A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
Nominal Compound Chain Extraction: A New Task for Semantic-enriched Lexical Chain
[article]
2020
arXiv
pre-print
In this paper, we introduce a novel task, Nominal Compound Chain Extraction (NCCE), extracting and clustering all the nominal compounds that share identical semantic topics. ...
In addition, we model the task as a two-stage prediction (i.e., compound extraction and chain detection), which is handled via a proposed joint framework. ...
To sufficiently exploit the richer semantic information into the lexical chain, in this paper, we propose a new task, named Nominal Compound Chain Extraction (NCCE). ...
arXiv:2009.09173v1
fatcat:s5hh62czm5bo5bcoktek4swg64
Information extraction from non-segmented text (on the material of weather forecast telegrams)
2000
Open research Areas in Information Retrieval
The presented work pursues the problem of text segmentation: a procedure for the recovery of text structure is proposed that results in a sequence of topically co herent text fragments suitable for semantic ...
Both the domain and sublanguage specific approach to text analysis and information extraction is proposed. Texts under consideration are weather forecast telegrams written in Russian. ...
The input chain is decomposed into a sequence of interre lated coherent text fragments (topical fragments), each being available for semantic analysis. ...
dblp:conf/riao/KononenkoKPZ00
fatcat:olaexfjlmbhu7bflh6tzpokvhm
Using Lexical and Encyclopedic Knowledge
[chapter]
2016
Anaphora Resolution
Semantic information is one of the indispensable ingredients that are necessary to raise the performance of anaphora resolution both for pronominal anaphors and for anaphoric definite descriptions beyond ...
In contrast to hard criteria such as binding and agreement constraints, however, the question of semantic constraints and preferences and its operationalization in a system that performs anaphora resolution ...
Using Semantic Compatibility Information for Nominal Resolution In the resolution of nominal coreference, Vieira and Poesio's [84] on a subset of the Penn Treebank texts and subsequent work using the ...
doi:10.1007/978-3-662-47909-4_14
dblp:series/tanlp/VersleyPP16
fatcat:xjwq7ae47zhwribgolaj42xlae
Extracting and Learning a Dependency-Enhanced Type Lexicon for Dutch
[article]
2019
arXiv
pre-print
An algorithm for the conversion of dependency-annotated sentences into type sequences is then implemented, populating the type logic with concrete, data-driven lexical types. ...
but enriched with decorations that aim to reduce its proof-theoretic complexity. ...
Concretely, for each lexical type assignment we need also provide a corresponding semantic assignment. ...
arXiv:1909.02955v2
fatcat:qjdwpjelcjgdnewx5wy2xofii4
Extracting Temporal and Causal Relations between Events
[article]
2016
arXiv
pre-print
Structured information resulting from temporal information processing is crucial for a variety of natural language processing tasks, for instance to generate timeline summarization of events from news ...
In this thesis we present a framework for an integrated temporal and causal relation extraction system. ...
SemEval-2007 Task 4 Classification of Semantic Relations between Nominals (Girju et al., 2007) gives access to a corpus containing nominal causal relations among others, as causality is one of the considered ...
arXiv:1604.08120v1
fatcat:fmd7z6hwyjhgphbrnc3mgpifde
Context Aware Ontology based Information Extraction
2012
International Conference on Management of Data
Ontology constructs such as classes, properties and relations are integral to pattern specification and provide a means for extracting entities and property values. ...
We have developed an ontology based information extraction system where property and relation name occurrences are used to identify domain entities using patterns written in terms of dependency relations ...
New business models are emerging that require highly dynamic configurations of supply chains. ...
dblp:conf/comad/ShahR12
fatcat:hj7ow7evbzeqpon4u3juf2yabq
Coreference Annotation Schema for an Inflectional Language
[chapter]
2013
Lecture Notes in Computer Science
Creating a coreference corpus for an inflectional and freeword-order language is a challenging task due to specific syntactic features largely ignored by existing annotation guidelines, such as the absence ...
This paper comments on the experience gained in preparation of such a resource for an ongoing project (CORE), aiming at creating tools for coreference resolution. ...
We also hope that the current work could help harmonize efforts aimed at creating similar corpora for a group of related languages and, in turn, testing new cross-lingual concepts such as coreference projection ...
doi:10.1007/978-3-642-37247-6_32
fatcat:w66m4swncjaurcftvxaxv2qcee
Automatic extraction of function–behaviour–state information from patents
2013
Advanced Engineering Informatics
Extracting technical and design information from a document whose aim is more legal than technical, and that is written using a specific jargon, is not a trivial task. ...
