Adversarial Multi-task Learning for Text Classification

Liu, Pengfei; Qiu, Xipeng; Huang, Xuanjing

doi:10.18653/v1/p17-1001

Cited by 517 publications

(478 citation statements)

References 21 publications

Supporting

Mentioning

472

Contrasting

Unclassified

Order By: Relevance

“…However we would like to extend the corpus to other domains than sales in order to i) validate the relevance of our model for other types of positions, ii) determine which competencies are common or not across jobs. In that sense, the use of multi-domain models (Liu, Qiu, and Huang 2017) could be of great help. Our model currently considers two labels ("hirable" and "not hirable").…”

Section: Discussionmentioning

confidence: 99%

HireNet: A Hierarchical Attention Model for the Automatic Analysis of Asynchronous Video Job Interviews

Hemamou

Felhi

Vandenbussche

et al. 2019

AAAI

View full text Add to dashboard Cite

New technologies drastically change recruitment techniques. Some research projects aim at designing interactive systems that help candidates practice job interviews. Other studies aim at the automatic detection of social signals (e.g. smile, turn of speech, etc...) in videos of job interviews. These studies are limited with respect to the number of interviews they process, but also by the fact that they only analyze simulated job interviews (e.g. students pretending to apply for a fake position). Asynchronous video interviewing tools have become mature products on the human resources market, and thus, a popular step in the recruitment process. As part of a project to help recruiters, we collected a corpus of more than 7000 candidates having asynchronous video job interviews for real positions and recording videos of themselves answering a set of questions. We propose a new hierarchical attention model called HireNet that aims at predicting the hirability of the candidates as evaluated by recruiters. In HireNet, an interview is considered as a sequence of questions and answers containing salient socials signals. Two contextual sources of information are modeled in HireNet: the words contained in the question and in the job position. Our model achieves better F1-scores than previous approaches for each modality (verbal content, audio and video). Results from early and late multimodal fusion suggest that more sophisticated fusion schemes are needed to improve on the monomodal results. Finally, some examples of moments captured by the attention mechanisms suggest our model could potentially be used to help finding key moments in an asynchronous job interview.

show abstract

Section: Discussionmentioning

confidence: 99%

HireNet: A Hierarchical Attention Model for the Automatic Analysis of Asynchronous Video Job Interviews

Hemamou

Felhi

Vandenbussche

et al. 2019

AAAI

View full text Add to dashboard Cite

show abstract

“…Multi-task learning for neural networks in general (Caruana, 1997) and within NLP specifically (Collobert and Weston, 2008;Luong et al, 2016) has been widely studied. Much of the recent work for NLP has centered on neural architecture design: e.g., ensuring only beneficial information is shared across tasks (Liu et al, 2017; or arranging tasks in linguistically-motivated hierarchies (Søgaard and Goldberg, 2016;Hashimoto et al, 2017;Sanh et al, 2019). These contributions are orthogonal to ours because we instead focus on the multi-task training algorithm.…”

Section: Related Workmentioning

confidence: 99%

BAM! Born-Again Multi-Task Networks for Natural Language Understanding

Clark¹,

Luong²,

Khandelwal³

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

188

170

View full text Add to dashboard Cite

It can be challenging to train multi-task neural networks that outperform or even match their single-task counterparts. To help address this, we propose using knowledge distillation where single-task models teach a multi-task model. We enhance this training with teacher annealing, a novel method that gradually transitions the model from distillation to supervised learning, helping the multi-task model surpass its single-task teachers. We evaluate our approach by multi-task fine-tuning BERT on the GLUE benchmark. Our method consistently improves over standard single-task and multi-task training.

show abstract

“…Our method concentrates on aspect-term level sentiment domain adaptation by separating the domain-specific aspect features. Bousmalis et al (2016) and Liu et al (2017) separate features into two subspaces by introducing constraints in the learned features. The difference is that our method is more fine-grained and utilizes the explicit aspect knowledge.…”

Section: Related Workmentioning

confidence: 99%

Domain-Invariant Feature Distillation for Cross-Domain Sentiment Classification

Hu¹,

Wu²,

Zhao³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

Cross-domain sentiment classification has drawn much attention in recent years. Most existing approaches focus on learning domaininvariant representations in both the source and target domains, while few of them pay attention to the domain-specific information. Despite the non-transferability of the domainspecific information, simultaneously learning domain-dependent representations can facilitate the learning of domain-invariant representations. In this paper, we focus on aspectlevel cross-domain sentiment classification, and propose to distill the domain-invariant sentiment features with the help of an orthogonal domain-dependent task, i.e. aspect detection, which is built on the aspects varying widely in different domains. We conduct extensive experiments on three public datasets and the experimental results demonstrate the effectiveness of our method.

show abstract

Adversarial Multi-task Learning for Text Classification

Cited by 517 publications

References 21 publications

HireNet: A Hierarchical Attention Model for the Automatic Analysis of Asynchronous Video Job Interviews

HireNet: A Hierarchical Attention Model for the Automatic Analysis of Asynchronous Video Job Interviews

BAM! Born-Again Multi-Task Networks for Natural Language Understanding

Domain-Invariant Feature Distillation for Cross-Domain Sentiment Classification

Contact Info

Product

Resources

About