Jak lépe rozpoznávat anaforické vztahy v češtině

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F07%3A00023097" target="_blank" >RIV/00216224:14330/07:00023097 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Enhancing Anaphora Resolution for Czech

Popis výsledku v původním jazyce

Resolution of anaphoric reference is one of the most important challenges in natural language processing (NLP). Functionality of most NLP systems crucially relies on an accurate mechanism for determining which expressions in the input refer to the same entity in the real world. The immense complexity of this issue has led the research community to adopt predominantly knowledge-poor methods, despite the fact that these are known to be incapable of solving this task reliably. This paper suggests several ways of extending such methods by further resources and mechanisms in order to arrive at a more adequate anaphora resolution procedure. First, the paper sketches how to exploit information about verb valencies or co-occurrence statistics to account for semantic plausibility of individual antecedent candidates. Further, several ways of adapting ML-based AR methods are suggested, so that they account for the structure of the AR task more closely.

Název v anglickém jazyce

Enhancing Anaphora Resolution for Czech

Popis výsledku anglicky

Resolution of anaphoric reference is one of the most important challenges in natural language processing (NLP). Functionality of most NLP systems crucially relies on an accurate mechanism for determining which expressions in the input refer to the same entity in the real world. The immense complexity of this issue has led the research community to adopt predominantly knowledge-poor methods, despite the fact that these are known to be incapable of solving this task reliably. This paper suggests several ways of extending such methods by further resources and mechanisms in order to arrive at a more adequate anaphora resolution procedure. First, the paper sketches how to exploit information about verb valencies or co-occurrence statistics to account for semantic plausibility of individual antecedent candidates. Further, several ways of adapting ML-based AR methods are suggested, so that they account for the structure of the AR task more closely.

Druh

D - Stať ve sborníku

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

<a href="/cs/project/LC536" target="_blank" >LC536: Centrum komputační lingvistiky</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2007

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

RASLAN 2007

ISBN

978-80-210-4471-5

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

57-62

Název nakladatele

Masarykova Univerzita

Místo vydání

Brno

Místo konání akce

Karlova Studánka

Datum konání akce

1. 1. 2007

Typ akce podle státní příslušnosti

CST - Celostátní akce

Kód UT WoS článku

—