This paper introduces a novel multimodal corpus consisting of 12 video recordings of Zoom meetings held in English by an international group of researchers from September 2021 to March 2023. The meetings have an average duration of about 40 minutes each, for a total of 8 hours. The number of participants varies from 5 to 9 per meeting. The participants’ speech was transcribed automatically using WhisperX, while visual coordinates of several keypoints of the participants’ head, their shoulders and wrists, were extracted using OpenPose. The audio-visual recordings will be distributed together with the orthographic transcription as well as the visual coordinates. In the paper we describe the way the corpus was collected, transcribed and enriched with the visual coordinates, we give descriptive statistics concerning both the speech transcription and the visual keypoint values and we present and discuss visualisations of these values. Finally, we carry out a short preliminary analysis of the role of feedback in the meetings, and show how visualising the coordinates extracted via OpenPose can be used to see how gestural behaviour supports the use of feedback words during the interaction.

In this paper, we present a possible solution to the SemEval23 shared task of generating spoilers for clickbait headlines. Using a Zero-Shot approach with two different Transformer architectures, BLOOM and RoBERTa, we generate three different types of spoilers: phrase, passage and multi. We found, RoBERTa pretrained for Question-Answering to perform better than BLOOM for causal language modelling, however both architectures proved promising for future attempts at such tasks.

To gain a better understanding of the linguistic information encoded in character-based language models, we probe the multilingual contextual CANINE model. We design a range of phonetic probing tasks in six Nordic languages, including Faroese as an additional zero-shot instance. We observe that some phonetic information is indeed encoded in the character representations, as consonants and vowels can be well distinguished using a linear classifier. Furthermore, results for the Danish and Norwegian language seem to be worse for the consonant/vowel distinction in comparison to other languages. The information encoded in these representations can also be learned in a zero-shot scenario, as Faroese shows a reasonably good performance in the same vowel/consonant distinction task.

Character-level information is included in many NLP models, but evaluating the information encoded in character representations is an open issue. We leverage perceptual representations in the form of shape, sound, and color embeddings and perform a representational similarity analysis to evaluate their correlation with textual representations in five languages. This cross-lingual analysis shows that textual character representations correlate strongly with sound representations for languages using an alphabetic script, while shape correlates with featural scripts. We further develop a set of probing classifiers to intrinsically evaluate what phonological information is encoded in character embeddings. Our results suggest that information on features such as voicing are embedded in both LSTM and transformer-based representations.

In this paper we present our approach for detecting signs of depression from social media text. Our model relies on word unigrams, part-of-speech tags, readabilitiy measures and the use of first, second or third person and the number of words. Our best model obtained a macro F1-score of 0.439 and ranked 25th, out of 31 teams. We further take advantage of the interpretability of the Logistic Regression model and we make an attempt to interpret the model coefficients with the hope that these will be useful for further research on the topic.

Formal verse poetry imposes strict constraints on the meter and rhyme scheme of poems. Most prior work on generating this type of poetry uses existing poems for supervision, which are difficult to obtain for most languages and poetic forms. In this work, we propose an unsupervised approach to generate poems that follow any given meter and rhyme scheme, without requiring any poetic text for training. Our method works by splitting a regular, non-poetic corpus into phrases, prepending control codes that describe the length and end rhyme of each phrase, and training a transformer language model in the augmented corpus. The transformer learns to link the structure descriptor with the control codes to the number of lines, their length and their end rhyme. During inference, we build control codes for the desired meter and rhyme scheme, and condition our language model on them to generate formal verse poetry. Experiments in Spanish and Basque show that our approach is able to generate valid poems, which are often comparable in quality to those written by humans.

We describe the second SIGMORPHON shared task on unsupervised morphology: the goal of the SIGMORPHON 2021 Shared Task on Unsupervised Morphological Paradigm Clustering is to cluster word types from a raw text corpus into paradigms. To this end, we release corpora for 5 development and 9 test languages, as well as gold partial paradigms for evaluation. We receive 14 submissions from 4 teams that follow different strategies, and the best performing system is based on adaptor grammars. Results vary significantly across languages. However, all systems are outperformed by a supervised lemmatizer, implying that there is still room for improvement.

In this article, we show and discuss our experience in applying the flipped classroom method for teaching Conditional Random Fields in a Natural Language Processing course. We present the activities that we developed together with their relationship to a cognitive complexity model (Bloom’s taxonomy). After this, we provide our own reflections and expectations of the model itself. Based on the evaluation got from students, it seems that students learn about the topic and also that the method is rewarding for some students. Additionally, we discuss some shortcomings and we propose possible solutions to them. We conclude the paper with some possible future work.

