Search Results for author:
Found 31 papers, 14 papers with code
Individuation in Neural Models with and without Visual Grounding
We show differences between a language-and-vision model CLIP and two text-only models - FastText and SBERT - when it comes to the encoding of individuation information.
PLUGH: A Benchmark for Spatial Understanding and Reasoning in Large Language Models
We present PLUGH (https://www. urbandictionary. com/define. php? term=plugh), a modern benchmark that currently consists of 5 tasks, each with 125 input texts extracted from 48 different games and representing 61 different (non-isomorphic) spatial graphs to assess the abilities of Large Language Models (LLMs) for spatial understanding and reasoning.
Machine Apophenia: The Kaleidoscopic Generation of Architectural Images
This study investigates the application of generative artificial intelligence in architectural design.
Humor Mechanics: Advancing Humor Generation with Multistep Reasoning
In this paper, we explore the generation of one-liner jokes through multi-step reasoning.
Branching Narratives: Character Decision Points Detection
This paper presents the Character Decision Points Detection (CHADPOD) task, a task of identification of points within narratives where characters make decisions that may significantly influence the story's direction.
Knowledge Graph Representation for Political Information Sources
With the rise of computational social science, many scholars utilize data analysis and natural language processing tools to analyze social media, news articles, and other accessible data sources for examining political and social discourse.
Unrolling Virtual Worlds for Immersive Experiences
This research pioneers a method for generating immersive worlds, drawing inspiration from elements of vintage adventure games like Myst and employing modern text-to-image models.
Post Turing: Mapping the landscape of LLM Evaluation
In the rapidly evolving landscape of Large Language Models (LLMs), introduction of well-defined and standardized evaluation methodologies remains a crucial challenge.
BERT in Plutarch's Shadows
In particular, the Placita Philosophorum, together with one of the other Pseudo-Plutarch texts, shows similarities with the texts written by authors from an Alexandrian context (2nd/3rd century CE).
What is Wrong with Language Models that Can Not Tell a Story?
This paper argues that a deeper understanding of narrative and the successful generation of longer subjectively interesting texts is a vital bottleneck that hinders the progress in modern Natural Language Processing (NLP) and may even be in the whole field of Artificial Intelligence.
Good Classification Measures and How to Find Them
Several performance measures can be used for evaluating classification results: accuracy, F-measure, and many others.
Fine-Tuning Transformers: Vocabulary Transfer
Transformers are responsible for the vast majority of recent advances in natural language processing.
Actionable Entities Recognition Benchmark for Interactive Fiction
This paper presents a new natural language processing task - Actionable Entities Recognition (AER) - recognition of entities that protagonists could interact with for further plot development.
Connecting degree and polarity: An artificial language learning study
We investigate a new linguistic generalization in pre-trained language models (taking BERT (Devlin et al., 2019) as a case study).
Transformers in the loop: Polarity in neural models of language
Establishing this allows us to more adequately evaluate the performance of language models and also to use language models to discover new insights into natural language grammar beyond existing linguistic theories.
HeadlineCause: A Dataset of News Headlines for Detecting Causalities
In this work, we present HeadlineCause, a dataset for detecting implicit causal relations between pairs of news headlines.
EENLP: Cross-lingual Eastern European NLP Index
Motivated by the sparsity of NLP resources for Eastern European languages, we present a broad index of existing Eastern European language resources (90+ datasets and 45+ models) published as a github repository open for updates from the community.
DYPLODOC: Dynamic Plots for Document Classification
Narrative generation and analysis are still on the fringe of modern natural language processing yet are crucial in a variety of applications.
It's All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning
Commonsense reasoning is one of the key problems in natural language processing, but the relative scarcity of labeled data holds back the progress for languages other than English.
Shape of Elephant: Study of Macro Properties of Word Embeddings Spaces
Pre-trained word representations became a key component in many NLP tasks.
Paranoid Transformer: Reading Narrative of Madness as Computational Approach to Creativity
We describe technical details of the generative system, provide examples of output and discuss the impact of receptive theory, chance discovery and simulation of fringe mental state on the understanding of computational creativity.
Artificial Neural Networks Jamming on the Beat
It suggests a very simple workaround for this challenge, namely, generation of a drum pattern that could be further used as a foundation for melody generation.
Intuitive Contrasting Map for Antonym Embeddings
This paper shows that, modern word embeddings contain information that distinguishes synonyms and antonyms despite small cosine similarities between corresponding vectors.
Style-transfer and Paraphrase: Looking for a Sensible Semantic Similarity Metric
The rapid development of such natural language processing tasks as style transfer, paraphrase, and machine translation often calls for the use of semantic similarity metrics.
Decomposing Textual Information For Style Transfer
This paper focuses on latent representations that could effectively decompose different aspects of textual information.
Style Transfer for Texts: Retrain, Report Errors, Compare with Rewrites
Second, starting with certain values of bilingual evaluation understudy (BLEU) between input and output and accuracy of the sentiment transfer the optimization of these two standard metrics diverge from the intuitive goal of the style transfer task.
Ranked #1 on
Text Style Transfer
on Yelp Review Dataset (Small)
Dyr Bul Shchyl. Proxying Sound Symbolism With Word Embeddings
This paper explores modern word embeddings in the context of sound symbolism.
What is wrong with style transfer for texts?
A number of recent machine learning papers work with an automated style transfer for texts and, counter to intuition, demonstrate that there is no consensus formulation of this NLP task.
Guess who? Multilingual approach for the automated generation of author-stylized poetry
This paper addresses the problem of stylized text generation in a multilingual setup.
