This paper presents a methodology for training a transformer-based model to classify lexical and morphosyntactic features of Skolt Sami, an endangered Uralic language characterized by complex morphology. The goal of our approach is to create an effective system for understanding and analyzing Skolt Sami, given the limited data availability and linguistic intricacies inherent to the language. Our end-to-end pipeline includes data extraction, augmentation, and training a transformer-based model capable of predicting inflection classes. The motivation behind this work is to support language preservation and revitalization efforts for minority languages like Skolt Sami. Accurate classification not only helps improve the state of Finite-State Transducers (FSTs) by providing greater lexical coverage but also contributes to systematic linguistic documentation for researchers working with newly discovered words from literature and native speakers. Our model achieves an average weighted F1 score of 1.00 for POS classification and 0.81 for inflection class classification. The trained model and code will be released publicly to facilitate future research in endangered NLP.

We present a novel digital humanities method for representing our Twitch chatters as user embeddings created by a large language model (LLM). We cluster these embeddings automatically using affinity propagation and further narrow this clustering down through manual analysis. We analyze the chat of one stream by each Twitch streamer: SmallAnt, DougDoug and PointCrow. Our findings suggest that each streamer has their own type of chatters, however two categories emerge for all of the streamers: supportive viewers and emoji and reaction senders. Repetitive message spammers is a shared chatter category for two of the streamers.

We present our work towards building an infrastructure for documenting endangered languages with the focus on Uralic languages in particular. Our infrastructure consists of tools to write dictionaries so that entries are structured in XML format. These dictionaries are the foundation for rule-based NLP tools such as FSTs. We also work actively towards enhancing these dictionaries and tools by using the latest state-of-the-art neural models by generating training data through rules and lexica

In this paper, we present an approach for translating word embeddings from a majority language into 4 minority languages: Erzya, Moksha, Udmurt and Komi-Zyrian. Furthermore, we align these word embeddings and present a novel neural network model that is trained on English data to conduct sentiment analysis and then applied on endangered language data through the aligned word embeddings. To test our model, we annotated a small sentiment analysis corpus for the 4 endangered languages and Finnish. Our method reached at least 56% accuracy for each endangered language. The models and the sentiment corpus will be released together with this paper. Our research shows that state-of-the-art neural models can be used with endangered languages with the only requirement being a dictionary between the endangered language and a majority language.

Neural Machine Translation (NMT) has made significant strides in breaking down language barriers around the globe. For lesser-resourced languages like Moksha and Erzya, however, the development of robust NMT systems remains a challenge due to the scarcity of parallel corpora. This paper presents a novel approach to address this challenge by leveraging the existing rule-based machine translation system Apertium as a tool for synthetic data generation. We fine-tune NLLB-200 for Moksha-Erzya translation and obtain a BLEU of 0.73 on the Apertium generated data. On real world data, we got an improvement of 0.058 BLEU score over Apertium.

In this paper, we present an FST based approach for conducting morphological analysis, lemmatization and generation of Lushootseed words. Furthermore, we use the FST to generate training data for an LSTM based neural model and train this model to do morphological analysis. The neural model reaches a 71.9% accuracy on the test data. Furthermore, we discuss reduplication types in the Lushootseed language forms. The approach involves the use of both attested instances of reduplication and bare stems for applying a variety of reduplications to, as it is unclear just how much variation can be attributed to the individual speakers and authors of the source materials. That is, there may be areal factors that can be aligned with certain types of reduplication and their frequencies.

We present a DialGPT based model for generating creative dialog responses that are conditioned based on one of the following emotions: anger, disgust, fear, happiness, pain, sadness and surprise. Our model is capable of producing a contextually apt response given an input sentence and a desired emotion label. Our model is capable of expressing the desired emotion with an accuracy of 0.6. The best performing emotions are neutral, fear and disgust. When measuring the strength of the expressed emotion, we find that anger, fear and disgust are expressed in the most strong fashion by the model.

While standard Estonian is not a low-resourced language, the different dialects of the language are under-resourced from the point of view of NLP, given that there are no vast hand normalized resources available for training a machine learning model to normalize dialectal Estonian to standard Estonian. In this paper, we crawl a small corpus of parallel dialectal Estonian - standard Estonian sentences. In addition, we take a savvy approach of generating more synthetic training data for the normalization task by using an existing dialect generator model built for Finnish to “dialectalize” standard Estonian sentences from the Universal Dependencies tree banks. Our BERT based normalization model achieves a word error rate that is 26.49 points lower when using both the synthetic data and Estonian data in comparison to training the model with only the available Estonian data. Our results suggest that synthetic data generated by a model trained on a more resourced related language can indeed boost the results for a less resourced language.

