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. We propose a novel dataset based on Choose Your Own Adventure (a registered trademark of Chooseco LLC) games graphs to be used as a benchmark for such a task. We provide a comparative analysis of different models’ performance on this task, including a couple of LLMs and several MLMs as baselines, achieving up to 89% accuracy. This underscores the complexity of narrative analysis, showing the challenges associated with understanding character-driven story dynamics. Additionally, we show how such a model can be applied to the existing text to produce linear segments divided by potential branching points, demonstrating the practical application of our findings in narrative analysis.
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. Particularly, the study of the emergence of echo-chambers due to the dissemination of specific information has become a topic of interest in mixed methods research areas. In this paper, we analyze data collected from two news portals, Breitbart News (BN) and New York Times (NYT) to prove the hypothesis that the formation of echo-chambers can be partially explained on the level of an individual information consumption rather than a collective topology of individuals’ social networks. Our research findings are presented through knowledge graphs, utilizing a dataset spanning 11.5 years gathered from BN and NYT media portals. We demonstrate that the application of knowledge representation techniques to the aforementioned news streams highlights, contrary to common assumptions, shows relative “internal” neutrality of both sources and polarizing attitude towards a small fraction of entities. Additionally, we argue that such characteristics in information sources lead to fundamental disparities in audience worldviews, potentially acting as a catalyst for the formation of echo-chambers.
We investigate a new linguistic generalisation in pre-trained language models (taking BERT Devlin et al. 2019 as a case study). We focus on degree modifiers (expressions like slightly, very, rather, extremely) and test the hypothesis that the degree expressed by a modifier (low, medium or high degree) is related to the modifier’s sensitivity to sentence polarity (whether it shows preference for affirmative or negative sentences or neither). To probe this connection, we apply the Artificial Language Learning experimental paradigm from psycholinguistics to a neural language model. Our experimental results suggest that BERT generalizes in line with existing linguistic observations that relate de- gree semantics to polarity sensitivity, including the main one: low degree semantics is associated with preference towards positive polarity.
Multimodal embeddings aim to enrich the semantic information in neural representations of language compared to text-only models. While different embeddings exhibit different applicability and performance on downstream tasks, little is known about the systematic representation differences attributed to the visual modality. Our paper compares word embeddings from three vision-and-language models (CLIP, OpenCLIP and Multilingual CLIP, Radford et al. 2021; Ilharco et al. 2021; Carlsson et al. 2022) and three text-only models, with static (FastText, Bojanowski et al. 2017) as well as contextual representations (multilingual BERT Devlin et al. 2018; XLM-RoBERTa, Conneau et al. 2019). This is the first large-scale study of the effect of visual grounding on language representations, including 46 semantic parameters. We identify meaning properties and relations that characterize words whose embeddings are most affected by the inclusion of visual modality in the training data; that is, points where visual grounding turns out most important. We find that the effect of visual modality correlates most with denotational semantic properties related to concreteness, but is also detected for several specific semantic classes, as well as for valence, a sentiment-related connotational property of linguistic expressions.
In the rapidly evolving landscape of Large Language Models (LLMs), introduction of well-defined and standardized evaluation methodologies remains a crucial challenge. This paper traces the historical trajectory of LLM evaluations, from the foundational questions posed by Alan Turing to the modern era of AI research. We categorize the evolution of LLMs into distinct periods, each characterized by its unique benchmarks and evaluation criteria. As LLMs increasingly mimic human-like behaviors, traditional evaluation proxies, such as the Turing test, have become less reliable. We emphasize the pressing need for a unified evaluation system, given the broader societal implications of these models. Through an analysis of common evaluation methodologies, we advocate for a qualitative shift in assessment approaches, underscoring the importance of standardization and objective criteria. This work serves as a call for the AI community to collaboratively address the challenges of LLM evaluation, ensuring their reliability, fairness, and societal benefit.
In this position paper, we contend that advancing our understanding of narrative and the effective generation of longer, subjectively engaging texts is crucial for progress in modern Natural Language Processing (NLP) and potentially the broader field of Artificial Intelligence. We highlight the current lack of appropriate datasets, evaluation methods, and operational concepts necessary for initiating work on narrative processing.
