Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop
Text Classification through Glyph-aware Disentangled Character Embedding and Semantic Sub-character Augmentation (2020.aacl-srw)
Copied to clipboard
| Challenge: | a character-based text classification framework for non-alphabetic languages is proposed . glyphs are used to give visual meaning to characters, such as "" and "." |
| Approach: | They propose a character-based text classification framework for non-alphabetic languages . they propose glyph-aware disentangled character embeddings that are dimensionally independent . |
| Outcome: | The proposed framework improves the performance of Japanese text classification tasks . it provides embedding interpretability and performance competitively with the state-of-the-art model . |
Two-Headed Monster and Crossed Co-Attention Networks (2020.aacl-srw)
Copied to clipboard
| Challenge: | a new co-attentional neural structure is proposed for machine translation tasks . a higher-level and more abstract paradigm generalized from CCNs is proposed . |
| Approach: | They propose a paradigm that consists of two symmetric encoder modules and one decoder module connected with co-attention. |
| Outcome: | The proposed model outperforms the current Transformer model on translation tasks but the epoch time increases by circa 75%. |
Towards a Task-Agnostic Model of Difficulty Estimation for Supervised Learning Tasks (2020.aacl-srw)
Copied to clipboard
| Challenge: | Recent advances on natural language processing (NLP) benchmarks have been driven by increasingly sophisticated language models, which are pretrained on enormous amounts of data before use. |
| Approach: | They propose to develop a task-agnostic model for problem difficulty and apply it to the Stanford Natural Language Inference dataset. |
| Outcome: | The proposed model predicts how many annotators will answer a question correctly and then projectes the difficulty estimates onto the full SNLI train set to create the curriculum. |
A Siamese CNN Architecture for Learning Chinese Sentence Similarity (2020.aacl-srw)
Copied to clipboard
| Challenge: | a deep neural architecture is used to learn a semantic similarity metric between two sentences . traditional methods of learning sentence similarity are based on the word level, which may not be sufficient. |
| Approach: | They propose a deep neural architecture which uses siamese convolutional neural network sharing model parameters to learn a semantic similarity metric between two sentences. |
| Outcome: | The proposed architecture outperforms baselines in similarity metrics for Chinese sentences by 8.7 points. |
Automatic Classification of Students on Twitter Using Simple Profile Information (2020.aacl-srw)
Copied to clipboard
| Challenge: | Existing models for age classification of students and non-students are restrictive and require access to many tweets. |
| Approach: | They propose a model which uses 3 tweet-content features to classify users as students or non-students. |
| Outcome: | The proposed model achieves an accuracy of 88.1% and an F1 score of .704 compared to previous models, which require access to many user tweets. |
Towards Code-switched Classification Exploiting Constituent Language Resources (2020.aacl-srw)
Copied to clipboard
| Challenge: | Code-switching is a communicative phenomenon denoting a shift from one language to another within the same speech exchange. |
| Approach: | They propose to convert code-switched data into its constituent high resource languages for use in both monolingual and cross-lingual settings. |
| Outcome: | The proposed code-switching language can be used for multiple downstream tasks . the proposed language increases the F1 score by 22% and 42.5% compared to the state-of-the-art. |
Hindi History Note Generation with Unsupervised Extractive Summarization (2020.aacl-srw)
Copied to clipboard
| Challenge: | Existing methods to extract summaries from Hindi textbooks perform poorly in English. |
| Approach: | They propose to use unsupervised methods to extract single document summarization from Hindi history textbooks. |
| Outcome: | The proposed tool could help students memorize a text summary for the exam . prior studies show that the proposed methods perform poorly on Hindi documents . |
Unbiasing Review Ratings with Tendency Based Collaborative Filtering (2020.aacl-srw)
Copied to clipboard
| Challenge: | Existing models for rating prediction neglect rating bias due to personal user bias preferences. |
| Approach: | They propose a tendency-based approach that models the user and item tendency for score prediction along with text review analysis with respect to ratings. |