We present a method to support the annotation of head movements in video-recorded conversations. Head movement segments from annotated multimodal data are used to train a model to detect head movements in unseen data. The resulting predicted movement sequences are uploaded to the ANVIL tool for post-annotation editing. The automatically identified head movements and the original annotations are compared to assess the overlap between the two. This analysis showed that movement onsets were more easily detected than offsets, and pointed at a number of patterns in the mismatches between original annotations and model predictions that could be dealt with in general terms in post-annotation guidelines.

We present a model for the unsupervised dis- covery of morphological paradigms. The goal of this model is to induce morphological paradigms from the bible (raw text) and a list of lemmas. We have created a model that splits each lemma in a stem and a suffix, and then we try to create a plausible suffix list by con- sidering lemma pairs. Our model was not able to outperform the official baseline, and there is still room for improvement, but we believe that the ideas presented here are worth considering.

This paper presents an approach to automatic head movement detection and classification in data from a corpus of video-recorded face-to-face conversations in Danish involving 12 different speakers. A number of classifiers were trained with different combinations of visual, acoustic and word features and tested in a leave-one-out cross validation scenario. The visual movement features were extracted from the raw video data using OpenPose, and the acoustic ones using Praat. The best results were obtained by a Multilayer Perceptron classifier, which reached an average 0.68 F1 score across the 12 speakers for head movement detection, and 0.40 for head movement classification given four different classes. In both cases, the classifier outperformed a simple most frequent class baseline as well as a more advanced baseline only relying on velocity features.

In this work we propose a data-driven methodology for identifying temporal trends in a corpus of medieval charters. We have used perplexities derived from RNNs as a distance measure between documents and then, performed clustering on those distances. We argue that perplexities calculated by such language models are representative of temporal trends. The clusters produced using the K-Means algorithm give an insight of the differences in language in different time periods at least partly due to language change. We suggest that the temporal distribution of the individual clusters might provide a more nuanced picture of temporal trends compared to discrete bins, thus providing better results when used in a classification task.

The use of a linking element between compound members is a common phenomenon in Germanic languages. Still, the exact use and conditioning of such elements is a disputed topic in linguistics. In this paper we address the issue of predicting the use of linking elements in Danish. Following previous research that shows how the choice of linking element might be conditioned by phonology, we frame the problem as a language modeling task: Considering the linking elements -s/-∅ the problem becomes predicting what is most probable to encounter next, a syllable boundary or the joining element, ‘s’. We show that training a language model on this task reaches an accuracy of 94 %, and in the case of an unsupervised model, the accuracy reaches 80%.

Our aim is to develop principled methods for sense clustering which can make existing lexical resources practically useful in NLP – not too fine-grained to be operational and yet finegrained enough to be worth the trouble. Where traditional dictionaries have a highly structured sense inventory typically describing the vocabulary by means of mainand subsenses, wordnets are generally fine-grained and unstructured. We present a series of clustering and annotation experiments with 10 of the most polysemous nouns in Danish. We combine the structured information of a traditional Danish dictionary with the ontological types found in the Danish wordnet, DanNet. This constellation enables us to automatically cluster senses in a principled way and improve inter-annotator agreement and wsd performance.

Automatic analysis of poetic rhythm is a challenging task that involves linguistics, literature, and computer science. When the language to be analyzed is known, rule-based systems or data-driven methods can be used. In this paper, we analyze poetic rhythm in English and Spanish. We show that the representations of data learned from character-based neural models are more informative than the ones from hand-crafted features, and that a Bi-LSTM+CRF-model produces state-of-the art accuracy on scansion of poetry in two languages. Results also show that the information about whole word structure, and not just independent syllables, is highly informative for performing scansion.

This article describes the systems submitted by the Citius_Ixa_Imaxin team to the Discriminating Similar Languages Shared Task 2016. The systems are based on two different strategies: classification with ranked dictionaries and Naive Bayes classifiers. The results of the evaluation show that ranking dictionaries are more sound and stable across different domains while basic bayesian models perform reasonably well on in-domain datasets, but their performance drops when they are applied on out-of-domain texts.

In this work we tackle the challenge of identifying rhythmic patterns in poetry written in English. Although poetry is a literary form that makes use standard meters usually repeated among different authors, we will see in this paper how performing such analyses is a difficult task in machine learning due to the unexpected deviations from such standard patterns. After breaking down some examples of classical poetry, we apply a number of NLP techniques for the scansion of poetry, training and testing our systems against a human-annotated corpus. With these experiments, our purpose is establish a baseline of automatic scansion of poetry using NLP tools in a straightforward manner and to raise awareness of the difficulties of this task.