicons. We show that seed lexicons can be improved by adding a bootstrapping procedure that uses cross-lingual distributional similarity.  ...  It is generally based on translation lexicons, which corresponds to the implicit assumption that (cross-lingual) synonymy is the semantic relation of primary interest, even though other semantic relations  ...  Bootstrapping The bilingual space shown in Figure 1 (a) has one bottleneck: to compute crosslingual semantic similarity, it requires a set of bilingual word pairs as bilingual dimensions.  ... 
doi:10.1145/2050100.2050102 dblp:journals/tslp/PeirsmanP11 fatcat:676ne4gqdvdevn5ltv7wxulbdy

Towards Bootstrapping a Polarity Shifter Lexicon using Linguistic Features

Marc Schulder, Michael Wiegand, Josef Ruppenhofer, Benjamin Roth
2019 Zenodo  
We present a major step towards the creation of the first high-coverage lexicon of polarity shifters. In this work, we bootstrap a lexicon of verbs by exploiting various linguistic features.  ...  On a sample of manually annotated verbs we examine a variety of linguistic features for this task. Then we build a supervised classifier to increase coverage.  ...  Acknowledgements The authors would like to thank Stephanie Köser for annotating the verb lexicon presented in this paper.  ... 
doi:10.5281/zenodo.3365608 fatcat:jowb2c4rifgw5alogqsi24ftaa

Automatic generation of lexica for sentiment polarity shifters

Marc Schulder, Michael Wiegand, Josef Ruppenhofer
2020 Natural Language Engineering  
The created lexicon is evaluated both on a polarity shifter gold standard and on a polarity classification task.  ...  Our approach leverages a number of linguistic insights; while some features are based on textual patterns, others use semantic resources or syntactic relatedness.  ...  FrameNet collects words with similar semantic behavior in semantic frames.  ... 
doi:10.1017/s135132492000039x fatcat:jauqzbifwnfpteeykcuzpio2py

A Broad-Coverage Deep Semantic Lexicon for Verbs [article]

James Allen, Hannah An, Ritwik Bose, Will de Beaumont, Choh Man Teng
2020 arXiv   pre-print
Bootstrapping from a hand-built lexicon and ontology, new ontological concepts and lexical entries, together with semantic role preferences and entailment axioms, are automatically derived by combining  ...  Progress on deep language understanding is inhibited by the lack of a broad coverage lexicon that connects linguistic behavior to ontological concepts and axioms.  ...  We have developed Comprehensive OntoLogy and Lexicon In English (COLLIE), a new resource constructed by bootstrapping from an initial hand-built lexicon and ontology, and using a semantic parser to read  ... 
arXiv:2007.02670v1 fatcat:6xuv7r3sznfnhecajk6n3wvoty

Large-Scale Noun Compound Interpretation Using Bootstrapping and the Web as a Corpus [article]

Su Nam Kim, Preslav Nakov
2019 arXiv   pre-print
In evaluation, we found that having one compound noun fixed yields both a higher number of semantically interpreted NCs and improved accuracy due to stronger semantic restrictions.  ...  We employ bootstrapping and web statistics, and utilize the relationship between NCs and paraphrasing patterns to jointly extract NCs and such patterns in multiple alternating iterations.  ...  These new NCs were further filtered based on their semantic similarity with the original NC.  ... 
arXiv:1911.12085v1 fatcat:5ulzqr5fljhepngefb5ls5lzvy

No nouns, no verbs

David Barner, Alan Bale
2002 Lingua  
Based on a review of research in linguistics, neurolinguistics, and developmental psychology, we argue that dividing the lexicon into categories such as noun and verb offers no descriptive edge, and adds  ...  the bootstrapping problem in language acquisition (Pinker, S., 1982.  ...  Acknowledgements This research was supported in part by a grant from SSHRC Research Grant No. 410-1999-0902 (PI: J.D. Bobaljik).  ... 
doi:10.1016/s0024-3841(02)00050-5 fatcat:fz7rwzqd7fd45gxqcwybklikm4

The Unifying Theory of Bootstrapping: The Collaboration of Multiple Language Acquisition Mechanisms