Patents contain a large quantity of technical information not available elsewhere and therefore very interesting for both academia and industry. ...
each source and for each task. ...
doi:10.1016/j.aei.2013.04.004
fatcat:3rtyn7w5lrfk5jvreikzy54tja
An Overview of Biomolecular Event Extraction from Scientific Documents
2015
Computational and Mathematical Methods in Medicine
Event extraction from biomedical literature has a broad range of applications, including support for information retrieval, knowledge summarization, and information extraction and discovery. ...
However, automatic event extraction is a challenging task due to the ambiguity and diversity of natural language and higher-level linguistic phenomena, such as speculations and negations, which occur in ...
Event enrichment: it is recognition of secondary arguments that further specify the events extracted in Task 1. Task 3. ...
doi:10.1155/2015/571381
pmid:26587051
pmcid:PMC4637451
fatcat:7vrwycaycvb3nbgbub4v57y2xa
Linguistic vs Encyclopaedic Knowledge. Classification of MWEs from Wikipedia Articles
2020
Cybernetics and Information Technologies
We look for a way to filter the Wikipedia MWEs in the effort of selecting the ones most beneficial to the enrichment of BTB-WN. ...
The task of expanding the BTB-WordNet with encyclopaedic knowledge is done by mapping its synsets to Wikipedia articles with many MWEs found in the articles and subjected to further analysis. ...
The task to build relations between linguistic and semantic resources and to use this kind of new data for generating knowledge graphs has proven to be beneficial for languages with less lexical resources ...
doi:10.2478/cait-2020-0051
fatcat:bqoay6xfu5eoxj5iqfbekz4xmq
Multilingual parsing and MWE detection
[chapter]
2019
Zenodo
(collocation identification and parsing), and in that of a subsequent task (machine translation). ...
Identifying multiword expressions (MWEs) in a sentence in order to ensure their proper processing in subsequent applications, like machine translation, and performing the syntactic analysis of the sentence ...
To help the linguist/lexicographer in the time-consuming task of inserting collocations, we have designed a collocation extraction tool (Seretan 2011) , dubbed FipsCo. ...
doi:10.5281/zenodo.2579047
fatcat:ameqxdptmbg3no4ap2m6aczp6a
Enriching Slovene Wordnet With Domain-Specific Terms
[chapter]
2017
Zenodo
In the next step we extract multi-word terms from the Slovene domain-specific corpus using a hybrid approach, and finally match the term candidates to existing wordnet synsets. ...
In the experiment described here we are using a large monolingual Slovene corpus of texts from the domain of informatics to harvest terminology from, and a parallel English-Slovene corpus and an online ...
expressions (MWE) are lexical units that include a range of linguistic phenomena, such as nominal compounds (e.g. blood vessel), phrasal verbs (e.g. put up), adverbial and prepositional locutions (e.g ...
doi:10.5281/zenodo.283489
fatcat:a7yazhvvyrg7lka2hnprqjo52m
Pielg: A Protein Interaction Extraction Systemusing A Link Grammar Parser From Biomedical Abstracts
2007
Zenodo
For further evaluation, the system is augmented with a graphical package (Cytoscape) for extracting protein interaction information from sequence databases. ...
This paper presents a Protein Interaction Extraction System using a Link Grammar Parser from biomedical abstracts (PIELG). ...
Semantic parsers for English language will be more useful and meaningful for the extraction tasks compared to syntactic parsers. ...
doi:10.5281/zenodo.1060042
fatcat:efclhqasszf5jljsfklqlvdpqy
Semantic Parsing for Textual Entailment
2015
Proceedings of the 14th International Conference on Parsing Technologies
In this paper we gauge the utility of general-purpose, open-domain semantic parsing for textual entailment recognition by combining graph-structured meaning representations with semantic technologies and ...
Our approach achieves high precision, and in two case studies we show that when reasoning over n-best analyses from the parser the performance of our system reaches stateof-the-art for rule-based textual ...
We extend the approach by enriching the graphs in a forward-chaining spirit using SWRL rules, and the Jena reasoner 1 . ...
doi:10.18653/v1/w15-2205
dblp:conf/iwpt/LienK15
fatcat:2pgq7lq2wzbm7g5pbgxyjvwvze
Autobank: a semi-automatic annotation tool for developing deep Minimalist Grammar treebanks
2017
Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics
The front end of the tool is a graphical user interface which facilitates the rapid development of a seed set of MG trees via manual reannotation of PTB preterminals with MG lexical categories. ...
This paper presents Autobank, a prototype tool for constructing a widecoverage Minimalist Grammar (MG) (Stabler, 1997) , and semi-automatically converting the Penn Treebank (PTB) into a deep Minimalist ...
Acknowledgements Many thanks to Ed Stabler for providing the initial inspiration for this project, and for his subsequent guidance and encouragement last summer. ...
doi:10.18653/v1/e17-3021
dblp:conf/eacl/Torr17
fatcat:lqalhewkkjeilepwvrixjoa2au
« Previous
Showing results 1 — 15 out of 1,117 results