| Outcome: | The proposed model minimizes the user and item tendency for score prediction along with text review analysis with respect to ratings. |
Building a Part-of-Speech Tagged Corpus for Drenjongke (Bhutia) (2020.aacl-srw)
Copied to clipboard
| Challenge: | a corpus of sentences and 1379 tokens were generated for the first Drenjongke corpus . the language is considered "vulnerable," "definitely endangered" and "severely endangered." |
| Approach: | They propose to generate the first corpus of the Tibetan language using a phrase book . they propose to use 34 Part-of-Speech (PoS) tags to define the first Drenjongke corpus . |
| Outcome: | The first corpus of the Drenjongke language comprises 275 sentences and 1379 tokens . the paper plans to expand with other materials to promote further studies of the language . |
Towards a Standardized Dataset on Indonesian Named Entity Recognition (2020.aacl-srw)
Copied to clipboard
| Challenge: | Named entity recognition (NER) tasks in the Indonesian language are still lacking data for the majority of languages, including Indonesian. |
| Approach: | They re-annotated an open dataset with 2,000 sentences and compared the results with a bidirectional long short-term memory and conditional random field approach. |
| Outcome: | The proposed approach improved the prediction score and consistent organization tag for the Indonesian language. |
Formal Sanskrit Syntax: A Specification for Programming Language (2020.aacl-srw)
Copied to clipboard
| Challenge: | a doctoral thesis examines the syntax of the primary statements of the Sanskritam programming language . the specification is based on the syntax used in generic Sanskrt . |
| Approach: | They propose a programming language specification based on natural Sanskrit . they use a natural language-based syntax similar to those of generic Sanskriti . |
| Outcome: | The proposed language is based on the natural Sanskrit language . the proposed language has 6 common statements . |
Resource Creation and Evaluation of Aspect Based Sentiment Analysis in Urdu (2020.aacl-srw)
Copied to clipboard
| Challenge: | Recent work on ABSA in Urdu language has limitations. |
| Approach: | They propose to create a dataset for Aspect Based Sentiment Analysis in Urdu language which will support multiple aspects. |
| Outcome: | The proposed dataset will provide a baseline evaluation for ABSA systems in Urdu language. |
Making a Point: Pointer-Generator Transformers for Disjoint Vocabularies (2020.aacl-srw)
Copied to clipboard
| Challenge: | Existing neural models rely on an overlap between source and target vocabularies to perform sequence-to-sequence tasks. |
| Approach: | They propose a pointer-generator transformer model for disjoint vocabularies that does not rely on an overlap between source and target vocs. |
| Outcome: | The proposed model outperforms a standard pointer-generator transformer by an average of 5.1 WER over 15 languages. |
Training with Adversaries to Improve Faithfulness of Attention in Neural Machine Translation (2020.aacl-srw)
Copied to clipboard
| Challenge: | Existing approaches to measure faithfulness of neural machine translation models are based on stress tests and a novel objective that rewards faithful behaviour by the model through probability divergence. |
| Approach: | They propose a measure of faithfulness for neural machine translation models based on stress tests and measuring faithfulness based upon how often the model output changes. |
| Outcome: | The proposed objective increases faithfulness without reducing translation quality and can even improve translation quality in some cases. |
Document-Level Neural Machine Translation Using BERT as Context Encoder (2020.aacl-srw)
Copied to clipboard
| Challenge: | Large-scale pre-trained representations such as BERT have been widely used in many natural language understanding tasks. |
| Approach: | They propose to use BERT as a context encoder to achieve document-level contextual information, which is then integrated into both the encoder and decoder. |
| Outcome: | The proposed model outperforms strong document-level machine translation baselines on BLEU score and captures document- level context information to boost translation performance. |
A Review of Cross-Domain Text-to-SQL Models (2020.aacl-srw)
Copied to clipboard
| Challenge: | WikiSQL and Spider are cross-domain text-to-SQl datasets that have attracted much attention from the research community. |
| Approach: | They propose to divide top models into two paradigms and evaluate their models for schema linking, pretrained word embeddings, reasoning assistance modules. |