Zequn Harry Song
2020 English Language Teaching and Linguistics Studies  
We contend that a unification of the current hypotheses (i.e., pragmatic, prosodic, semantic, and syntactic bootstrapping) is substantial for first-language acquisition, and that scientists should be wary  ...  What UG may comprise is debated: if semantics is innate, or syntax, or some other linguistic aspects. Moreover, no definitive evidence has surfaced to attest to its existence.  ...  A child learns verbs-at this stage, words for actions-in a similar fashion.  ... 
doi:10.22158/eltls.v2n4p16 fatcat:mu2krzclf5g5jh6hvlr774ntu4

Page 144 of Computational Linguistics Vol. 31, Issue 1 [page]

2005 Computational Linguistics  
For instance, if ratification of [_] is similar to ratify [_], we may infer that the verb ratify and the noun ratification are semantically related.  ...  In future work, we aim at extending the lexicon in order to increase the coverage of the parser. To do this, parsing and learning can be involved in a bootstrapping process.  ... 

Development of the Multilingual Semantic Annotation System

Scott Piao, Francesca Bianchi, Carmen Dayrell, Angela D'Egidio, Paul Rayson
2015 Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies  
based on a lexical semantic classification scheme.  ...  Our experiment demonstrates that it is feasible to rapidly develop prototype semantic annotation tools for new languages by automatically bootstrapping new semantic lexicons based on existing ones.  ...  Because a single semantic category tends to span similar POS categories, e.g. present/past/progressive tense of verbs, simplification of POS tagsets generally does not affect semantic annotation accuracy  ... 
doi:10.3115/v1/n15-1137 dblp:conf/naacl/PiaoBDDR15 fatcat:q23zmmwv5naulmrz7xw5t4kzm4

Acquisition of verb categories

Mark Steedman
1994 Lingua  
Its importance is enhanced by the recent tendency in theories of grammar to gravitate to a lexicalist position, and the role of verbs as the head of their clause.  ...  the basis of semantic and contextual cues remains strong.  ...  First, it demonstrates a practical technique that actually can be used to automatically build lexicons on the basis of large volumes of text.  ... 
doi:10.1016/0024-3841(94)90350-6 fatcat:6wdgqtnpuvhyrhoirtbxafxiqu

A bootstrapping approach to unsupervised detection of cue phrase variants

Rashid M. Abdalla, Simone Teufel
2006 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06  
It successfully excludes phrases which are different from the target semantics, but which look superficially similar. The method achieves 88% accuracy, outperforming standard bootstrapping approaches.  ...  We investigate the unsupervised detection of semi-fixed cue phrases such as "This paper proposes a novel approach. . . 1 " from unseen text, on the basis of only a handful of seed cue phrases with the  ...  Our approach for finding semantically similar variants in an unsupervised fashion relies on bootstrapping of seeds from within the cue phrase.  ... 
doi:10.3115/1220175.1220291 dblp:conf/acl/AbdallaT06 fatcat:plamailxj5bzdpwjcoqhxzc7eu

Lexical Acquisition for Opinion Inference: A Sense-Level Lexicon of Benefactive and Malefactive Events

Yoonjung Choi, Lingjia Deng, Janyce Wiebe
2014 Proceedings of the 5th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis  
Verbs may be ambiguous, in that some meanings may be benefactive and others may be malefactive or neither. Thus, we use WordNet to create a sense-level lexicon.  ...  This paper addresses creating a lexicon of such events, which would be helpful to infer opinions.  ...  WordNet Similarity 4 , is a facility that provides a variety of semantic similarity and relatedness measures based on information found in the Word-Net lexical database.  ... 
doi:10.3115/v1/w14-2618 dblp:conf/wassa/ChoiDW14 fatcat:cqiqtafibbbpbax4zwaq2wkqvi

Bilingual Lexicon Extraction from Arabic-English Parallel Corpora with a View to Machine Translation

Yasser Muhammad Naguib Sabtan
2016 Social Science Research Network  
These seeds are used as anchor points to resegment the parallel corpus in order to bootstrap the lexicon extraction process.  ...  Experimental results show that the accuracy of the extracted lexicons was improved after applying the bootstrapping techniques.  ...  Finally, the word ‫يبشر‬ yb$r is a lexically compressed verb. This means that the verb contains a number of semantic features that are compressed in a single lexical item.  ... 
doi:10.2139/ssrn.2795900 fatcat:ou6wut5nyrgyrmhik6vi23fzz4
« Previous Showing results 1 — 15 out of 2,493 results