Search

In this paper, we explore the extent to which readability contributes to the perception of literary quality as defined by two categories of variables: expert-based (e.g., Pulitzer Prize, National Book Award) and crowd-based (e.g., GoodReads, WorldCat). Based on a large corpus of modern and contemporary fiction in English, we examine the correlation of a text's readability with its perceived literary quality, also assessing readability measures against simpler stylometric features. Our results show that readability generally correlates with popularity as measured through open platforms such as GoodReads and WorldCat but has an inverse relation with three prestigious literary awards. This points to a distinction between crowd- and expert-based judgments of literary style, as well as to a discrimination between fame and appreciation in the reception of a book.

This article explores the sentiment dynamics present in narratives and their contribution to literary appreciation. Specifically, we investigate whether a certain type of sentiment development in a literary narrative correlates with its quality as perceived by a large number of readers. While we do not expect a story's sentiment arc to relate directly to readers' appreciation, we focus on its internal coherence as measured by its sentiment arc's level of fractality as a potential predictor of literary quality. To measure the arcs' fractality we use the Hurst exponent, a popular measure of fractal patterns that reflects the predictability or self-similarity of a time series. We apply this measure to the fairy tales of H.C. Andersen, using GoodReads' scores to approximate their level of appreciation. Based on our results we suggest that there might be an optimal balance between predictability and surprise in a sentiment arcs' structure that contributes to the perceived quality of a narrative text.

Narrative organization of information ties together storytelling in its many modalities. One archetypal expression of narratives we find in literary fiction. In this paper, we approach the elements of a successful narrative, and by extension storytelling, from the perspective of computational narratology. We are specifically interested in how to identify 'a good story'. Quality assessment of literature is complicated by many factors. Literature is a complex linguistic phenomenon that conveys information indirectly, readers have different aesthetic preferences, and there is a lack of proper scientific instruments. One noisy, but ecologically valid measure is quantitative 'reader reviews.' On this account, a narrative is successful if readers rate it high. Such an 'extrinsic' success criterion is tempting because it is relatively easy to access, reflects readers' preferences in a natural setting, and its standardization appears trivial. A criterion that relies on reviews is however prone to several well-known biases, for instance, gender [1], ethnicity, and race [2], which point to fairness challenges in the classification of real-world data [3]. Instead of merely relying of review annotation of the success of a story, we suggest paying attention to the inner structure of a story, termed the 'intrinsic success'. A recent theoretical paper has suggested that the affective coherence of a story, that is, the self-similarity of a sentiment story arc, functions as an index of a narrative's intrinsic success [4]. A complementary empirical study has shown that affective coherence can detect canonical literature [5]. (something is missing here) While the use of computational narratology may seem compelling to minimize demographic disparities introduced by extrinsic success, it introduces less apparent and unknown biases. Genre, for instance, impacts a story arc and shows complex interactions with psychological propensities, aesthetic evaluation, and gender [1]. Socio-cultural norms may also play an important role in introducing unknown biases even at the methodological level. In sum, there is no golden path to successful storytelling, that is, no single path that optimizes both quality and bias response. Instead, we see a multitude of possible trajectories, each of which implies different choices of known and unknown biases. References [1] S. Touileb, L. Øvrelid, E. Velldal, Gender and sentiment, critics and authors: a dataset ofNorwegian book reviews, in: Proceedings of the Second Workshop on Gender Bias inNatural Language Processing, Association for Computational Linguistics, Barcelona, Spain(Online), 2020, pp. 125-138. [2] P. Chong, Reading difference: How race and ethnicity function as tools for critical appraisal, Poetics 39 (2011) 64-84. [3] T. Miconi, The impossibility of "fairness": a generalized impossibility result for decisions,2017.arXiv:1707.01195. [4] Q. Hu, B. Liu, M. R. Thomsen, J. Gao, K. L. Nielbo, Dynamic evolution of sentiments in Never Let Me Go: Insights from multifractal theory and its implications for literary analysis,Digital Scholarship in the Humanities 36 (2020) 322-332. [5] Y. Bizzoni, T. Peura, M. R. Thomsen, K. L. Nielbo, Sentiment Dynamics of Success: Fractal Scaling of Story Arcs Predicts Reader Preferences, 2021. Proceedings of the First Workshop on Natural Language Processing for Digital Humanities (2021), 1-6.