Many endangered Uralic languages have multilingual machine readable dictionaries saved in an XML format. However, the dictionaries cover translations very inconsistently between language pairs, for instance, the Livonian dictionary has some translations to Finnish, Latvian and Estonian, and the Komi-Zyrian dictionary has some translations to Finnish, English and Russian. We utilize graph-based approaches to augment such dictionaries by predicting new translations to existing and new languages based on different dictionaries for endangered languages and Wiktionaries. Our study focuses on the lexical resources for Komi-Zyrian (kpv), Erzya (myv) and Livonian (liv). We evaluate our approach by human judges fluent in the three endangered languages in question. Based on the evaluation, the method predicted good or acceptable translations 77% of the time. Furthermore, we train a neural prediction model to predict the quality of the automatically predicted translations with an 81% accuracy. The resulting extensions to the dictionaries are made available on the online dictionary platform used by the speakers of these languages.

We present the first openly available multimodal metaphor annotated corpus. The corpus consists of videos including audio and subtitles that have been annotated by experts. Furthermore, we present a method for detecting metaphors in the new dataset based on the textual content of the videos. The method achieves a high F1-score (62%) for metaphorical labels. We also experiment with other modalities and multimodal methods; however, these methods did not out-perform the text-based model. In our error analysis, we do identify that there are cases where video could help in disambiguating metaphors, however, the visual cues are too subtle for our model to capture. The data is available on Zenodo.

Prerecorded laughter accompanying dialog in comedy TV shows encourages the audience to laugh by clearly marking humorous moments in the show. We present an approach for automatically detecting humor in the Friends TV show using multimodal data. Our model is capable of recognizing whether an utterance is humorous or not and assess the intensity of it. We use the prerecorded laughter in the show as annotation as it marks humor and the length of the audience’s laughter tells us how funny a given joke is. We evaluate the model on episodes the model has not been exposed to during the training phase. Our results show that the model is capable of correctly detecting whether an utterance is humorous 78% of the time and how long the audience’s laughter reaction should last with a mean absolute error of 600 milliseconds.

We present our current work on developing keyboard layouts for a critically endangered Uralic language called Livonian. Our layouts work on Windows, MacOS and Linux. In addition, we have developed keyboard apps with predictive text for Android and iOS. This work has been conducted in collaboration with the language community.

We train neural models for morphological analysis, generation and lemmatization for morphologically rich languages. We present a method for automatically extracting substantially large amount of training data from FSTs for 22 languages, out of which 17 are endangered. The neural models follow the same tagset as the FSTs in order to make it possible to use them as fallback systems together with the FSTs. The source code, models and datasets have been released on Zenodo.

We present the first openly available corpus for detecting depression in Thai. Our corpus is compiled by expert verified cases of depression in several online blogs. We experiment with two different LSTM based models and two different BERT based models. We achieve a 77.53% accuracy with a Thai BERT model in detecting depression. This establishes a good baseline for future researcher on the same corpus. Furthermore, we identify a need for Thai embeddings that have been trained on a more varied corpus than Wikipedia. Our corpus, code and trained models have been released openly on Zenodo.

We construct the first ever multimodal sarcasm dataset for Spanish. The audiovisual dataset consists of sarcasm annotated text that is aligned with video and audio. The dataset represents two varieties of Spanish, a Latin American variety and a Peninsular Spanish variety, which ensures a wider dialectal coverage for this global language. We present several models for sarcasm detection that will serve as baselines in the future research. Our results show that results with text only (89%) are worse than when combining text with audio (91.9%). Finally, the best results are obtained when combining all the modalities: text, audio and video (93.1%). Our dataset will be published on Zenodo with access granted by request.

This study presents a new dataset on rumor detection in Finnish language news headlines. We have evaluated two different LSTM based models and two different BERT models, and have found very significant differences in the results. A fine-tuned FinBERT reaches the best overall accuracy of 94.3% and rumor label accuracy of 96.0% of the time. However, a model fine-tuned on Multilingual BERT reaches the best factual label accuracy of 97.2%. Our results suggest that the performance difference is due to a difference in the original training data. Furthermore, we find that a regular LSTM model works better than one trained with a pretrained word2vec model. These findings suggest that more work needs to be done for pretrained models in Finnish language as they have been trained on small and biased corpora.

We survey human evaluation in papers presenting work on creative natural language generation that have been published in INLG 2020 and ICCC 2020. The most typical human evaluation method is a scaled survey, typically on a 5 point scale, while many other less common methods exist. The most commonly evaluated parameters are meaning, syntactic correctness, novelty, relevance and emotional value, among many others. Our guidelines for future evaluation include clearly defining the goal of the generative system, asking questions as concrete as possible, testing the evaluation setup, using multiple different evaluation setups, reporting the entire evaluation process and potential biases clearly, and finally analyzing the evaluation results in a more profound way than merely reporting the most typical statistics.

We outline the Great Misalignment Problem in natural language processing research, this means simply that the problem definition is not in line with the method proposed and the human evaluation is not in line with the definition nor the method. We study this misalignment problem by surveying 10 randomly sampled papers published in ACL 2020 that report results with human evaluation. Our results show that only one paper was fully in line in terms of problem definition, method and evaluation. Only two papers presented a human evaluation that was in line with what was modeled in the method. These results highlight that the Great Misalignment Problem is a major one and it affects the validity and reproducibility of results obtained by a human evaluation.

