@inproceedings{eichel-schulte-im-walde-2024-multi,
title = "Multi-Task Learning with Adapters for Plausibility Prediction: Bridging the Gap or Falling into the Trenches?",
author = "Eichel, Annerose and
Schulte Im Walde, Sabine",
editor = "Tafreshi, Shabnam and
Akula, Arjun and
Sedoc, Jo{\~a}o and
Drozd, Aleksandr and
Rogers, Anna and
Rumshisky, Anna",
booktitle = "Proceedings of the Fifth Workshop on Insights from Negative Results in NLP",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.insights-1.18/",
doi = "10.18653/v1/2024.insights-1.18",
pages = "154--168",
abstract = "We present a multi-task learning approach to predicting semantic plausibility by leveraging 50+ adapters categorized into 17 tasks within an efficient training framework. Across four plausibility datasets in English of varying size and linguistic constructions, we compare how models provided with knowledge from a range of NLP tasks perform in contrast to models without external information. Our results show that plausibility prediction benefits from complementary knowledge (e.g., provided by syntactic tasks) are significant but non-substantial, while performance may be hurt when injecting knowledge from an unsuitable task. Similarly important, we find that knowledge transfer may be hindered by class imbalance, and demonstrate the positive yet minor effect of balancing training data, even at the expense of size."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eichel-schulte-im-walde-2024-multi">
<titleInfo>
<title>Multi-Task Learning with Adapters for Plausibility Prediction: Bridging the Gap or Falling into the Trenches?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Annerose</namePart>
<namePart type="family">Eichel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabine</namePart>
<namePart type="family">Schulte Im Walde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Insights from Negative Results in NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shabnam</namePart>
<namePart type="family">Tafreshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arjun</namePart>
<namePart type="family">Akula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksandr</namePart>
<namePart type="family">Drozd</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a multi-task learning approach to predicting semantic plausibility by leveraging 50+ adapters categorized into 17 tasks within an efficient training framework. Across four plausibility datasets in English of varying size and linguistic constructions, we compare how models provided with knowledge from a range of NLP tasks perform in contrast to models without external information. Our results show that plausibility prediction benefits from complementary knowledge (e.g., provided by syntactic tasks) are significant but non-substantial, while performance may be hurt when injecting knowledge from an unsuitable task. Similarly important, we find that knowledge transfer may be hindered by class imbalance, and demonstrate the positive yet minor effect of balancing training data, even at the expense of size.</abstract>
<identifier type="citekey">eichel-schulte-im-walde-2024-multi</identifier>
<identifier type="doi">10.18653/v1/2024.insights-1.18</identifier>
<location>
<url>https://aclanthology.org/2024.insights-1.18/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>154</start>
<end>168</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Task Learning with Adapters for Plausibility Prediction: Bridging the Gap or Falling into the Trenches?
%A Eichel, Annerose
%A Schulte Im Walde, Sabine
%Y Tafreshi, Shabnam
%Y Akula, Arjun
%Y Sedoc, João
%Y Drozd, Aleksandr
%Y Rogers, Anna
%Y Rumshisky, Anna
%S Proceedings of the Fifth Workshop on Insights from Negative Results in NLP
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F eichel-schulte-im-walde-2024-multi
%X We present a multi-task learning approach to predicting semantic plausibility by leveraging 50+ adapters categorized into 17 tasks within an efficient training framework. Across four plausibility datasets in English of varying size and linguistic constructions, we compare how models provided with knowledge from a range of NLP tasks perform in contrast to models without external information. Our results show that plausibility prediction benefits from complementary knowledge (e.g., provided by syntactic tasks) are significant but non-substantial, while performance may be hurt when injecting knowledge from an unsuitable task. Similarly important, we find that knowledge transfer may be hindered by class imbalance, and demonstrate the positive yet minor effect of balancing training data, even at the expense of size.
%R 10.18653/v1/2024.insights-1.18
%U https://aclanthology.org/2024.insights-1.18/
%U https://doi.org/10.18653/v1/2024.insights-1.18
%P 154-168
Markdown (Informal)
[Multi-Task Learning with Adapters for Plausibility Prediction: Bridging the Gap or Falling into the Trenches?](https://aclanthology.org/2024.insights-1.18/) (Eichel & Schulte Im Walde, insights 2024)
ACL