Narrative organization of information ties together storytelling in its many modalities. One archetypal expression of narratives we find in literary fiction. In this paper, we approach the elements of a successful narrative, and by extension storytelling, from the perspective of computational narratology. We are specifically interested in how to identify ’a good story’ and navigate in two dimensions of literary success: ‘Extrinsic’ and ‘intrinsic’. We investigate the association between the self-similarity of a sentiment story arc and review assessment of a literary work. In doing so, we direct our attention to known and unknown biases in the suggested dimensions of success to avoid reinforcing existing unwanted structures in our exploration of successful narratives.Quality assessment of literature is not a simple inquiry and is complicated by various factors. Literature is a complex linguistic phenomenon that conveys information indirectly, and readers have different aesthetic preferences, and, in general, there is a lack of robust scientific instruments for measuring literary quality. One noisy, but ecologically valid measure is quantitative ’reader reviews.’ On this account, a narrative is successful if readers rate it high. Such an ’extrinsic’ success criterion is tempting because it is relatively easy to access, reflects readers’ preferences in a natural setting, and its standardization appears trivial. A criterion that relies on reviews is however prone to several well-known biases, for instance, grading disparities between gender [1], ethnicity and race [2], which point to fairness challenges in classification of real-world data [3]. Instead of merely relying upon review annotation of the success of a story, we suggest paying attention to the inner structure of a story, the ’intrinsic success’.A recent theoretical paper has suggested that the affective coherence of a story, that is, the self-similarity of a sentiment story arc, functions as an index of a narrative’s intrinsic success [4]. A complementary empirical study has shown that affective coherence can detect canonical literature [5].While the use of computational narratology may seem compelling to minimize demographic disparities introduced by extrinsic success, it introduces less apparent and unknown biases. Genre, for instance, impacts a story arc and shows complex interactions with psychological propensities, aesthetic evaluation, and gender [1]. In this work, we examine the association between the internal sentiment structure of a work and known biases. Socio-cultural norms may also play an important role in introducing unknown biases even at the methodological level, such as representational biases of reader types.In sum, there is no golden path to identify successful storytelling, that is, no single path that optimizes both quality assessment and bias response. Instead of relying on single dimensions of success, either compelling computational approaches or accessible standardization, we suggest a deliberate combination of dimensions and approaches which includes choices about bias acceptance. We see a multitude of possible trajectories, each of which implies different choices of known and unknown biases.

International audience

Metaphor is one of the most prominent, and most studied, figures of speech. While it is considered an element of great interest in several branches of linguistics, such as semantics, pragmatics and stylistics, its automatic processing remains an open challenge. First of all, the semantic complexity of the concept of metaphor itself creates a range of theoretical complications. Secondly, the practical lack of large scale resources for machine learning approaches forces researchers to work under conditions of data scarcity. This compilation thesis provides a set of experiments to (i) automatically detect metaphors and (ii) assess a metaphor's aptness with respect to a given literal equivalent. The first task has already been tackled by a number of studies. We approach it as a way to assess the potentialities and limitations of our approach, before dealing with the second task. For metaphor detection we were able to use existing resources, while we created our own dataset to explore metaphor aptness assessment, which constitutes the most innovative part of this research. In all of the studies presented here, I have used a combination of word embeddings and neural networks. This combination appears particularly effective since pre-trained word embeddings can provide the networks with information necessary to deal with metaphors under conditions of data scarcity. To deal with metaphor aptness assessment, we frame the problem as a case of paraphrase identification. Given a sentence containing a metaphor, the task is to find the best literal paraphrase from a set of candidates. We build a dataset designed for this task, that allows a gradient scoring of various paraphrases with respect to a reference sentence, so that paraphrases are ordered according to their degree of aptness. Therefore, we can use it for both binary classification and ordering tasks. This dataset is annotated through crowd sourcing by an average of 20 annotators for each pair. We then design a deep neural network to be trained on this dataset. We show that its architecture is able achieve encouraging levels of performance, despite the serious limitations of data scarcity in which it is applied. In the final experiment of this compilation, more context is added to a sub-section of the dataset in order to study the effect of extended context on metaphor aptness rating. We show that extended context changes human perception of metaphor aptness and that this effect is reproduced by our neural classifier. The conclusion of the last study is that extended context compresses aptness scores towards the center of the scale, raising low ratings and decreasing high ratings given to paraphrase candidates outside of any context.

