Papers by Gustavo Aguilar
Char2Subword: Extending the Subword Embedding Space Using Robust Character Compositionality (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Byte-pair encoding (BPE) is a ubiquitous algorithm in the tokenization process of language models but is only based on pre-training data statistics. |
| Approach: | They propose a character-based subword module that learns the subword embedding table in pre-trained language models like BERT. |
| Outcome: | The proposed method significantly improves the performance on the social media linguistic code-switching evaluation (LinCE) benchmark. |
Modeling Noisiness to Recognize Named Entities using Multitask Neural Networks on Social Media (N18-1)
Copied to clipboard
| Challenge: | Current approaches to Named Entity Recognition (NER) are effective in formal text, but they fail on informal text, where improper grammatical structures, spelling inconsistencies, and slang vocabulary prevail. |
| Approach: | They propose a multitask end-to-end bidirectional long short-term memory (BLSTM)-Conditional Random Field (CRF) network with two CRF classifiers and a feature extractor that transfers learning to a CRF for prediction. |
| Outcome: | The proposed models outperform the current state-of-the-art on the Workshop on Noisy User-generated Text 2017 dataset by 2.45% and 3.69%, establishing a more suitable approach for social media environments. |
From English to Code-Switching: Transfer Learning with Strong Morphological Clues (2020.acl-main)
Copied to clipboard
| Challenge: | Linguistic code-switching (CS) is an understudied area in natural language processing . lack of resources and annotated data makes it difficult to strive for progress in CS-related tasks. |
| Approach: | They propose a method to adapt monolingual models to code-switched text in various tasks . they transfer English knowledge from a pre-trained ELMo model to different code-paired languages . |
| Outcome: | The proposed method outperforms multilingual BERT and homologous CS-unaware models and provides state-of-the-art in CS tasks. |
LinCE: A Centralized Benchmark for Linguistic Code-switching Evaluation (2020.lrec-1)
Copied to clipboard
| Challenge: | Recent trends in NLP research have raised an interest in linguistic code-switching . however, many of these approaches are limited to a few language pairs and a specific domain . |
| Approach: | They propose a centralized benchmark for Linguistic Code-switching Evaluation that combines eleven corpora covering four different code-switch languages and four tasks. |
| Outcome: | The proposed benchmark provides a centralized benchmark and compares with other benchmarks in real-time. |
Self-Aware Feedback-Based Self-Learning in Large-Scale Conversational AI (2022.naacl-industry)
Copied to clipboard
| Challenge: | Large-scale conversational AI systems require constant update to adapt to changing customer behavior and trends . lack of self-awareness in feedback-based systems can cause degradation of performance . et al., e. alderman and scott k. d. argues that such systems are not scalable enough to sustain the rapid update pace of conversational systems. |
| Approach: | They propose a superposition-based model that reactively learns local-adaptive decision boundaries . they propose rewritings with a bi-variate beta setting to improve the model's performance . |
| Outcome: | The proposed model improves the PR-AUC by 27.45% and reduces relative defect reductions by 31.22% . the proposed model can adapt faster to changes in global preferences across a large number of customers . |
Data Augmentation for Cross-Domain Named Entity Recognition (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for named entity recognition focus on augmenting in-domain data in low-resource scenarios where annotated data is limited. |
| Approach: | They propose a neural architecture to transform data from high-resource to low-resourced domains by learning the patterns in the text that differentiate them. |
| Outcome: | The proposed approach improves on high-resource domain representations over high- and low-resourced domains. |
Multimodal and Multi-view Models for Emotion Recognition (P19-1)
Copied to clipboard
| Challenge: | combining lexical and acoustic information results in more robust and accurate models . combining both modalities may be a bottleneck in a deployment pipeline due to computational complexity or privacy constraints . |
| Approach: | They propose to combine acoustic and lexical information to provide a deployable acustic model . they use multimodal models and two attention mechanisms to assess the benefits of lexicals . |
| Outcome: | The proposed model outperforms the state-of-the-art on the USC-IEMOCAP dataset . it significantly surpasses models that have been exclusively trained with acoustic features . |
Multi-view Story Characterization from Movie Plot Synopses and Reviews (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for characterizing stories by generating tags from synopses suffer from coverage issues. |
| Approach: | They propose to use synopses and reviews to characterize stories by inferring attributes such as theme and style from written synopsis and reviews. |
| Outcome: | The proposed model improves over methods that only use synopses and reviews . it can extract a complementary set of story attributes from reviews without supervision . |