@inproceedings{du-etal-2024-language,
title = "When is a Language Process a Language Model?",
author = "Du, Li and
Lee, Holden and
Eisner, Jason and
Cotterell, Ryan",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.659",
doi = "10.18653/v1/2024.findings-acl.659",
pages = "11083--11094",
abstract = "A language model may be viewed as a $\Sigma$-valued stochastic process for some alphabet $\Sigma$.However, in some pathological situations, such a stochastic process may {``}leak{''} probability mass onto the set of infinite strings and hence is not equivalent to the conventional view of a language model as a distribution over ordinary (finite) strings.Such ill-behaved language processes are referred to as *non-tight* in the literature.In this work, we study conditions of tightness through the lens of stochastic processes.In particular, by regarding the symbol as marking a stopping time and using results from martingale theory, we give characterizations of tightness that generalize our previous work [(Du et al. 2023)](https://arxiv.org/abs/2212.10502).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="du-etal-2024-language">
<titleInfo>
<title>When is a Language Process a Language Model?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Holden</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Eisner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A language model may be viewed as a Σ-valued stochastic process for some alphabet Σ.However, in some pathological situations, such a stochastic process may “leak” probability mass onto the set of infinite strings and hence is not equivalent to the conventional view of a language model as a distribution over ordinary (finite) strings.Such ill-behaved language processes are referred to as *non-tight* in the literature.In this work, we study conditions of tightness through the lens of stochastic processes.In particular, by regarding the symbol as marking a stopping time and using results from martingale theory, we give characterizations of tightness that generalize our previous work [(Du et al. 2023)](https://arxiv.org/abs/2212.10502).</abstract>
<identifier type="citekey">du-etal-2024-language</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.659</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.659</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>11083</start>
<end>11094</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When is a Language Process a Language Model?
%A Du, Li
%A Lee, Holden
%A Eisner, Jason
%A Cotterell, Ryan
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F du-etal-2024-language
%X A language model may be viewed as a Σ-valued stochastic process for some alphabet Σ.However, in some pathological situations, such a stochastic process may “leak” probability mass onto the set of infinite strings and hence is not equivalent to the conventional view of a language model as a distribution over ordinary (finite) strings.Such ill-behaved language processes are referred to as *non-tight* in the literature.In this work, we study conditions of tightness through the lens of stochastic processes.In particular, by regarding the symbol as marking a stopping time and using results from martingale theory, we give characterizations of tightness that generalize our previous work [(Du et al. 2023)](https://arxiv.org/abs/2212.10502).
%R 10.18653/v1/2024.findings-acl.659
%U https://aclanthology.org/2024.findings-acl.659
%U https://doi.org/10.18653/v1/2024.findings-acl.659
%P 11083-11094
Markdown (Informal)
[When is a Language Process a Language Model?](https://aclanthology.org/2024.findings-acl.659) (Du et al., Findings 2024)
ACL
- Li Du, Holden Lee, Jason Eisner, and Ryan Cotterell. 2024. When is a Language Process a Language Model?. In Findings of the Association for Computational Linguistics: ACL 2024, pages 11083–11094, Bangkok, Thailand. Association for Computational Linguistics.