Search Results - "Apidianaki, Marianna"

Let’s Play Mono - Poly : BERT Can Reveal Words’ Polysemy Level and Partitionability into Senses by Garí Soler, Aina, Apidianaki, Marianna

“…Pre-trained language models (LMs) encode rich information about linguistic structure but their knowledge about lexical polysemy remains unclear. We propose a…”
Get full text

From Word Types to Tokens and Back: A Survey of Approaches to Word Meaning Representation and Interpretation by Apidianaki, Marianna

“…Vector-based word representation paradigms situate lexical meaning at different levels of abstraction. Distributional and static embedding models generate a…”
Get full text

Towards Faithful Model Explanation in NLP: A Survey by Lyu, Qing, Apidianaki, Marianna, Callison-Burch, Chris

“…End-to-end neural Natural Language Processing (NLP) models are notoriously difficult to understand. This has given rise to numerous efforts towards model…”
Get full text

Language Learning, Representation, and Processing in Humans and Machines: Introduction to the Special Issue by Apidianaki, Marianna, Fourtassi, Abdellah, Padó, Sebastian

“…Abstract Large Language Models (LLMs) and humans acquire knowledge about language without direct supervision. LLMs do so by means of specific training…”
Get full text

Data-driven synset induction and disambiguation for wordnet development : LREC 2012: State of the Art in Resource Development and Evaluation by APIDIANAKI, Marianna, SAGOT, Benoît

Get full text

Data-driven synset induction and disambiguation for wordnet development by Apidianaki, Marianna, Sagot, Benoît

“…Automatic methods for wordnet development in languages other than English generally exploit information found in Princeton WordNet (PWN) and translations…”
Get full text

Adjusting Interpretable Dimensions in Embedding Space with Human Judgments by Erk, Katrin, Apidianaki, Marianna

“…Embedding spaces contain interpretable dimensions indicating gender, formality in style, or even object properties. This has been observed multiple times. Such…”
Get full text

Representation Of Lexical Stylistic Features In Language Models' Embedding Space by Lyu, Qing, Apidianaki, Marianna, Callison-Burch, Chris

“…The representation space of pretrained Language Models (LMs) encodes rich information about words and their relationships (e.g., similarity, hypernymy,…”
Get full text

ALL Dolphins Are Intelligent and SOME Are Friendly: Probing BERT for Nouns' Semantic Properties and their Prototypicality by Apidianaki, Marianna, Soler, Aina Garí

“…Large scale language models encode rich commonsense knowledge acquired through exposure to massive data during pre-training, but their understanding of…”
Get full text

Scalar Adjective Identification and Multilingual Ranking by Soler, Aina Garí, Apidianaki, Marianna

“…The intensity relationship that holds between scalar adjectives (e.g., nice < great < wonderful) is highly relevant for natural language inference and…”
Get full text

Let's Play Mono-Poly: BERT Can Reveal Words' Polysemy Level and Partitionability into Senses by Soler, Aina Garí, Apidianaki, Marianna

“…Pre-trained language models (LMs) encode rich information about linguistic structure but their knowledge about lexical polysemy remains unclear. We propose a…”
Get full text

Towards Faithful Model Explanation in NLP: A Survey by Lyu, Qing, Apidianaki, Marianna, Callison-Burch, Chris

“…End-to-end neural Natural Language Processing (NLP) models are notoriously difficult to understand. This has given rise to numerous efforts towards model…”
Get full text

BERT Knows Punta Cana is not just beautiful, it's gorgeous: Ranking Scalar Adjectives with Contextualised Representations by Soler, Aina Garí, Apidianaki, Marianna

“…Adjectives like pretty, beautiful and gorgeous describe positive properties of the nouns they modify but with different intensity. These differences are…”
Get full text

MULTISEM at SemEval-2020 Task 3: Fine-tuning BERT for Lexical Meaning by Soler, Aina Garí, Apidianaki, Marianna

“…We present the MULTISEM systems submitted to SemEval 2020 Task 3: Graded Word Similarity in Context (GWSC). We experiment with injecting semantic knowledge…”
Get full text

StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples by Patel, Ajay, Zhu, Jiacheng, Qiu, Justin, Horvitz, Zachary, Apidianaki, Marianna, McKeown, Kathleen, Callison-Burch, Chris

“…Style representations aim to embed texts with similar writing styles closely and texts with different styles far apart, regardless of content. However, the…”
Get full text

Latent Space Interpretation for Stylistic Analysis and Explainable Authorship Attribution by Alshomary, Milad, Ri, Narutatsu, Apidianaki, Marianna, Patel, Ajay, Muresan, Smaranda, McKeown, Kathleen

“…Recent state-of-the-art authorship attribution methods learn authorship representations of texts in a latent, non-interpretable space, hindering their…”
Get full text

Simple-QE: Better Automatic Quality Estimation for Text Simplification by Kriz, Reno, Apidianaki, Marianna, Callison-Burch, Chris

“…Text simplification systems generate versions of texts that are easier to understand for a broader audience. The quality of simplified texts is generally…”
Get full text

SemEval-2024 Shared Task 6: SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes by Mickus, Timothee, Zosa, Elaine, Vázquez, Raúl, Vahtola, Teemu, Tiedemann, Jörg, Segonne, Vincent, Raganato, Alessandro, Apidianaki, Marianna

“…This paper presents the results of the SHROOM, a shared task focused on detecting hallucinations: outputs from natural language generation (NLG) systems that…”
Get full text

How Does Data Corruption Affect Natural Language Understanding Models? A Study on GLUE datasets by Talman, Aarne, Apidianaki, Marianna, Chatzikyriakidis, Stergios, Tiedemann, Jörg

“…A central question in natural language understanding (NLU) research is whether high performance demonstrates the models' strong reasoning capabilities. We…”
Get full text

Learning Translations via Matrix Completion by Wijaya, Derry, Callahan, Brendan, Hewitt, John, Gao, Jie, Ling, Xiao, Apidianaki, Marianna, Callison-Burch, Chris

“…Volume: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Year: 2017, Pages: 1452-1463 Bilingual Lexicon Induction is the…”
Get full text