Representation of linguistic phenomena in computational language models is typically assessed against the predictions of existing linguistic theories of these phenomena. Using the notion of polarity as a case study, we show that this is not always the most adequate set-up. We probe polarity via so-called ‘negative polarity items’ (in particular, English ‘any’) in two pre-trained Transformer-based models (BERT and GPT-2). We show that – at least for polarity – metrics derived from language models are more consistent with data from psycholinguistic experiments than linguistic theory predictions. 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. This work contributes to establishing closer ties between psycholinguistic experiments and experiments with language models.
The extensive surviving corpus of the ancient scholar Plutarch of Chaeronea (ca. 45-120 CE) also contains several texts which, according to current scholarly opinion, did not originate with him and are therefore attributed to an anonymous author Pseudo-Plutarch. These include, in particular, the work Placita Philosophorum (Quotations and Opinions of the Ancient Philosophers), which is extremely important for the history of ancient philosophy. Little is known about the identity of that anonymous author and its relation to other authors from the same period. This paper presents a BERT language model for Ancient Greek. The model discovers previously unknown statistical properties relevant to these literary, philosophical, and historical problems and can shed new light on this authorship question. 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).
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. Furthermore, to support the evaluation of commonsense reasoning tasks, we provide hand-crafted cross-lingual datasets for five different semantic tasks (namely news categorization, paraphrase detection, Natural Language Inference (NLI) task, tweet sentiment detection, and news sentiment detection) for some of the Eastern European languages. We perform several experiments with the existing multilingual models on these datasets to define the performance baselines and compare them to the existing results for other languages.
Detecting implicit causal relations in texts is a task that requires both common sense and world knowledge. Existing datasets are focused either on commonsense causal reasoning or explicit causal relations. In this work, we present HeadlineCause, a dataset for detecting implicit causal relations between pairs of news headlines. The dataset includes over 5000 headline pairs from English news and over 9000 headline pairs from Russian news labeled through crowdsourcing. The pairs vary from totally unrelated or belonging to the same general topic to the ones including causation and refutation relations. We also present a set of models and experiments that demonstrates the dataset validity, including a multilingual XLM-RoBERTa based model for causality detection and a GPT-2 based model for possible effects prediction.
This paper presents StoryDB — a broad multi-language dataset of narratives. StoryDB is a corpus of texts that includes stories in 42 different languages. Every language includes 500+ stories. Some of the languages include more than 20 000 stories. Every story is indexed across languages and labeled with tags such as a genre or a topic. The corpus shows rich topical and language variation and can serve as a resource for the study of the role of narrative in natural language processing across various languages including low resource ones. We also demonstrate how the dataset could be used to benchmark three modern multilanguage models, namely, mDistillBERT, mBERT, and XLM-RoBERTa.
This paper shows that standard assessment methodology for style transfer has several significant problems. First, the standard metrics for style accuracy and semantics preservation vary significantly on different re-runs. Therefore one has to report error margins for the obtained results. 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. Finally, due to the nature of the task itself, there is a specific dependence between these two metrics that could be easily manipulated. Under these circumstances, we suggest taking BLEU between input and human-written reformulations into consideration for benchmarks. We also propose three new architectures that outperform state of the art in terms of this metric.
This paper focuses on latent representations that could effectively decompose different aspects of textual information. Using a framework of style transfer for texts, we propose several empirical methods to assess information decomposition quality. We validate these methods with several state-of-the-art textual style transfer methods. Higher quality of information decomposition corresponds to higher performance in terms of bilingual evaluation understudy (BLEU) between output and human-written reformulations.
This paper explores modern word embeddings in the context of sound symbolism. Using basic properties of the representations space one can construct semantic axes. A method is proposed to measure if the presence of individual sounds in a given word shifts its semantics of that word along a specific axis. It is shown that, in accordance with several experimental and statistical results, word embeddings capture symbolism for certain sounds.