Papers by Marianna Apidianaki
Comparing Constraints for Taxonomic Organization (N18-1)
Copied to clipboard
| Challenge: | Using general ontologies and domain-specific ontology, taxonomies encode knowledge that is important for understanding systems. |
| Approach: | They propose to modify a non-transitive branching algorithm to explicitly incorporate synonymy into the taxonomy structure to give it a faster performance. |
| Outcome: | The proposed method outperforms the best transitive algorithm while giving comparable performance over a dataset of local taxonomies. |
SUM-QE: a BERT-based Summary Quality Estimation Model (D19-1)
Copied to clipboard
| Challenge: | SUM-QE is a quality estimation model for summarization that captures linguistic qualities that traditional evaluation metrics fail to capture. |
| Approach: | They propose a new quality estimation model based on BERT that addresses linguistic quality aspects that are only indirectly captured by content-based approaches to summary evaluation without comparison with human ratings. |
| Outcome: | The proposed model outperforms existing models on linguistic quality aspects that are only indirectly captured by content-based summarization evaluations without comparison with human ratings. |
BERT Knows Punta Cana is not just beautiful, it’s gorgeous: Ranking Scalar Adjectives with Contextualised Representations (2020.emnlp-main)
Copied to clipboard
| Challenge: | Adjectives describe positive properties of nouns but with different intensity. |
| Approach: | They propose a BERT-based approach to intensity detection for scalar adjectives by generating vectors directly from contextualised representations. |
| Outcome: | The proposed model outperforms static embeddings and previous models with dedicated resources on an Indirect Question Answering task. |
How Does Data Corruption Affect Natural Language Understanding Models? A Study on GLUE datasets (2022.starsem-1)
Copied to clipboard
| Challenge: | Existing studies on the performance of pre-trained language models on natural language understanding tasks have focused on the natural language inference and textual entailment tasks. |
| Approach: | They propose to use corrupted data to fine-tune pre-trained language models to assess their language understanding capabilities. |
| Outcome: | The proposed transformations can be applied to all but one NLU task and show that understanding the meaning of utterances is not required for high performance. |
Simplification Using Paraphrases and Context-Based Lexical Substitution (N18-1)
Copied to clipboard
| Challenge: | Lexical simplification involves identifying complex words or phrases that need to be simplified and suggesting simpler meaning-preserving substitutes. |
| Approach: | They propose a complex word identification model that exploits both lexical and contextual features and a word-embedding lexical substitution model to replace the detected complex words with simpler paraphrases. |
| Outcome: | The proposed model detects complex words with higher accuracy than other models and proposes good substitutes in context. |
I Spy a Metaphor: Large Language Models and Diffusion Models Co-Create Visual Metaphors (2023.findings-acl)
Copied to clipboard
Tuhin Chakrabarty, Arkadiy Saakyan, Olivia Winn, Artemis Panagopoulou, Yue Yang, Marianna Apidianaki, Smaranda Muresan
| Challenge: | Visual metaphors are powerful rhetorical devices used to communicate creative ideas through images. |
| Approach: | They propose to generate visual metaphors from linguistic metaphors by using large language models and Diffusion models. |
| Outcome: | The proposed task requires the ability to model implicit meaning and compositionality. |
Let’s Play Mono-Poly: BERT Can Reveal Words’ Polysemy Level and Partitionability into Senses (2021.tacl-1)
Copied to clipboard
| Challenge: | Pre-trained language models encode rich information about linguistic structure but their knowledge about lexical polysemy remains unclear. |
| Approach: | They propose a setup for analyzing lexical polysemy knowledge in pre-trained language models and multilingual BERT models by analyzing different sense distributions and controlling for parameters that are highly correlated with polysyntax. |
| Outcome: | The proposed model can be used to analyze lexical polysemy in English, French, Spanish, and Greek and in multilingual BERT. |
Is “My Favorite New Movie” My Favorite Movie? Probing the Understanding of Recursive Noun Phrases (2022.naacl-main)
Copied to clipboard
| Challenge: | Recursive noun phrases have interesting semantic properties, yet it is unknown whether language models have such knowledge. |
| Approach: | They propose a dataset of three textual inference tasks targeting recursive noun phrases . they show that such knowledge is learnable with appropriate data . |
| Outcome: | The proposed model achieves strong zero-shot performance on an extrinsic Harm Detection task. |
Complexity-Weighted Loss and Diverse Reranking for Sentence Simplification (N19-1)
Copied to clipboard
Reno Kriz, João Sedoc, Marianna Apidianaki, Carolina Zheng, Gaurav Kumar, Eleni Miltsakaki, Chris Callison-Burch
| Challenge: | Recent research has applied sequence-to-sequence (Seq2Sequen) models to text simplification . generic models tend to copy directly from the original sentence, resulting in outputs that are long and complex. |
| Approach: | They propose to incorporate word complexities into the loss function during training and generate a large set of diverse candidate simplifications at test time. |
| Outcome: | The proposed model can perform competitively with state-of-the-art systems while generating simpler sentences. |
Visualizing the Obvious: A Concreteness-based Ensemble Model for Noun Property Prediction (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Neural language models encode rich knowledge about entities and their relationships but common properties of nouns are difficult to extract because they are rarely explicitly stated in texts. |
| Approach: | They propose to extract perceptual properties from images and use them in an ensemble model to complement the information extracted from language models. |
| Outcome: | The proposed model improves noun property prediction compared to powerful text-based language models. |
