Results 21 to 30 of about 121,704 (159)
Zero-Shot Cross-Lingual Transfer with Meta Learning
, 2020 Learning what to share between tasks has been a topic of great importance recently, as strategic sharing of knowledge has been shown to improve downstream task performance.
Augenstein, Isabelle +3 more
core +1 more source
British Educational Research Journal, EarlyView., 2023 Abstract Children's relationship with time in preschools is an under‐researched area. Young children rarely know how to measure time using a clock, but their experiences of time may contribute to understanding children's well‐being and debates about quality in preschools.
Kristín Dýrfjörð +3 more
wiley +1 more source
Comparing knowledge sources for nominal anaphora resolution [PDF]
, 2005 We compare two ways of obtaining lexical knowledge for antecedent selection in other-anaphora and definite noun phrase coreference. Specifically, we compare an algorithm that relies on links encoded in the manually created lexical hierarchy WordNet and
Markert, K., Nissim, M.
core +3 more sources
Characterizing the impact of geometric properties of word embeddings on task performance [PDF]
, 2019 Analysis of word embedding properties to inform their use in downstream NLP tasks has largely been studied by assessing nearest neighbors. However, geometric properties of the continuous feature space contribute directly to the use of embedding features ...
Ferhatosmanoglu, Hakan +4 more
core +4 more sources
, 2023 Current research in zero-shot translation is plagued by several issues such as high compute requirements, increased training time and off target translations. Proposed remedies often come at the cost of additional data or compute requirements. Pivot based neural machine translation is preferred over a single-encoder model for most settings despite the ...
Ebadulla, Danish +4 more
openaire +2 more sources
Compositional Vector Space Models for Knowledge Base Completion [PDF]
, 2015 Knowledge base (KB) completion adds new facts to a KB by making inferences from existing facts, for example by inferring with high likelihood nationality(X,Y) from bornIn(X,Y).
McCallum, Andrew +2 more
core +3 more sources
From Frequency to Meaning: Vector Space Models of Semantics [PDF]
, 2010 Computers understand very little of the meaning of human language. This profoundly limits our ability to give instructions to computers, the ability of computers to explain their actions to us, and the ability of computers to analyse and process text ...
Pantel, Patrick, Turney, Peter D.
core +2 more sources
PERFORMING ANAPHORA IN MODERN GREEK: A NEO-GRICEAN PRAGMATIC ANALYSIS [PDF]
, 2013 The paper addresses the problem of interpreting anaphoric NPs in Modern Greek. It includes a proposal of a novel analysis based on the systematic interaction of the neo- Gricean pragmatic principles of communication, which provides a neat and elegant ...
Anagnostopoulou +118 more
core +1 more source
Cross-Lingual Adaptation using Structural Correspondence Learning [PDF]
, 2010 Cross-lingual adaptation, a special case of domain adaptation, refers to the transfer of classification knowledge between two languages. In this article we describe an extension of Structural Correspondence Learning (SCL), a recently proposed algorithm ...
Prettenhofer, Peter, Stein, Benno
core +1 more source
Zero-shot Generative Linguistic Steganography
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)Generative linguistic steganography attempts to hide secret messages into covertext. Previous studies have generally focused on the statistical differences between the covertext and stegotext, however, ill-formed stegotext can readily be identified by humans.
Lin, Ke +3 more
openaire +2 more sources