@inproceedings{rajaby-faghihi-kordjamshidi-2021-time,
title = "Time-Stamped Language Model: Teaching Language Models to Understand The Flow of Events",
author = "Rajaby Faghihi, Hossein and
Kordjamshidi, Parisa",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.362",
doi = "10.18653/v1/2021.naacl-main.362",
pages = "4560--4570",
abstract = "Tracking entities throughout a procedure described in a text is challenging due to the dynamic nature of the world described in the process. Firstly, we propose to formulate this task as a question answering problem. This enables us to use pre-trained transformer-based language models on other QA benchmarks by adapting those to the procedural text understanding. Secondly, since the transformer-based language models cannot encode the flow of events by themselves, we propose a Time-Stamped Language Model (TSLM) to encode event information in LMs architecture by introducing the timestamp encoding. Our model evaluated on the Propara dataset shows improvements on the published state-of-the-art results with a 3.1{\%} increase in F1 score. Moreover, our model yields better results on the location prediction task on the NPN-Cooking dataset. This result indicates that our approach is effective for procedural text understanding in general.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rajaby-faghihi-kordjamshidi-2021-time">
<titleInfo>
<title>Time-Stamped Language Model: Teaching Language Models to Understand The Flow of Events</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hossein</namePart>
<namePart type="family">Rajaby Faghihi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parisa</namePart>
<namePart type="family">Kordjamshidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</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>Tracking entities throughout a procedure described in a text is challenging due to the dynamic nature of the world described in the process. Firstly, we propose to formulate this task as a question answering problem. This enables us to use pre-trained transformer-based language models on other QA benchmarks by adapting those to the procedural text understanding. Secondly, since the transformer-based language models cannot encode the flow of events by themselves, we propose a Time-Stamped Language Model (TSLM) to encode event information in LMs architecture by introducing the timestamp encoding. Our model evaluated on the Propara dataset shows improvements on the published state-of-the-art results with a 3.1% increase in F1 score. Moreover, our model yields better results on the location prediction task on the NPN-Cooking dataset. This result indicates that our approach is effective for procedural text understanding in general.</abstract>
<identifier type="citekey">rajaby-faghihi-kordjamshidi-2021-time</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.362</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.362</url>
</location>
<part>
<date>2021-jun</date>
<extent unit="page">
<start>4560</start>
<end>4570</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Time-Stamped Language Model: Teaching Language Models to Understand The Flow of Events
%A Rajaby Faghihi, Hossein
%A Kordjamshidi, Parisa
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 jun
%I Association for Computational Linguistics
%C Online
%F rajaby-faghihi-kordjamshidi-2021-time
%X Tracking entities throughout a procedure described in a text is challenging due to the dynamic nature of the world described in the process. Firstly, we propose to formulate this task as a question answering problem. This enables us to use pre-trained transformer-based language models on other QA benchmarks by adapting those to the procedural text understanding. Secondly, since the transformer-based language models cannot encode the flow of events by themselves, we propose a Time-Stamped Language Model (TSLM) to encode event information in LMs architecture by introducing the timestamp encoding. Our model evaluated on the Propara dataset shows improvements on the published state-of-the-art results with a 3.1% increase in F1 score. Moreover, our model yields better results on the location prediction task on the NPN-Cooking dataset. This result indicates that our approach is effective for procedural text understanding in general.
%R 10.18653/v1/2021.naacl-main.362
%U https://aclanthology.org/2021.naacl-main.362
%U https://doi.org/10.18653/v1/2021.naacl-main.362
%P 4560-4570
Markdown (Informal)
[Time-Stamped Language Model: Teaching Language Models to Understand The Flow of Events](https://aclanthology.org/2021.naacl-main.362) (Rajaby Faghihi & Kordjamshidi, NAACL 2021)
ACL