Multi-Task Learning for Chemical Named Entity Recognition with Chemical Compound Paraphrasing

Watanabe, Taiki; Tamura, Akihiro; Ninomiya, Takashi; Makino, Takuya; Iwakura, Tomoya

doi:10.18653/v1/d19-1648

Cited by 18 publications

(11 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[137] transfers knowledge from a large opendomain corpus to the data-scarce medical domain for Chinese word segmentation by developing a parallel MTL architecture. HanPaNE [130] improves NER for chemical compounds by jointly training a chemical compound paraphrase model. [134] enhances Chinese semantic role labeling by adding a dependency parsing model and uses the output of dependency parsing as additional features.…”

Section: Auxiliary Mtlmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Task Learning in Natural Language Processing: An Overview

Chen¹,

Qiang²

2021

Preprint

View full text Add to dashboard Cite

Deep learning approaches have achieved great success in the field of Natural Language Processing (NLP). However, deep neural models often suffer from overfitting and data scarcity problems that are pervasive in NLP tasks. In recent years, Multi-Task Learning (MTL), which can leverage useful information of related tasks to achieve simultaneous performance improvement on multiple related tasks, has been used to handle these problems. In this paper, we give an overview of the use of MTL in NLP tasks. We first review MTL architectures used in NLP tasks and categorize them into four classes, including the parallel architecture, hierarchical architecture, modular architecture, and generative adversarial architecture. Then we present optimization techniques on loss construction, data sampling, and task scheduling to properly train a multi-task model. After presenting applications of MTL in a variety of NLP tasks, we introduce some benchmark datasets. Finally, we make a conclusion and discuss several possible research directions in this field.

show abstract

Section: Auxiliary Mtlmentioning

confidence: 99%

“…[116] uses hashtags to represent genres of tweet posts. [130] generates sentence pairs by replacing chemical named entities with their paraphrases in the PubChemDic database. Unicoder [49] uses translated text from the source language to fine-tune on the target language.…”

Section: Multi-label Datasetsmentioning

confidence: 99%

Multi-Task Learning in Natural Language Processing: An Overview

Chen¹,

Qiang²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The performance of BioNER models has been further improved with the introduction of multi-task learning on multiple biomedical corpora (Crichton et al, 2017;Yoon et al, 2019). Several works demonstrated the effectiveness of jointly learning the BioNER task and other biomedical NLP tasks Watanabe et al, 2019;Zhao et al, 2019;Peng et al, 2020b).…”

Section: Related Workmentioning

confidence: 99%

How Do Your Biomedical Named Entity Recognition Models Generalize to Novel Entities?

Kim,

Kang

2021

Preprint

View full text Add to dashboard Cite

The number of biomedical literature on new biomedical concepts is rapidly increasing, which necessitates a reliable biomedical named entity recognition (BioNER) model for identifying new and unseen entity mentions. However, it is questionable whether existing BioNER models can effectively handle them. In this work, we systematically analyze the three types of recognition abilities of BioNER models: memorization, synonym generalization, and concept generalization. We find that (1) BioNER models are overestimated in terms of their generalization ability, and (2) they tend to exploit dataset biases, which hinders the models' abilities to generalize. To enhance the generalizability, we present a simple debiasing method based on the data statistics. Our method consistently improves the generalizability of the state-of-the-art (SOTA) models on five benchmark datasets, allowing them to better perform on unseen entity mentions.

show abstract

“…The question of retrieving multiword named entities that may not have been lexicalised yet or that may have a different form compared to the lexicalised ones, is addressed in Nayel et al (2019) for the biomedical domain and in Watanabe et al (2019) for the chemical domain. Our study here also aims at showing how to detect INE that may not have been lexicalised and that may not be detected by traditional NER tools, but without focusing on specific domains such as the biomedical or chemical ones.…”

Section: Nermentioning

confidence: 99%

Indirectly Named Entity Recognition

Kauffmann

Rey

Atanassova

et al. 2021

J. Comp. Assist. Linguist. Res.

View full text Add to dashboard Cite

We define here indirectly named entities, as a term to denote multiword expressions referring to known named entities by means of periphrasis. While named entity recognition is a classical task in natural language processing, little attention has been paid to indirectly named entities and their treatment. In this paper, we try to address this gap, describing issues related to the detection and understanding of indirectly named entities in texts. We introduce a proof of concept for retrieving both lexicalised and non-lexicalised indirectly named entities in French texts. We also show example cases where this proof of concept is applied, and discuss future perspectives. We have initiated the creation of a first lexicon of 712 indirectly named entity entries that is available for future research.

show abstract

Multi-Task Learning for Chemical Named Entity Recognition with Chemical Compound Paraphrasing

Cited by 18 publications

References 20 publications

Multi-Task Learning in Natural Language Processing: An Overview

Multi-Task Learning in Natural Language Processing: An Overview

How Do Your Biomedical Named Entity Recognition Models Generalize to Novel Entities?

Indirectly Named Entity Recognition

Contact Info

Product

Resources

About