<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="volpi-malago-2020-evaluating">
    <titleInfo>
        <title>Evaluating Natural Alpha Embeddings on Intrinsic and Extrinsic Tasks</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Riccardo</namePart>
        <namePart type="family">Volpi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Luigi</namePart>
        <namePart type="family">Malagò</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-jul</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 5th Workshop on Representation Learning for NLP</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Skip-Gram is a simple, but effective, model to learn a word embedding mapping by estimating a conditional probability distribution for each word of the dictionary. In the context of Information Geometry, these distributions form a Riemannian statistical manifold, where word embeddings are interpreted as vectors in the tangent bundle of the manifold. In this paper we show how the choice of the geometry on the manifold allows impacts on the performances both on intrinsic and extrinsic tasks, in function of a deformation parameter alpha.</abstract>
    <identifier type="citekey">volpi-malago-2020-evaluating</identifier>
    <identifier type="doi">10.18653/v1/2020.repl4nlp-1.9</identifier>
    <location>
        <url>https://aclanthology.org/2020.repl4nlp-1.9</url>
    </location>
    <part>
        <date>2020-jul</date>
        <extent unit="page">
            <start>61</start>
            <end>71</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Evaluating Natural Alpha Embeddings on Intrinsic and Extrinsic Tasks
%A Volpi, Riccardo
%A Malagò, Luigi
%S Proceedings of the 5th Workshop on Representation Learning for NLP
%D 2020
%8 jul
%I Association for Computational Linguistics
%C Online
%F volpi-malago-2020-evaluating
%X Skip-Gram is a simple, but effective, model to learn a word embedding mapping by estimating a conditional probability distribution for each word of the dictionary. In the context of Information Geometry, these distributions form a Riemannian statistical manifold, where word embeddings are interpreted as vectors in the tangent bundle of the manifold. In this paper we show how the choice of the geometry on the manifold allows impacts on the performances both on intrinsic and extrinsic tasks, in function of a deformation parameter alpha.
%R 10.18653/v1/2020.repl4nlp-1.9
%U https://aclanthology.org/2020.repl4nlp-1.9
%U https://doi.org/10.18653/v1/2020.repl4nlp-1.9
%P 61-71

Markdown (Informal)

[Evaluating Natural Alpha Embeddings on Intrinsic and Extrinsic Tasks](https://aclanthology.org/2020.repl4nlp-1.9) (Volpi & Malagò, RepL4NLP 2020)

• Evaluating Natural Alpha Embeddings on Intrinsic and Extrinsic Tasks (Volpi & Malagò, RepL4NLP 2020)

ACL

• Riccardo Volpi and Luigi Malagò. 2020. Evaluating Natural Alpha Embeddings on Intrinsic and Extrinsic Tasks. In Proceedings of the 5th Workshop on Representation Learning for NLP, pages 61–71, Online. Association for Computational Linguistics.