23 citations · 92 across the 17 of their papers we have counts for
22 papers
Learning Translations via Matrix Completion
Derry Wijaya, Brendan Callahan, John Hewitt +4
Bilingual Lexicon Induction is the task of learning word translations without bilingual parallel corpora. We model this task as a matrix completion problem, and present an effectiv…
Calibrating Large Language Models with Sample Consistency
Qing Lyu, Kumar Shridhar, Chaitanya Malaviya +6
Accurately gauging the confidence level of Large Language Models' (LLMs) predictions is pivotal for their reliable application. However, LLMs are often uncalibrated inherently and…
Explanation-based Finetuning Makes Models More Robust to Spurious Cues
Josh Magnus Ludan, Yixuan Meng, Tai Nguyen +4
Large Language Models (LLMs) are so powerful that they sometimes learn correlations between labels and features that are irrelevant to the task, leading to poor generalization on o…
Representation Of Lexical Stylistic Features In Language Models' Embedding Space
Qing Lyu, Marianna Apidianaki, Chris Callison-Burch
The representation space of pretrained Language Models (LMs) encodes rich information about words and their relationships (e.g., similarity, hypernymy, polysemy) as well as abstrac…
I Spy a Metaphor: Large Language Models and Diffusion Models Co-Create Visual Metaphors
Tuhin Chakrabarty, Arkadiy Saakyan, Olivia Winn +4
Visual metaphors are powerful rhetorical devices used to persuade or communicate creative ideas through images. Similar to linguistic metaphors, they convey meaning implicitly thro…
Faithful Chain-of-Thought Reasoning
Qing Lyu, Shreya Havaldar, Adam Stein +5
While Chain-of-Thought (CoT) prompting boosts Language Models' (LM) performance on a gamut of complex reasoning tasks, the generated reasoning chain does not necessarily reflect ho…
Visualizing the Obvious: A Concreteness-based Ensemble Model for Noun Property Prediction
Yue Yang, Artemis Panagopoulou, Marianna Apidianaki +2
Neural language models encode rich knowledge about entities and their relationships which can be extracted from their representations using probing. Common properties of nouns (e.g…
Towards Faithful Model Explanation in NLP: A Survey
Qing Lyu, Marianna Apidianaki, Chris Callison-Burch
End-to-end neural Natural Language Processing (NLP) models are notoriously difficult to understand. This has given rise to numerous efforts towards model explainability in recent y…
How Does Data Corruption Affect Natural Language Understanding Models? A Study on GLUE datasets
Aarne Talman, Marianna Apidianaki, Stergios Chatzikyriakidis +1
A central question in natural language understanding (NLU) research is whether high performance demonstrates the models' strong reasoning capabilities. We present an extensive seri…
Is "My Favorite New Movie" My Favorite Movie? Probing the Understanding of Recursive Noun Phrases
Qing Lyu, Hua Zheng, Daoxin Li +3
Recursive noun phrases (NPs) have interesting semantic properties. For example, "my favorite new movie" is not necessarily my favorite movie, whereas "my new favorite movie" is. Th…
ALL Dolphins Are Intelligent and SOME Are Friendly: Probing BERT for Nouns' Semantic Properties and their Prototypicality
Marianna Apidianaki, Aina Garí Soler
Large scale language models encode rich commonsense knowledge acquired through exposure to massive data during pre-training, but their understanding of entities and their semantic…
Scalar Adjective Identification and Multilingual Ranking
Aina Garí Soler, Marianna Apidianaki
The intensity relationship that holds between scalar adjectives (e.g., nice < great < wonderful) is highly relevant for natural language inference and common-sense reasoning. Previ…
Let's Play Mono-Poly: BERT Can Reveal Words' Polysemy Level and Partitionability into Senses
Aina Garí Soler, Marianna Apidianaki
Pre-trained language models (LMs) encode rich information about linguistic structure but their knowledge about lexical polysemy remains unclear. We propose a novel experimental set…
NLI Data Sanity Check: Assessing the Effect of Data Corruption on Model Performance
Aarne Talman, Marianna Apidianaki, Stergios Chatzikyriakidis +1
Pre-trained neural language models give high performance on natural language inference (NLI) tasks. But whether they actually understand the meaning of the processed sequences rema…
Simple-QE: Better Automatic Quality Estimation for Text Simplification
Reno Kriz, Marianna Apidianaki, Chris Callison-Burch
Text simplification systems generate versions of texts that are easier to understand for a broader audience. The quality of simplified texts is generally estimated using metrics th…
BERT Knows Punta Cana is not just beautiful, it's gorgeous: Ranking Scalar Adjectives with Contextualised Representations
Aina Garí Soler, Marianna Apidianaki
Adjectives like pretty, beautiful and gorgeous describe positive properties of the nouns they modify but with different intensity. These differences are important for natural langu…
MULTISEM at SemEval-2020 Task 3: Fine-tuning BERT for Lexical Meaning
Aina Garí Soler, Marianna Apidianaki
We present the MULTISEM systems submitted to SemEval 2020 Task 3: Graded Word Similarity in Context (GWSC). We experiment with injecting semantic knowledge into pre-trained BERT mo…
SumQE: a BERT-based Summary Quality Estimation Model
Stratos Xenouleas, Prodromos Malakasiotis, Marianna Apidianaki +1
We propose SumQE, a novel Quality Estimation model for summarization based on BERT. The model addresses linguistic quality aspects that are only indirectly captured by content-base…
Embedding Biomedical Ontologies by Jointly Encoding Network Structure and Textual Node Descriptors
Sotiris Kotitsas, Dimitris Pappas, Ion Androutsopoulos +2
Network Embedding (NE) methods, which map network nodes to low-dimensional feature vectors, have wide applications in network analysis and bioinformatics. Many existing NE methods…
Word Usage Similarity Estimation with Sentence Representations and Automatic Substitutes
Aina Garí Soler, Marianna Apidianaki, Alexandre Allauzen
Usage similarity estimation addresses the semantic proximity of word instances in different contexts. We apply contextualized (ELMo and BERT) word and sentence embeddings to this t…
Complexity-Weighted Loss and Diverse Reranking for Sentence Simplification
Reno Kriz, João Sedoc, Marianna Apidianaki +4
Sentence simplification is the task of rewriting texts so they are easier to understand. Recent research has applied sequence-to-sequence (Seq2Seq) models to this task, focusing la…
Magnitude: A Fast, Efficient Universal Vector Embedding Utility Package
Ajay Patel, Alexander Sands, Chris Callison-Burch +1
Vector space embedding models like word2vec, GloVe, fastText, and ELMo are extremely popular representations in natural language processing (NLP) applications. We present Magnitude…