Adjusting Interpretable Dimensions in Embedding Space with Human Judgments (2024.naacl-long)
Copied to clipboard
| Challenge: | Embedding spaces contain interpretable dimensions indicating gender, formality in style, or even object properties. |
| Approach: | They combine seed-based vectors with human ratings of where words fall along a specific dimension to evaluate on predicting object properties and stylistic properties. |
| Outcome: | The proposed model improves on seed-based vectors and human ratings on object properties and stylistic properties. |
Explanation-based Finetuning Makes Models More Robust to Spurious Cues (2023.acl-long)
Copied to clipboard
Josh Magnus Ludan, Yixuan Meng, Tai Nguyen, Saurabh Shah, Qing Lyu, Marianna Apidianaki, Chris Callison-Burch
| Challenge: | Large Language Models (LLMs) learn correlations between labels and features that are irrelevant to the task, leading to poor generalization on out-of-distribution data. |
| Approach: | They propose an explanation-based approach to fine tune large language models to generate a free-text explanation supporting their answer. |
| Outcome: | The proposed model is more robust against spurious cues in terms of accuracy drop across four classification tasks: ComVE (+1.2), CREAK (+9.1), e-SNLI (+5.4), and SBIC (+6.5). |
Learning Scalar Adjective Intensity from Paraphrases (D18-1)
Copied to clipboard
| Challenge: | Existing lexical resources do not include the relative intensities of adjectives. |
| Approach: | They propose a method to automatically learn relative intensity relation between scalar adjectives . they use a paraphrase-based method that assumes that a pair of adjectives is "really hot" a similar method is used to infer the polarity of indirect answers to "yes/no" questions . |
| Outcome: | The proposed method improves the quality of systems for ordering sets of scalar adjectives and inferring the polarity of indirect answers to "yes/no" questions. |
Latent Space Interpretation for Stylistic Analysis and Explainable Authorship Attribution (2025.coling-main)
Copied to clipboard
| Challenge: | Recent authorship attribution methods learn authorship representations of text in a latent, uninterpretable space, which hinders their usability in real-world applications. |
| Approach: | They propose a method for interpreting latent authorship representations by identifying representative points in the latent space and leveraging large language models to generate informative natural language descriptions of the writing style associated with each point. |
| Outcome: | The proposed method outperforms baseline methods on the authorship attribution task by +20% on average when aided with explanations from the method. |
Scalar Adjective Identification and Multilingual Ranking (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing studies on scalar adjective ranking have focused on English due to the availability of datasets for evaluation. |
| Approach: | They propose a binary classification task to examine the models’ ability to distinguish scalar from relational adjectives in English. |
| Outcome: | The proposed task compares the models' ability to distinguish scalar from relational adjectives in English using monolingual and multilingual models. |
Magnitude: A Fast, Efficient Universal Vector Embedding Utility Package (D18-2)
Copied to clipboard
| Challenge: | Magnitude is an open source Python package that performs common operations up to 6,000 times faster than Gensim. |
| Approach: | They present a Python tool for utilizing vector embeddings that performs common operations up to 6,000 times faster than Gensim. |
| Outcome: | The Magnitude package performs common operations up to 6,000 times faster than Gensim and introduces several novel features for improved robustness like out-of-vocabulary lookups. |
Automated Paraphrase Lattice Creation for HyTER Machine Translation Evaluation (N18-2)
Copied to clipboard
| Challenge: | Existing machine translation evaluation metrics use synonyms and paraphrases to reward meaning-equivalent but lexically divergent translations. |
| Approach: | They propose a machine translation evaluation metric which exploits reference translations enriched with meaning equivalent expressions. |
| Outcome: | The proposed metric achieves medium performance on large and noisier datasets . it is compared with the existing HyTER evaluation metric . |
StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples (2025.naacl-long)
Copied to clipboard
Ajay Patel, Jiacheng Zhu, Justin Qiu, Zachary Horvitz, Marianna Apidianaki, Kathleen McKeown, Chris Callison-Burch
| Challenge: | Existing methods for embedding text are limited by the imperfect nature of data acquired under such assumptions. |
| Approach: | They propose a new approach to training stronger content-independent style embeddings using a synthetic dataset of near-exact paraphrases with controlled style variations. |
| Outcome: | The proposed model outperforms existing methods in real-world benchmarks and outperformed leading style representations in downstream applications. |
mStyleDistance: Multilingual Style Embeddings and their Evaluation (2025.findings-acl)
Copied to clipboard
| Challenge: | Multilingual StyleDistance embeddings are useful for stylistic analysis and style transfer, but they only exist for English. |
| Approach: | They propose a method that can generate style embeddings in new languages using synthetic data and a contrastive loss. |
| Outcome: | The proposed method outperforms existing style embeddings on these benchmarks and generalizes well to unseen features and languages. |
Representation of Lexical Stylistic Features in Language Models’ Embedding Space (2023.starsem-1)
Copied to clipboard
| Challenge: | lexical stylistic notions such as complexity, formality, and figurativeness can be identified in pretrained Language Models . static embeddings encode these features more accurately at the level of words and phrases whereas contextualized LMs perform better on sentences. |
| Approach: | They propose to derive a vector representation for stylistic notions from seed pairs . they find that static embeddings encode stylistic features more accurately . |
| Outcome: | The proposed representations can be used to characterize new texts in terms of these dimensions using a small number of seed pairs. |