| Outcome: | The proposed models have over 90% execution accuracy, the authors show . the proposed models are more complex and more complex than the proposed ones . |
Multi-task Learning for Automated Essay Scoring with Sentiment Analysis (2020.aacl-srw)
Copied to clipboard
| Challenge: | Automated Essay Scoring (AES) is a process that aims to alleviate the workload of graders and improve the feedback cycle in educational systems. |
| Approach: | They propose to combine two tasks, sentiment analysis and AES by utilizing multi-task learning to combine sentiment features extracted from opinion expressions. |
| Outcome: | The proposed model produces a QWK of 0.763 on the Automated StudentAssessment Prize (ASAP) benchmark. |
Aspect Extraction Using Coreference Resolution and Unsupervised Filtering (2020.aacl-srw)
Copied to clipboard
| Challenge: | Existing approaches to extract aspects from text are supervised and unsupervised . experimental results show that unsupervised approaches are more accurate than supervised ones . |
| Approach: | They propose to combine a lexical rule-based approach with coreference resolution to improve accuracy. |
| Outcome: | The proposed approach outperforms baseline methods on two benchmark datasets. |
GRUBERT: A GRU-Based Method to Fuse BERT Hidden Layers for Twitter Sentiment Analysis (2020.aacl-srw)
Copied to clipboard
| Challenge: | GRUBERT learns to map the different BERT hidden layers to fused embeddings . aims to achieve high accuracy on Twitter sentiment analysis task . |
| Approach: | They propose a GRU-based architecture that learns to map BERT hidden layers to fused embeddings to capture tweets' full extent. |
| Outcome: | The proposed method outperforms well-known embeddings and heuristics on Twitter sentiment analysis. |
Exploring Statistical and Neural Models for Noun Ellipsis Detection and Resolution in English (2020.aacl-srw)
Copied to clipboard
| Challenge: | Existing approaches to noun ellipsis resolution have been sparse, using syntactic feature constraints for marking licensors and selecting their antecedents. |
| Approach: | They propose to use supervised machine learning to improve the existing F1 score by 16.55% and resolution by 14.97% for noun ellipsis subtasks. |
| Outcome: | The proposed framework improves the existing F1 score by 16.55% and the resolution subtask by 14.97%. |
MRC Examples Answerable by BERT without a Question Are Less Effective in MRC Model Training (2020.aacl-srw)
Copied to clipboard
| Challenge: | Existing models for Machine Reading Comprehension (MRC) are unable to predict answers from a question and its related context. |
| Approach: | They propose a method that splits the training examples into those that are “easy to answer” or “hard to answer”. |
| Outcome: | The proposed model outperforms the previous models on a large-scale English MRC dataset. |
Text Simplification with Reinforcement Learning Using Supervised Rewards on Grammaticality, Meaning Preservation, and Simplicity (2020.aacl-srw)
Copied to clipboard
| Challenge: | Existing studies in text-to-text generation do not align with human-perspectives for these perspectives. |
| Approach: | They propose to use BERT regressors fine-tuned for grammaticality, meaning preservation, and simplicity as reward estimators to optimize rewards for text simplification. |
| Outcome: | The proposed method achieves text simplification conforming to human-perspectives. |
Label Representations in Modeling Classification as Text Generation (2020.aacl-srw)
Copied to clipboard
| Challenge: | Existing methods for text generation use strings to represent labels . linguistic properties of labels do affect performance, though their results are limited to document retrieval. |
| Approach: | They investigate the effect of string representations on how effectively a model learns a task . they use four standard text classification tasks to model string representation . |
| Outcome: | The proposed model improves on four standard text classification tasks . the results are largely negative in the low data setting . |
Generating Inflectional Errors for Grammatical Error Correction in Hindi (2020.aacl-srw)
Copied to clipboard
| Challenge: | Automated grammatical error correction is a data-heavy task . indic languages have a relatively low amount of digitized content and complex morphology . |
| Approach: | They generate a corpus of inflectional errors for training neural networks to correct grammatical errors in Hindi. |
| Outcome: | The proposed model trains on a corpus of inflectional errors extracted from Wikipedia edits. |