The study forms a technical report of various tasks that have been performed on the materials collected and published by Finnish ethnographer and linguist, Matthias Alexander Castrén (1813–1852). The Finno-Ugrian Society is publishing Castrén’s manuscripts as new critical and digital editions, and at the same time different research groups have also paid attention to these materials. We discuss the workflows and technical infrastructure used, and consider how datasets that benefit different computational tasks could be created to further improve the usability of these materials, and also to aid the further processing of similar archived collections. We specifically focus on the parts of the collections that are processed in a way that improves their usability in more technical applications, complementing the earlier work on the cultural and linguistic aspects of these materials. Most of these datasets are openly available in Zenodo. The study points to specific areas where further research is needed, and provides benchmarks for text recognition tasks.

Measuring the semantic similarity of different texts has many important applications in Digital Humanities research such as information retrieval, document clustering and text summarization. The performance of different methods depends on the length of the text, the domain and the language. This study focuses on experimenting with some of the current approaches to Finnish, which is a morphologically rich language. At the same time, we propose a simple method, TFW2V, which shows high efficiency in handling both long text documents and limited amounts of data. Furthermore, we design an objective evaluation method which can be used as a framework for benchmarking text similarity approaches.

Finnish is a language with multiple dialects that not only differ from each other in terms of accent (pronunciation) but also in terms of morphological forms and lexical choice. We present the first approach to automatically detect the dialect of a speaker based on a dialect transcript and transcript with audio recording in a dataset consisting of 23 different dialects. Our results show that the best accuracy is received by combining both of the modalities, as text only reaches to an overall accuracy of 57%, where as text and audio reach to 85%. Our code, models and data have been released openly on Github and Zenodo.

In this study, we have normalized and lemmatized an Old Literary Finnish corpus using a lemmatization model trained on texts from Agricola. We analyse the error types that occur and appear in different decades, and use word error rate (WER) and different error types as a proxy for measuring linguistic innovation and change. We show that the proposed approach works, and the errors are connected to accumulating changes and innovations, which also results in a continuous decrease in the accuracy of the model. The described error types also guide further work in improving these models, and document the currently observed issues. We also have trained word embeddings for four centuries of lemmatized Old Literary Finnish, which are available on Zenodo.

Texts written in Old Literary Finnish represent the first literary work ever written in Finnish starting from the 16th century. There have been several projects in Finland that have digitized old publications and made them available for research use. However, using modern NLP methods in such data poses great challenges. In this paper we propose an approach for simultaneously normalizing and lemmatizing Old Literary Finnish into modern spelling. Our best model reaches to 96.3% accuracy in texts written by Agricola and 87.7% accuracy in other contemporary out-of-domain text. Our method has been made freely available on Zenodo and Github.

We present an open-source online dictionary editing system, Ve′rdd, that offers a chance to re-evaluate and edit grassroots dictionaries that have been exposed to multiple amateur editors. The idea is to incorporate community activities into a state-of-the-art finite-state language description of a seriously endangered minority language, Skolt Sami. Problems involve getting the community to take part in things above the pencil-and-paper level. At times, it seems that the native speakers and the dictionary oriented are lacking technical understanding to utilize the infrastructures which might make their work more meaningful in the future, i.e. multiple reuse of all of their input. Therefore, our system integrates with the existing tools and infrastructures for Uralic language masking the technical complexities behind a user-friendly UI.

We present a novel approach for generating poetry automatically for the morphologically rich Finnish language by using a genetic algorithm. The approach improves the state of the art of the previous Finnish poem generators by introducing a higher degree of freedom in terms of structural creativity. Our approach is evaluated and described within the paradigm of computational creativity, where the fitness functions of the genetic algorithm are assimilated with the notion of aesthetics. The output is considered to be a poem 81.5% of the time by human evaluators.

We compare different LSTMs and transformer models in terms of their effectiveness in normalizing dialectal Finnish into the normative standard Finnish. As dialect is the common way of communication for people online in Finnish, such a normalization is a necessary step to improve the accuracy of the existing Finnish NLP tools that are tailored for normative Finnish text. We work on a corpus consisting of dialectal data of 23 distinct Finnish dialects. The best functioning BRNN approach lowers the initial word error rate of the corpus from 52.89 to 5.73.

We present a creative poem generator for the morphologically rich Finnish language. Our method falls into the master-apprentice paradigm, where a computationally creative genetic algorithm teaches a BRNN model to generate poetry. We model several parts of poetic aesthetics in the fitness function of the genetic algorithm, such as sonic features, semantic coherence, imagery and metaphor. Furthermore, we justify the creativity of our method based on the FACE theory on computational creativity and take additional care in evaluating our system by automatic metrics for concepts together with human evaluation for aesthetics, framing and expressions.

Satire has played a role in indirectly expressing critique towards an authority or a person from time immemorial. We present an autonomously creative master-apprentice approach consisting of a genetic algorithm and an NMT model to produce humorous and culturally apt satire out of movie titles automatically. Furthermore, we evaluate the approach in terms of its creativity and its output. We provide a solid definition for creativity to maximize the objectiveness of the evaluation.