@inproceedings{yang-wan-2022-dependency,
title = "Dependency-based Mixture Language Models",
author = "Yang, Zhixian and
Wan, Xiaojun",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.535",
doi = "10.18653/v1/2022.acl-long.535",
pages = "7758--7773",
abstract = "Various models have been proposed to incorporate knowledge of syntactic structures into neural language models. However, previous works have relied heavily on elaborate components for a specific language model, usually recurrent neural network (RNN), which makes themselves unwieldy in practice to fit into other neural language models, such as Transformer and GPT-2. In this paper, we introduce the Dependency-based Mixture Language Models. In detail, we first train neural language models with a novel dependency modeling objective to learn the probability distribution of future dependent tokens given context. We then formulate the next-token probability by mixing the previous dependency modeling probability distributions with self-attention. Extensive experiments and human evaluations show that our method can be easily and effectively applied to different neural language models while improving neural text generation on various tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-wan-2022-dependency">
<titleInfo>
<title>Dependency-based Mixture Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhixian</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Various models have been proposed to incorporate knowledge of syntactic structures into neural language models. However, previous works have relied heavily on elaborate components for a specific language model, usually recurrent neural network (RNN), which makes themselves unwieldy in practice to fit into other neural language models, such as Transformer and GPT-2. In this paper, we introduce the Dependency-based Mixture Language Models. In detail, we first train neural language models with a novel dependency modeling objective to learn the probability distribution of future dependent tokens given context. We then formulate the next-token probability by mixing the previous dependency modeling probability distributions with self-attention. Extensive experiments and human evaluations show that our method can be easily and effectively applied to different neural language models while improving neural text generation on various tasks.</abstract>
<identifier type="citekey">yang-wan-2022-dependency</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.535</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.535</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>7758</start>
<end>7773</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dependency-based Mixture Language Models
%A Yang, Zhixian
%A Wan, Xiaojun
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F yang-wan-2022-dependency
%X Various models have been proposed to incorporate knowledge of syntactic structures into neural language models. However, previous works have relied heavily on elaborate components for a specific language model, usually recurrent neural network (RNN), which makes themselves unwieldy in practice to fit into other neural language models, such as Transformer and GPT-2. In this paper, we introduce the Dependency-based Mixture Language Models. In detail, we first train neural language models with a novel dependency modeling objective to learn the probability distribution of future dependent tokens given context. We then formulate the next-token probability by mixing the previous dependency modeling probability distributions with self-attention. Extensive experiments and human evaluations show that our method can be easily and effectively applied to different neural language models while improving neural text generation on various tasks.
%R 10.18653/v1/2022.acl-long.535
%U https://aclanthology.org/2022.acl-long.535
%U https://doi.org/10.18653/v1/2022.acl-long.535
%P 7758-7773
Markdown (Informal)
[Dependency-based Mixture Language Models](https://aclanthology.org/2022.acl-long.535) (Yang & Wan, ACL 2022)
ACL
- Zhixian Yang and Xiaojun Wan. 2022. Dependency-based Mixture Language Models. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7758–7773, Dublin, Ireland. Association for Computational Linguistics.