@inproceedings{raman-etal-2022-transforming,
title = "Transforming Sequence Tagging Into A {S}eq2{S}eq Task",
author = "Raman, Karthik and
Naim, Iftekhar and
Chen, Jiecao and
Hashimoto, Kazuma and
Yalasangi, Kiran and
Srinivasan, Krishna",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.813",
doi = "10.18653/v1/2022.emnlp-main.813",
pages = "11856--11874",
abstract = "Pretrained, large, generative language models (LMs) have had great success in a wide range of sequence tagging and structured prediction tasks. Casting a sequence tagging task as a Seq2Seq one requires deciding the formats of the input and output sequences. However, we lack a principled understanding of the trade-offs associated with these formats (such as the effect on model accuracy, sequence length, multilingual generalization, hallucination). In this paper, we rigorously study different formats one could use for casting input text sentences and their output labels into the input and target (i.e., output) of a Seq2Seq model. Along the way, we introduce a new format, which we show to to be both simpler and more effective. Additionally the new format demonstrates significant gains in the multilingual settings {--} both zero-shot transfer learning and joint training. Lastly, we find that the new format is more robust and almost completely devoid of hallucination {--} an issue we find common in existing formats. With well over a 1000 experiments studying 14 different formats, over 7 diverse public benchmarks {--} including 3 multilingual datasets spanning 7 languages {--} we believe our findings provide a strong empirical basis in understanding how we should tackle sequence tagging tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="raman-etal-2022-transforming">
<titleInfo>
<title>Transforming Sequence Tagging Into A Seq2Seq Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Karthik</namePart>
<namePart type="family">Raman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iftekhar</namePart>
<namePart type="family">Naim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiecao</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazuma</namePart>
<namePart type="family">Hashimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kiran</namePart>
<namePart type="family">Yalasangi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krishna</namePart>
<namePart type="family">Srinivasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pretrained, large, generative language models (LMs) have had great success in a wide range of sequence tagging and structured prediction tasks. Casting a sequence tagging task as a Seq2Seq one requires deciding the formats of the input and output sequences. However, we lack a principled understanding of the trade-offs associated with these formats (such as the effect on model accuracy, sequence length, multilingual generalization, hallucination). In this paper, we rigorously study different formats one could use for casting input text sentences and their output labels into the input and target (i.e., output) of a Seq2Seq model. Along the way, we introduce a new format, which we show to to be both simpler and more effective. Additionally the new format demonstrates significant gains in the multilingual settings – both zero-shot transfer learning and joint training. Lastly, we find that the new format is more robust and almost completely devoid of hallucination – an issue we find common in existing formats. With well over a 1000 experiments studying 14 different formats, over 7 diverse public benchmarks – including 3 multilingual datasets spanning 7 languages – we believe our findings provide a strong empirical basis in understanding how we should tackle sequence tagging tasks.</abstract>
<identifier type="citekey">raman-etal-2022-transforming</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.813</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.813</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>11856</start>
<end>11874</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Transforming Sequence Tagging Into A Seq2Seq Task
%A Raman, Karthik
%A Naim, Iftekhar
%A Chen, Jiecao
%A Hashimoto, Kazuma
%A Yalasangi, Kiran
%A Srinivasan, Krishna
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F raman-etal-2022-transforming
%X Pretrained, large, generative language models (LMs) have had great success in a wide range of sequence tagging and structured prediction tasks. Casting a sequence tagging task as a Seq2Seq one requires deciding the formats of the input and output sequences. However, we lack a principled understanding of the trade-offs associated with these formats (such as the effect on model accuracy, sequence length, multilingual generalization, hallucination). In this paper, we rigorously study different formats one could use for casting input text sentences and their output labels into the input and target (i.e., output) of a Seq2Seq model. Along the way, we introduce a new format, which we show to to be both simpler and more effective. Additionally the new format demonstrates significant gains in the multilingual settings – both zero-shot transfer learning and joint training. Lastly, we find that the new format is more robust and almost completely devoid of hallucination – an issue we find common in existing formats. With well over a 1000 experiments studying 14 different formats, over 7 diverse public benchmarks – including 3 multilingual datasets spanning 7 languages – we believe our findings provide a strong empirical basis in understanding how we should tackle sequence tagging tasks.
%R 10.18653/v1/2022.emnlp-main.813
%U https://aclanthology.org/2022.emnlp-main.813
%U https://doi.org/10.18653/v1/2022.emnlp-main.813
%P 11856-11874
Markdown (Informal)
[Transforming Sequence Tagging Into A Seq2Seq Task](https://aclanthology.org/2022.emnlp-main.813) (Raman et al., EMNLP 2022)
ACL
- Karthik Raman, Iftekhar Naim, Jiecao Chen, Kazuma Hashimoto, Kiran Yalasangi, and Krishna Srinivasan. 2022. Transforming Sequence Tagging Into A Seq2Seq Task. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11856–11874, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.