Neural Temporality Adaptation for Document Classification: Diachronic Word Embeddings and Domain Adaptation Models

Huang, Xiaolei; Paul, Michael J.

doi:10.18653/v1/p19-1403

Cited by 26 publications

(26 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Temporal information has also been used to improve named entity disambiguation on a data set of historical documents (Agarwal et al, 2018). Finally, Huang and Paul (2019) present a model that uses diachronic word embeddings combined with a method inspired by domain adaptation to improve document classification.…”

Section: Related Workmentioning

confidence: 99%

Temporally-Informed Analysis of Named Entity Recognition

Rijhwani¹,

Preoţiuc-Pietro²

2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

Natural language processing models often have to make predictions on text data that evolves over time as a result of changes in language use or the information described in the text. However, evaluation results on existing data sets are seldom reported by taking the timestamp of the document into account. We analyze and propose methods that make better use of temporally-diverse training data, with a focus on the task of named entity recognition. To support these experiments, we introduce a novel data set of English tweets annotated with named entities. 1 We empirically demonstrate the effect of temporal drift on performance, and how the temporal information of documents can be used to obtain better models compared to those that disregard temporal information. Our analysis gives insights into why this information is useful, in the hope of informing potential avenues of improvement for named entity recognition as well as other NLP tasks under similar experimental setups.

show abstract

Section: Related Workmentioning

confidence: 99%

Temporally-Informed Analysis of Named Entity Recognition

Rijhwani¹,

Preoţiuc-Pietro²

2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…Finally, our attempts at domain transfer are constrained. Namely, we do not invoke explicit domain adaptation methods (Peng and Dredze, 2017;Li et al, 2018;Huang and Paul, 2019). Moving forward, we plan to explore algorithmic strategies to mitigate the biases discovered in this study.…”

Section: Limitations and Future Workmentioning

confidence: 99%

Do Models of Mental Health Based on Social Media Data Generalize?

Harrigian¹,

Aguirre²,

Dredze³

2020

Findings of the Association for Computational Linguistics: EMNLP 2020

View full text Add to dashboard Cite

Proxy-based methods for annotating mental health status in social media have grown popular in computational research due to their ability to gather large training samples. However, an emerging body of literature has raised new concerns regarding the validity of these types of methods for use in clinical applications. To further understand the robustness of distantly supervised mental health models, we explore the generalization ability of machine learning classifiers trained to detect depression in individuals across multiple social media platforms. Our experiments not only reveal that substantial loss occurs when transferring between platforms, but also that there exist several unreliable confounding factors that may enable researchers to overestimate classification performance. Based on these results, we enumerate recommendations for future mental health dataset construction.

show abstract

“…For our experiments, we used the IMDB dataset (135,669 documents) [ 28 ], the Yelp-hotel dataset (34,961 documents) [ 29 ], the Yelp-rest dataset (178,239 documents) [ 29 ], and the Amazon dataset (83,159 documents) [ 29 ]. The IMDB dataset is a movie review dataset annotated with 10-scale polarities.…”

Section: Resultsmentioning

confidence: 99%

“…Table 2 lists data statistics of the four datasets. For fair comparison with the previous models, we encoded review scores of the Yelp-hotel dataset, the Yelp-rest dataset, and the Amazon dataset into three discrete categories (score >3 as positive, =3 as neutral, and <3 as negative) according to Huang and Paul's experimental settings [29].…”

Section: Datasets and Experimental Settingsmentioning

confidence: 99%

Improving Document-Level Sentiment Classification Using Importance of Sentences

Choi

Kim

2020

Entropy

View full text Add to dashboard Cite

Previous researchers have considered sentiment analysis as a document classification task, in which input documents are classified into predefined sentiment classes. Although there are sentences in a document that support important evidences for sentiment analysis and sentences that do not, they have treated the document as a bag of sentences. In other words, they have not considered the importance of each sentence in the document. To effectively determine polarity of a document, each sentence in the document should be dealt with different degrees of importance. To address this problem, we propose a document-level sentence classification model based on deep neural networks, in which the importance degrees of sentences in documents are automatically determined through gate mechanisms. To verify our new sentiment analysis model, we conducted experiments using the sentiment datasets in the four different domains such as movie reviews, hotel reviews, restaurant reviews, and music reviews. In the experiments, the proposed model outperformed previous state-of-the-art models that do not consider importance differences of sentences in a document. The experimental results show that the importance of sentences should be considered in a document-level sentiment classification task.

show abstract

Neural Temporality Adaptation for Document Classification: Diachronic Word Embeddings and Domain Adaptation Models

Cited by 26 publications

References 24 publications

Temporally-Informed Analysis of Named Entity Recognition

Temporally-Informed Analysis of Named Entity Recognition

Do Models of Mental Health Based on Social Media Data Generalize?

Improving Document-Level Sentiment Classification Using Importance of Sentences

Contact Info

Product

Resources

About