Papers by Shiva Taslimipoor

8 papers
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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations