Jussi Karlgren

Ekaterina Garmash, Edgar Tanaka, Ann Clifton et al.

In this paper we describe the Portuguese-language podcast dataset we have released for academic research purposes. We give an overview of how the data was sampled, descriptive statistics over the collection, as well as information about the distribution over Brazilian and Portuguese dialects. We give results from experiments on multi-lingual summarization, showing that summarizing podcast transcripts can be performed well by a system supporting both English and Portuguese. We also show experiments on Portuguese podcast genre classification using text metadata. Combining this collection with previously released English-language collection opens up the potential for multi-modal, multi-lingual and multi-dialect podcast information access research.

Jussi Karlgren

This chapter argues for more informed target metrics for the statistical processing of stylistic variation in text collections. Much as operationalised relevance proved a useful goal to strive for in information retrieval, research in textual stylistics, whether application oriented or philologically inclined, needs goals formulated in terms of pertinence, relevance, and utility - notions that agree with reader experience of text. Differences readers are aware of are mostly based on utility - not on textual characteristics per se. Mostly, readers report stylistic differences in terms of genres. Genres, while vague and undefined, are well-established and talked about: very early on, readers learn to distinguish genres. This chapter discusses variation given by genre, and contrasts it to variation occasioned by individual choice.

M. Iftekhar Tanveer, Diego Casabuena, Jussi Karlgren et al.

Podcasts are conversational in nature and speaker changes are frequent -- requiring speaker diarization for content understanding. We propose an unsupervised technique for speaker diarization without relying on language-specific components. The algorithm is overlap-aware and does not require information about the number of speakers. Our approach shows 79% improvement on purity scores (34% on F-score) against the Google Cloud Platform solution on podcast data.

Jussi Karlgren

Genres can be understood in many different ways. They are often perceived as a primarily sociological construction, or, alternatively, as a stylostatistically observable objective characteristic of texts. The latter view is more common in the research field of information and language technology. These two views can be quite compatible and can inform each other; this present investigation discusses knowledge sources for studying genre variation and change by observing reader and author behaviour rather than performing analyses on the information objects themselves.

Shahrzad Naseri, Sravana Reddy, Joana Correia et al.

In this work, we study the association between song lyrics and mood through a data-driven analysis. Our data set consists of nearly one million songs, with song-mood associations derived from user playlists on the Spotify streaming platform. We take advantage of state-of-the-art natural language processing models based on transformers to learn the association between the lyrics and moods. We find that a pretrained transformer-based language model in a zero-shot setting -- i.e., out of the box with no further training on our data -- is powerful for capturing song-mood associations. Moreover, we illustrate that training on song-mood associations results in a highly accurate model that predicts these associations for unseen songs. Furthermore, by comparing the prediction of a model using lyrics with one using acoustic features, we observe that the relative importance of lyrics for mood prediction in comparison with acoustics depends on the specific mood. Finally, we verify if the models are capturing the same information about lyrics and acoustics as humans through an annotation task where we obtain human judgments of mood-song relevance based on lyrics and acoustics.

Raúl Vázquez, Timothee Mickus, Elaine Zosa et al.

We present the Mu-SHROOM shared task which is focused on detecting hallucinations and other overgeneration mistakes in the output of instruction-tuned large language models (LLMs). Mu-SHROOM addresses general-purpose LLMs in 14 languages, and frames the hallucination detection problem as a span-labeling task. We received 2,618 submissions from 43 participating teams employing diverse methodologies. The large number of submissions underscores the interest of the community in hallucination detection. We present the results of the participating systems and conduct an empirical analysis to identify key factors contributing to strong performance in this task. We also emphasize relevant current challenges, notably the varying degree of hallucinations across languages and the high annotator disagreement when labeling hallucination spans.

Reza Qorbani, Gianluca Villani, Theodoros Panagiotakopoulos et al.

Open-vocabulary semantic segmentation models associate vision and text to label pixels from an undefined set of classes using textual queries, providing versatile performance on novel datasets. However, large shifts between training and test domains degrade their performance, requiring fine-tuning for effective real-world applications. We introduce Semantic Library Adaptation (SemLA), a novel framework for training-free, test-time domain adaptation. SemLA leverages a library of LoRA-based adapters indexed with CLIP embeddings, dynamically merging the most relevant adapters based on proximity to the target domain in the embedding space. This approach constructs an ad-hoc model tailored to each specific input without additional training. Our method scales efficiently, enhances explainability by tracking adapter contributions, and inherently protects data privacy, making it ideal for sensitive applications. Comprehensive experiments on a 20-domain benchmark built over 10 standard datasets demonstrate SemLA's superior adaptability and performance across diverse settings, establishing a new standard in domain adaptation for open-vocabulary semantic segmentation.

Christine Bauer, Li Chen, Nicola Ferro et al.

During the workshop, we deeply discussed what CONversational Information ACcess (CONIAC) is and its unique features, proposing a world model abstracting it, and defined the Conversational Agents Framework for Evaluation (CAFE) for the evaluation of CONIAC systems, consisting of six major components: 1) goals of the system's stakeholders, 2) user tasks to be studied in the evaluation, 3) aspects of the users carrying out the tasks, 4) evaluation criteria to be considered, 5) evaluation methodology to be applied, and 6) measures for the quantitative criteria chosen.

Filip Cornell, Yifei Jin, Jussi Karlgren et al.

The standard evaluation protocol for measuring the quality of Knowledge Graph Completion methods - the task of inferring new links to be added to a graph - typically involves a step which ranks every entity of a Knowledge Graph to assess their fit as a head or tail of a candidate link to be added. In Knowledge Graphs on a larger scale, this task rapidly becomes prohibitively heavy. Previous approaches mitigate this problem by using random sampling of entities to assess the quality of links predicted or suggested by a method. However, we show that this approach has serious limitations since the ranking metrics produced do not properly reflect true outcomes. In this paper, we present a thorough analysis of these effects along with the following findings. First, we empirically find and theoretically motivate why sampling uniformly at random vastly overestimates the ranking performance of a method. We show that this can be attributed to the effect of easy versus hard negative candidates. Second, we propose a framework that uses relational recommenders to guide the selection of candidates for evaluation. We provide both theoretical and empirical justification of our methodology, and find that simple and fast methods can work extremely well, and that they match advanced neural approaches. Even when a large portion of true candidates for a property are missed, the estimation barely deteriorates. With our proposed framework, we can reduce the time and computation needed similar to random sampling strategies while vastly improving the estimation; on ogbl-wikikg2, we show that accurate estimations of the full, filtered ranking can be obtained in 20 seconds instead of 30 minutes. We conclude that considerable computational effort can be saved by effective preprocessing and sampling methods and still reliably predict performance accurately of the true performance for the entire ranking procedure.

Ben Carterette, Rosie Jones, Gareth F. Jones et al.

Rapidly growing online podcast archives contain diverse content on a wide range of topics. These archives form an important resource for entertainment and professional use, but their value can only be realized if users can rapidly and reliably locate content of interest. Search for relevant content can be based on metadata provided by content creators, but also on transcripts of the spoken content itself. Excavating relevant content from deep within these audio streams for diverse types of information needs requires varying the approach to systems prototyping. We describe a set of diverse podcast information needs and different approaches to assessing retrieved content for relevance. We use these information needs in an investigation of the utility and effectiveness of these information sources. Based on our analysis, we recommend approaches for indexing and retrieving podcast content for ad hoc search.

Jussi Karlgren, Lennart E. Fahlén, Anders Wallberg et al.

This paper describes how home appliances might be enhanced to improve user awareness of energy usage. Households wish to lead comfortable and manageable lives. Balancing this reasonable desire with the environmental and political goal of reducing electricity usage is a challenge that we claim is best met through the design of interfaces that allows users better control of their usage and unobtrusively informs them of the actions of their peers. A set of design principles along these lines is formulated in this paper. We have built a fully functional prototype home appliance with a socially aware interface to signal the aggregate usage of the users peer group according to these principles, and present the prototype in the paper.

Rosie Jones, Hamed Zamani, Markus Schedl et al.

Podcasts are spoken documents across a wide-range of genres and styles, with growing listenership across the world, and a rapidly lowering barrier to entry for both listeners and creators. The great strides in search and recommendation in research and industry have yet to see impact in the podcast space, where recommendations are still largely driven by word of mouth. In this perspective paper, we highlight the many differences between podcasts and other media, and discuss our perspective on challenges and future research directions in the domain of podcast information access.

Jussi Karlgren

This paper describes how the current lexical similarity and analogy gold standards are built to conform to certain ideas about what the models they are designed to evaluate are used for. Topical relevance has always been the most important target notion for information access tools and related language technology technologies, and while this has proven a useful starting point for much of what information technology is used for, it does not always align well with other uses to which technologies are being put, most notably use cases from digital scholarship in the humanities or social sciences. This paper argues for more systematic formulation of requirements from the digital humanities and social sciences and more explicit description of the assumptions underlying model design.

Jussi Karlgren, Pentti Kanerva

High-dimensional distributed semantic spaces have proven useful and effective for aggregating and processing visual, auditory, and lexical information for many tasks related to human-generated data. Human language makes use of a large and varying number of features, lexical and constructional items as well as contextual and discourse-specific data of various types, which all interact to represent various aspects of communicative information. Some of these features are mostly local and useful for the organisation of e.g. argument structure of a predication; others are persistent over the course of a discourse and necessary for achieving a reasonable level of understanding of the content. This paper describes a model for high-dimensional representation for utterance and text level data including features such as constructions or contextual data, based on a mathematically principled and behaviourally plausible approach to representing linguistic information. The implementation of the representation is a straightforward extension of Random Indexing models previously used for lexical linguistic items. The paper shows how the implemented model is able to represent a broad range of linguistic features in a common integral framework of fixed dimensionality, which is computationally habitable, and which is suitable as a bridge between symbolic representations such as dependency analysis and continuous representations used e.g. in classifiers or further machine-learning approaches. This is achieved with operations on vectors that constitute a powerful computational algebra, accompanied with an associative memory for the vectors. The paper provides a technical overview of the framework and a worked through implemented example of how it can be applied to various types of linguistic features.

Rosie Jones, Ben Carterette, Ann Clifton et al.

The Podcast Track is new at the Text Retrieval Conference (TREC) in 2020. The podcast track was designed to encourage research into podcasts in the information retrieval and NLP research communities. The track consisted of two shared tasks: segment retrieval and summarization, both based on a dataset of over 100,000 podcast episodes (metadata, audio, and automatic transcripts) which was released concurrently with the track. The track generated considerable interest, attracted hundreds of new registrations to TREC and fifteen teams, mostly disjoint between search and summarization, made final submissions for assessment. Deep learning was the dominant experimental approach for both search experiments and summarization. This paper gives an overview of the tasks and the results of the participants' experiments. The track will return to TREC 2021 with the same two tasks, incorporating slight modifications in response to participant feedback.

Jussi Karlgren, Renee Li, Eva M Meyersson Milgrom

We use commercially available text analysis technology to process interview text data from a computational social science study. We find that topical clustering and terminological enrichment provide for convenient exploration and quantification of the responses. This makes it possible to generate and test hypotheses and to compare textual and non-textual variables, and saves analyst effort. We encourage studies in social science to use text analysis, especially for exploratory open-ended studies. We discuss how replicability requirements are met by text analysis technology. We note that the most recent learning models are not designed with transparency in mind, and that research requires a model to be editable and its decisions to be explainable. The tools available today, such as the one used in the present study, are not built for processing interview texts. While many of the variables under consideration are quantifiable using lexical statistics, we find that some interesting and potentially valuable features are difficult or impossible to automatise reliably at present. We note that there are some potentially interesting applications for traditional natural language processing mechanisms such as named entity recognition and anaphora resolution in this application area. We conclude with a suggestion for language technologists to investigate the challenge of processing interview data comprehensively, especially the interplay between question and response, and we encourage social science researchers not to hesitate to use text analysis tools, especially for the exploratory phase of processing interview data.?

Ann Clifton, Aasish Pappu, Sravana Reddy et al.

Podcasts are a relatively new form of audio media. Episodes appear on a regular cadence, and come in many different formats and levels of formality. They can be formal news journalism or conversational chat; fiction or non-fiction. They are rapidly growing in popularity and yet have been relatively little studied. As an audio format, podcasts are more varied in style and production types than, say, broadcast news, and contain many more genres than typically studied in video research. The medium is therefore a rich domain with many research avenues for the IR and NLP communities. We present the Spotify Podcast Dataset, a set of approximately 100K podcast episodes comprised of raw audio files along with accompanying ASR transcripts. This represents over 47,000 hours of transcribed audio, and is an order of magnitude larger than previous speech-to-text corpora.

Max Berggren, Jussi Karlgren, Robert Östling et al.

For the purposes of computational dialectology or other geographically bound text analysis tasks, texts must be annotated with their or their authors' location. Many texts are locatable through explicit labels but most have no explicit annotation of place. This paper describes a series of experiments to determine how positionally annotated microblog posts can be used to learn location-indicating words which then can be used to locate blog texts and their authors. A Gaussian distribution is used to model the locational qualities of words. We introduce the notion of placeness to describe how locational words are. We find that modelling word distributions to account for several locations and thus several Gaussian distributions per word, defining a filter which picks out words with high placeness based on their local distributional context, and aggregating locational information in a centroid for each text gives the most useful results. The results are applied to data in the Swedish language.

Kerry Zhang, Jussi Karlgren, Cheng Zhang et al.

There are multiple sides to every story, and while statistical topic models have been highly successful at topically summarizing the stories in corpora of text documents, they do not explicitly address the issue of learning the different sides, the viewpoints, expressed in the documents. In this paper, we show how these viewpoints can be learned completely unsupervised and represented in a human interpretable form. We use a novel approach of applying CorrLDA2 for this purpose, which learns topic-viewpoint relations that can be used to form groups of topics, where each group represents a viewpoint. A corpus of documents about the Israeli-Palestinian conflict is then used to demonstrate how a Palestinian and an Israeli viewpoint can be learned. By leveraging the magnitudes and signs of the feature weights of a linear SVM, we introduce a principled method to evaluate associations between topics and viewpoints. With this, we demonstrate, both quantitatively and qualitatively, that the learned topic groups are contextually coherent, and form consistently correct topic-viewpoint associations.