Results 121 to 130 of about 487 (158)
Some of the next articles are maybe not open access.

Multilingual Anaphora Resolution

Machine Translation, 1999
This paper presents a multilingual robust, knowledge-poor approach to resolving pronouns in technical manuals. This approach is a modification of the practical approach (Mitkov 1998a) and operates on texts pre-processed by a part-of-speech tagger. Input is checked against agreement and a number of antecedent indicators.
openaire   +2 more sources

Anaphora Resolution

2020
This chapter provides a theoretical background of anaphora and introduces the varieties of this pervasive linguistic phenomenon. Next, it defines the task of anaphora resolution and introduces it as a three-stage process: identification of anaphors, location of the candidates for antecedents, and the resolution algorithm.
openaire   +1 more source

Anaphora Resolution

2012
The article provides a theoretical background of anaphora and introduces the task of anaphora resolution. The importance of anaphora resolution in natural language parsing (NLP) is distinct, and early work and recent developments are outlined in this article. Finally, issues that need further attention are discussed.
openaire   +1 more source

Semantic Information in Anaphora Resolution

2002
Building a NLP system requires the adding of linguistic phenomena resolution. One of the most relevant tasks regarding to these phenomena is the coreference resolution. Coreference is defined as a semantic phenomenon and, therefore, apart from the morphological and syntactic information that is highly useful, adding semantic sources improves the ...
Rafael Muñoz 0001   +2 more
openaire   +1 more source

Anaphora Resolution Algorithm for Sanskrit

2010
This paper presents an algorithm, which identifies different types of pronominal and its antecedents in Sanskrit, an Indo-European language. The computational grammar implemented here uses very familiar concepts such as clause, subject, object etc., which are identified with the help of morphological information and concepts such as precede and follow.
Pravin Pralayankar, Sobha Lalitha Devi
openaire   +2 more sources

Anaphora Resolution in Tamil Novels

2014
We have presented a robust anaphora resolution system for Tamil, one of Indian languages belonging to Dravidian language family. We have used Conditional Random Fields (CRFs), a machine learning technique with linguistically motivated features. We have performed exhaustive experiments using data from different genres and domains and evaluated for ...
A. Akilandeswari, Sobha Lalitha Devi
openaire   +1 more source

The Mitkov Algorithm for Anaphora Resolution in Portuguese

2008
This paper reports on the use of the Mitkov's algorithm for resolution of third person pronouns in texts written in Brazilian Portuguese. A system for anaphora resolution was built that embeds most of the Mitkov's features. Some of his resolution factors were directly incorporated into the system; others had to be slightly modified for language ...
Amanda Rocha Chaves   +1 more
openaire   +3 more sources

Anaphora resolution in ExtrAns

2003
The true power of anaphora resolution algorithms can only be gauged when embedded into specific Natural Language Processing (NLP) applications. In this paper we report on the anaphora resolution module from ExtrAns, an answer extraction system. The anaphora resolution module is based on Lappin and Leass' original algorithm, which used McCord's Slot ...
Mollà Aliod, D   +4 more
openaire   +2 more sources

Belief Revision on Anaphora Resolution

2001
The aim of this article is to describe a new approach for solving anaphora problem. We focus on anaphora resolution by means of belief revision process.
openaire   +2 more sources

Evalita 2011: Anaphora Resolution Task

2013
This paper discusses the Anaphora Resolution task proposed as a track at the Evalita-2011 evaluation campaign for the Italian language. This task can be seen as a successor of the Evalita-2009 Local Entity Detection and Recognition (LEDR) track, expanding on the scope of addressed phenomena. The annotation guidelines have been designed to cover a large
Uryupina, Olga, Poesio, Massimo
openaire   +1 more source

Home - About - Disclaimer - Privacy