Transcripts of spontaneous human speech present a significant obstacle for traditional NER models. The lack of grammatical structure of spoken utterances and word errors introduced by the ASR make downstream NLP tasks challenging. In this paper, we examine in detail the complex relationship between ASR and NER errors which limit the ability of NER models to recover entity mentions from spontaneous speech transcripts. Using publicly available benchmark datasets (SWNE, Earnings-21, OntoNotes), we present the full taxonomy of ASR-NER errors and measure their true impact on entity recognition. We find that NER models fail spectacularly even if no word errors are introduced by the ASR. We also show why the F1 score is inadequate to evaluate NER models on conversational transcripts.

Models are increasing in size and complexity in the hunt for SOTA. But what if those 2%increase in performance does not make a difference in a production use case? Maybe benefits from a smaller, faster model outweigh those slight performance gains. Also, equally good performance across languages in multilingual tasks is more important than SOTA results on a single one. We present the biggest, unified, multilingual collection of sentiment analysis datasets. We use these to assess 11 models and 80 high-quality sentiment datasets (out of 342 raw datasets collected) in 27 languages and included results on the internally annotated datasets. We deeply evaluate multiple setups, including fine-tuning transformer-based models for measuring performance. We compare results in numerous dimensions addressing the imbalance in both languages coverage and dataset sizes. Finally, we present some best practices for working with such a massive collection of datasets and models for a multi-lingual perspective.

The popularity of social media makes politicians use it for political advertisement. Therefore, social media is full of electoral agitation (electioneering), especially during the election campaigns. The election administration cannot track the spread and quantity of messages that count as agitation under the election code. It addresses a crucial problem, while also uncovering a niche that has not been effectively targeted so far. Hence, we present the first publicly open data set for detecting electoral agitation in the Polish language. It contains 6,112 human-annotated tweets tagged with four legally conditioned categories. We achieved a 0.66 inter-annotator agreement (Cohen’s kappa score). An additional annotator resolved the mismatches between the first two improving the consistency and complexity of the annotation process. The newly created data set was used to fine-tune a Polish Language Model called HerBERT (achieving a 68% F1 score). We also present a number of potential use cases for such data sets and models, enriching the paper with an analysis of the Polish 2020 Presidential Election on Twitter.

Political campaigns are full of political ads posted by candidates on social media. Political advertisements constitute a basic form of campaigning, subjected to various social requirements. We present the first publicly open dataset for detecting specific text chunks and categories of political advertising in the Polish language. It contains 1,705 human-annotated tweets tagged with nine categories, which constitute campaigning under Polish electoral law. We achieved a 0.65 inter-annotator agreement (Cohen’s kappa score). An additional annotator resolved the mismatches between the first two annotators improving the consistency and complexity of the annotation process. We used the newly created dataset to train a well established neural tagger (achieving a 70% percent points F1 score). We also present a possible direction of use cases for such datasets and models with an initial analysis of the Polish 2020 Presidential Elections on Twitter.

Natural language processing of conversational speech requires the availability of high-quality transcripts. In this paper, we express our skepticism towards the recent reports of very low Word Error Rates (WERs) achieved by modern Automatic Speech Recognition (ASR) systems on benchmark datasets. We outline several problems with popular benchmarks and compare three state-of-the-art commercial ASR systems on an internal dataset of real-life spontaneous human conversations and HUB’05 public benchmark. We show that WERs are significantly higher than the best reported results. We formulate a set of guidelines which may aid in the creation of real-life, multi-domain datasets with high quality annotations for training and testing of robust ASR systems.