Papers by Shiva Taslimipoor
Verbal Multiword Expressions for Identification of Metaphor (2020.acl-main)
Copied to clipboard
| Challenge: | Metaphor is a linguistic device in which a concept is expressed by mentioning another . Verbal MWEs are examples of non-literal language in which multiple words form a single unit of meaning. |
| Approach: | They propose to analyze the interplay between metaphor and multiword expressions processing by informing the model of the presence of MWEs. |
| Outcome: | The proposed architecture reach state-of-the-art on two established metaphor datasets. |
Prompting open-source and commercial language models for grammatical error correction of English learner text (2024.findings-acl)
Copied to clipboard
Christopher Davis, Andrew Caines, O Andersen, Shiva Taslimipoor, Helen Yannakoudakis, Zheng Yuan, Christopher Bryant, Marek Rei, Paula Buttery
| Challenge: | Recent advances in generative AI have enabled us to prompt large language models (LLMs) to produce texts which are fluent and grammatical. |
| Approach: | They evaluate model performance by measuring their performance on established benchmarks. |
| Outcome: | The proposed models outperform supervised English GEC models on fluency correction benchmarks and commercial LLMs on edit benchmarks. |
Bridging the Gap: Attending to Discontinuity in Identification of Multiword Expressions (N19-1)
Copied to clipboard
| Challenge: | Existing approaches to identify discontinuous multiword expressions are limited in dealing with discontinuous occurrences. |
| Approach: | They propose a method to tag Multiword Expressions using a language-independent deep learning architecture to target discontinuity. |
| Outcome: | The proposed model outperforms baseline models on a multilingual dataset and scores higher than baseline models. |
SeCoDa: Sense Complexity Dataset (2020.lrec-1)
Copied to clipboard
| Challenge: | Sense Complexity Dataset (SeCoDa) provides a corpus that is annotated jointly for word senses and word tokens. |
| Approach: | They propose to use a hierarchical sense annotation scheme that draws on information available in the Cambridge Advanced Learner's Dictionary to provide more coarse-grained senses than WordNet. |
| Outcome: | The Sense Complexity Dataset (SeCoDa) provides a corpus that is annotated jointly for complexity and word senses. |
Distractor Generation Using Generative and Discriminative Capabilities of Transformer-based Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Multiple Choice Questions (MCQs) are used to test language learners' comprehension and knowledge. |
| Approach: | They propose an automatic distractor generation approach which generates correct and incorrect answer options and then discriminates potential correct options from distractors. |
| Outcome: | The proposed approach outperforms previous models on multiple choice questions and reading comprehension questions. |
Multi-Class Grammatical Error Detection for Correction: A Tale of Two Systems (2021.emnlp-main)
Copied to clipboard
| Challenge: | a multi-class grammatical error detection system can be used to improve grammamatical errors correction (GEC) for English. |
| Approach: | They develop a multi-class grammatical error detection system based on pre-trained ELECTRA and extend it to multi-Class detection using different error type tagsets. |
| Outcome: | The proposed system outperforms previous systems on the BEA-test benchmark. |
CEPOC: The Cambridge Exams Publishing Open Cloze dataset (2022.lrec-1)
Copied to clipboard
| Challenge: | This paper presents the first dataset of open cloze tests for language learners at different proficiency levels. |
| Approach: | They present the Cambridge Exams Publishing Open Cloze (CEPOC) dataset . they perform a set of experiments on three tasks: gap filling, gap prediction, and CEFR text classification. |
| Outcome: | The results of the study are promising for a number of NLP tasks. |
Constructing Open Cloze Tests Using Generation and Discrimination Capabilities of Transformers (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing open cloze tests are laborious to design because they require a large number of variables to predict the distribution of words in a text passage. |
| Approach: | They propose a transformer-based model that exploits generation and discrimination capabilities to improve performance. |
| Outcome: | The proposed model outperforms previous work and baselines in 82% accuracy and can be used as a future benchmark. |