La collana pubblica gli atti del convegno annuale di Linguistica Computazionale (CLiC-it), che ha lo scopo di costituire un luogo di discussione di riferimento nel campo delle ricerce sulla linguistica computazionale. Gli atti includono interventi sul trattamento automatico della lingua, comprendenti le riflessioni teoriche e metodologiche sul tema, e forniscono un contributo importante per questo campo di ricerca. Le altre tematiche principali sono: la linguistica computazionale, la linguistica, le scienze cognitive, l'apprendimento automatico, l'informatica, la rappresentazione della conoscenza, l'information retrieval e l'umanistica digitale. L'organizzazione del convegno è il risultato dello sforzo dell'Associazione Italiana di Linguistica Computazionale (AILC http://www.ai-lc.it/), rappresentata ogni anno da alcuni dei membri organizzatori, che sono affiliati anche ad altre organizzazioni che operano nell'ambito della linguistica computazionale. This book presents the proceedings of the annual Conference of Computational Linguistics (CLiC-it), which aims to provide a forum for discussion in the field of computational linguistics. The proceedings include interventions on the automatic treatment of language, with theoretical and methodological reflections on the subject, and provide an important contribution to this field of research. The other main topics are: computational linguistics, linguistics, cognitive sciences, automatic learning, computer science, knowledge representation, information retrieval and digital humanities. The organization of the conference is the result of the effort of the Italian Association of Computational Linguistics (AILC http://www.ai-lc.it/), represented every year by some of the organizing members, who are also affiliated to other organizations operating in the field of computational linguistics.

In this paper we intend to present a tool we developed for translation studies and diachronically compare various French translations of the Odyssey.

CLiC-it 2015 is held in Trento on December 3-4 2015, hosted and locally organized by Fondazione Bruno Kessler (FBK), one the most important Italian research centers for what concerns CL. The organization of the conference is the result of a fruitful conjoint effort of different research groups (Università di Torino, Università di Roma Tor Vergata and FBK) showing the nationwide spreading of CL in Italy. As in the first edition, the main aim of the event is at establishing a reference forum on CL, covering all the aspects needed to describe the multi-faceted and cross-disciplinary reality of the involved research topics and of the Italian community working in this area. Indeed the spirit of CLiC-it is inclusive, in order to build a scenario as much as possible comprehensive of the complexity of language phenomena and approaches to address them, bringing together researchers and scholars with different competences and skills and working on different aspects according to different perspectives. The large number of researchers that have decided to present their work at CLiC-it and the number of directions here investigated are proof of the maturity of our community and a promising indication of its vitality. We received a total of 64 paper submissions, out of which 52 have been accepted to appear in the Conference Proceedings, which are available online and on the OpenEdition platform. Overall, we collected 129 authors from 15 countries.

International audience; Our program compares French and Italian translations of Homer's Odyssey, from the XVIth to the XXth century. We focus on the third point, showing how distributional semantics systems can be used both to improve alignment between different French translations as well as between the Greek text and a French translation. Although we focus on French examples, the techniques we display are completely language independent.

By using a trigram model and fine-tuning a pretrained BERT model for sequence classification, we show that machine translation and human translation can be classified with an accuracy above chance level, which suggests that machine translation and human translation are different in a systematic way. The classification accuracy of machine translation is much higher than of human translation. We show that this may be explained by the difference in lexical diversity between machine translation and human translation. If machine translation has independent patterns from human translation, automatic metrics which measure the deviation of machine translation from human translation may conflate difference with quality. Our experiment with two different types of automatic metrics shows correlation with the result of the classification task. Therefore, we suggest the difference in lexical diversity between machine translation and human translation be given more attention in machine translation evaluation., accepted by MoTra21, Nodalida 2021