Papers by Ira Assent
Anchoring Fine-tuning of Sentence Transformer with Semantic Label Information for Efficient Truly Few-shot Classification (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for fewshot text classification require substantial computing power and data. |
| Approach: | They propose an efficient method to add task and label information to a sentence transformer model by contrastive learning and a triplet loss to enforce training instances to be closest to their own textual semantic label information. |
| Outcome: | The proposed method achieves strong performance in data-sparse scenarios compared to existing methods across SST-5, Emotion detection, and AG News data even with just two examples per class. |
Accelerated High-Quality Mutual-Information Based Word Clustering (2020.lrec-1)
Copied to clipboard
| Challenge: | Word clustering is a hard hierarchical clustering that uses short-range distributional information to construct clusters. |
| Approach: | They propose to use a hierarchical clustering algorithm with a fixed-width beam to build clusters that outperform other word representations. |
| Outcome: | The proposed method outperforms the original methods in the computation of hierarchical and flat clusters. |
A reproduction of Apple’s bi-directional LSTM models for language identification in short strings (2021.eacl-srw)
Copied to clipboard
| Challenge: | Language Identification is the task of identifying a document’s language. |
| Approach: | They propose to use bi-LSTMs to identify language on very short strings such as text message fragments to perform automatic spell check. |
| Outcome: | The proposed model outperforms open-source language identifiers and its language identification mistakes are due to confusion between related languages. |
Mind the Style Gap: Meta-Evaluation of Style and Attribute Transfer Metrics (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) make it easy to rewrite a text in any style, but they are not straightforward when evaluating content preservation. |
| Approach: | They propose a large meta-evaluation of metrics for evaluating style and attribute transfer, focusing on content preservation. |
| Outcome: | The proposed method achieves higher alignment with human judgements than prompting a model of a similar size as an autorater. |
Abbreviation Explorer - an interactive system for pre-evaluation of Unsupervised Abbreviation Disambiguation (N19-4)
Copied to clipboard
| Challenge: | Abbreviation Explorer helps to identify long-forms that are easily confused . it can also pinpoint likely causes such as limitations of normalization, language switching, or inconsistent typing. |
| Approach: | They propose a system that supports interactive exploration of abbreviations that are challenging for Unsupervised Abbreviation Disambiguation. |
| Outcome: | The proposed system can identify long-forms that are easily confused and pinpoint likely causes . it can also identify which long-terms would benefit from additional input text . the proposed rules can be easily applied to existing vector spaces to improve performance while avoiding the cost of retraining. |
Measuring and Benchmarking Large Language Models’ Capabilities to Generate Persuasive Language (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent studies have focused on specific domains or types of persuasion, but a general study has focused on how LLMs produce persuasive text. |
| Approach: | They construct a dataset to measure and benchmark the ability of Large Language Models (LLMs) to produce persuasive text. |
| Outcome: | The proposed model can be used to generate persuasive text across domains and domains. |
Abbreviation Expander - a Web-based System for Easy Reading of Technical Documents (C18-2)
Copied to clipboard
| Challenge: | Existing abbreviation expansion systems or tools require technical knowledge to set up . existing systems require strong assumptions and are limited in their usefulness . |
| Approach: | They propose a web-based system that automatically expands abbreviations and acronyms in a user provided document. |
| Outcome: | The proposed system expands abbreviations and acronyms automatically in a user provided document. |
Analysing Differences in Persuasive Language in LLM-Generated Text: Uncovering Stereotypical Gender Patterns (2026.findings-acl)
Copied to clipboard
| Challenge: | Prior work has shown that large language models can successfully persuade humans and amplify persuasive language. |
| Approach: | They propose a framework for evaluating how persuasive language generation is affected by recipient gender, sender intent, or output language. |
| Outcome: | The proposed framework varies persuasive language when the recipient gender is specified or when the sender intent is specified. |
A Real-World Data Resource of Complex Sensitive Sentences Based on Documents from the Monsanto Trial (2020.lrec-1)
Copied to clipboard
| Challenge: | Sensitive information detection is of great importance in a number of applications where unintended leaks of sensitive information may incur severe negative consequences. |
| Approach: | They propose to use a corpus of sentences to evaluate sensitive information detection approaches . they employ human annotations and automatically infer labels from domain experts . |
| Outcome: | The proposed models are based on a monsanto trial and are evaluated on sentence level. |
Quantifying the morphosyntactic content of Brown Clusters (N19-1)
Copied to clipboard
| Challenge: | Using corpora representing several language families, we show that word clusters are highly capable at distinguishing Parts of Speech. |
| Approach: | They propose to use Brown and Exchange word clusters to represent morphosyntactic information in NLP systems. |
| Outcome: | The proposed clusters are highly capable at distinguishing Parts of Speech and can be used to perform tasks dependent on morphosyntactic information. |