Effective token graph modeling using a novel labeling strategy for structured sentiment analysis

W Shi, F Li, J Li, H Fei, D Ji - arxiv preprint arxiv:2203.10796, 2022 - arxiv.org
The state-of-the-art model for structured sentiment analysis casts the task as a dependency
parsing problem, which has some limitations:(1) The label proportions for span prediction …

Operationalizing a national digital library: The case for a Norwegian transformer model

PE Kummervold, J De la Rosa, F Wetjen… - arxiv preprint arxiv …, 2021 - arxiv.org
In this work, we show the process of building a large-scale training set from digital and
digitized collections at a national library. The resulting Bidirectional Encoder …

Structured sentiment analysis as dependency graph parsing

J Barnes, R Kurtz, S Oepen, L Øvrelid… - arxiv preprint arxiv …, 2021 - arxiv.org
Structured sentiment analysis attempts to extract full opinion tuples from a text, but over time
this task has been subdivided into smaller and smaller sub-tasks, e, g,, target extraction or …

SemEval 2022 task 10: Structured sentiment analysis

J Barnes, L Oberlaender, E Troiano… - Proceedings of the …, 2022 - aclanthology.org
In this paper, we introduce the first SemEval shared task on Structured Sentiment Analysis,
for which participants are required to predict all sentiment graphs in a text, where a single …

Large-scale contextualised language modelling for Norwegian

A Kutuzov, J Barnes, E Velldal, L Øvrelid… - arxiv preprint arxiv …, 2021 - arxiv.org
We present the ongoing NorLM initiative to support the creation and use of very large
contextualised language models for Norwegian (and in principle other Nordic languages) …

skweak: Weak supervision made easy for NLP

P Lison, J Barnes, A Hubin - arxiv preprint arxiv:2104.09683, 2021 - arxiv.org
We present skweak, a versatile, Python-based software toolkit enabling NLP developers to
apply weak supervision to a wide range of NLP tasks. Weak supervision is an emerging …

NorBench--A Benchmark for Norwegian Language Models

D Samuel, A Kutuzov, S Touileb, E Velldal… - arxiv preprint arxiv …, 2023 - arxiv.org
We present NorBench: a streamlined suite of NLP tasks and probes for evaluating
Norwegian language models (LMs) on standardized data splits and evaluation metrics. We …

USSA: A unified table filling scheme for structured sentiment analysis

Z Zhai, H Chen, R Li, X Wang - … of the 61st Annual Meeting of the …, 2023 - aclanthology.org
Most previous studies on Structured Sentiment Analysis (SSA) have cast it as a problem of bi-
lexical dependency parsing, which cannot address issues of overlap and discontinuity …

Entity-level sentiment analysis (ELSA): An exploratory task survey

E Rønningstad, E Velldal, L Øvrelid - arxiv preprint arxiv:2304.14241, 2023 - arxiv.org
This paper explores the task of identifying the overall sentiment expressed towards volitional
entities (persons and organizations) in a document--what we refer to as Entity-Level …

Machamp at semeval-2022 tasks 2, 3, 4, 6, 10, 11, and 12: Multi-task multi-lingual learning for a pre-selected set of semantic datasets

R Van der Goot - Proceedings of the 16th International Workshop …, 2022 - aclanthology.org
Previous work on multi-task learning in Natural Language Processing (NLP)
oftenincorporated carefully selected tasks as well as carefully tuning ofarchitectures to share …