Alert button
Picture for Rabih Zbib

Rabih Zbib

Alert button

Résumé Parsing as Hierarchical Sequence Labeling: An Empirical Study

Sep 13, 2023
Federico Retyk, Hermenegildo Fabregat, Juan Aizpuru, Mariana Taglio, Rabih Zbib

Figure 1 for Résumé Parsing as Hierarchical Sequence Labeling: An Empirical Study
Figure 2 for Résumé Parsing as Hierarchical Sequence Labeling: An Empirical Study
Figure 3 for Résumé Parsing as Hierarchical Sequence Labeling: An Empirical Study
Figure 4 for Résumé Parsing as Hierarchical Sequence Labeling: An Empirical Study

Extracting information from r\'esum\'es is typically formulated as a two-stage problem, where the document is first segmented into sections and then each section is processed individually to extract the target entities. Instead, we cast the whole problem as sequence labeling in two levels -- lines and tokens -- and study model architectures for solving both tasks simultaneously. We build high-quality r\'esum\'e parsing corpora in English, French, Chinese, Spanish, German, Portuguese, and Swedish. Based on these corpora, we present experimental results that demonstrate the effectiveness of the proposed models for the information extraction task, outperforming approaches introduced in previous work. We conduct an ablation study of the proposed architectures. We also analyze both model performance and resource efficiency, and describe the trade-offs for model deployment in the context of a production environment.

* RecSys in HR'23: The 3rd Workshop on Recommender Systems for Human Resources, in conjunction with the 17th ACM Conference on Recommender Systems, September 18--22, 2023, Singapore, Singapore 
Viaarxiv icon

Learning Job Titles Similarity from Noisy Skill Labels

Jul 01, 2022
Rabih Zbib, Lucas Lacasa Alvarez, Federico Retyk, Rus Poves, Juan Aizpuru, Hermenegildo Fabregat, Vaidotas Simkus, Emilia García-Casademont

Figure 1 for Learning Job Titles Similarity from Noisy Skill Labels
Figure 2 for Learning Job Titles Similarity from Noisy Skill Labels
Figure 3 for Learning Job Titles Similarity from Noisy Skill Labels
Figure 4 for Learning Job Titles Similarity from Noisy Skill Labels

Measuring semantic similarity between job titles is an essential functionality for automatic job recommendations. This task is usually approached using supervised learning techniques, which requires training data in the form of equivalent job title pairs. In this paper, we instead propose an unsupervised representation learning method for training a job title similarity model using noisy skill labels. We show that it is highly effective for tasks such as text ranking and job normalization.

Viaarxiv icon

Statistical Machine Translation Features with Multitask Tensor Networks

Jun 01, 2015
Hendra Setiawan, Zhongqiang Huang, Jacob Devlin, Thomas Lamar, Rabih Zbib, Richard Schwartz, John Makhoul

Figure 1 for Statistical Machine Translation Features with Multitask Tensor Networks
Figure 2 for Statistical Machine Translation Features with Multitask Tensor Networks
Figure 3 for Statistical Machine Translation Features with Multitask Tensor Networks
Figure 4 for Statistical Machine Translation Features with Multitask Tensor Networks

We present a three-pronged approach to improving Statistical Machine Translation (SMT), building on recent success in the application of neural networks to SMT. First, we propose new features based on neural networks to model various non-local translation phenomena. Second, we augment the architecture of the neural network with tensor layers that capture important higher-order interaction among the network units. Third, we apply multitask learning to estimate the neural network parameters jointly. Each of our proposed methods results in significant improvements that are complementary. The overall improvement is +2.7 and +1.8 BLEU points for Arabic-English and Chinese-English translation over a state-of-the-art system that already includes neural network features.

* 11 pages (9 content + 2 references), 2 figures, accepted to ACL 2015 as a long paper 
Viaarxiv icon