Roberta Rocca
Roberta Rocca
It takes words w(1), w(2),..., w(n-1) from a ComplexTextStim text elements, and returns forward language modeling predicted logits for w(n). Could be used in combo w/ `MetricExtractor` for entropy and...
would be useful to add info on what frequency bands each MelSpectrogramExtractor features represent
Currently, the `feature` argument for [LibrosaFeatureExtractor](https://github.com/PsychoinformaticsLab/pliers/blob/208a009c5d7e11cee660f8d28fd0dcb50d8252b8/pliers/extractors/audio.py#L150) (which selects the target librosa feature) is not stored in `log_attributes`. It may make sense to do so, as it is otherwise not possible...
For extractors such as the Bert encoding extractors, we stumbled upon the issue of whether/how to return results which are not strictly speaking "features", but which may nonetheless be of...
Need to settle on a way to handle non pip-installable modules and files. At the moment, this is done with with ad-hoc scripts and `MissingDependencyError` messages for `nltk` and `yamnet`....
Probably low priority but for the record: Dictionaries tend not to include inflected forms of verbs or nouns. For some lexical norms, it might make sense to assume that inflected...
* Contextualized Topic Models version: 2.2.0 * Python version: 3.8 * Operating System: macOs Monterey 12.5.1 ### Description https://github.com/MilaNLProc/contextualized-topic-models/blob/f3225055440b2ebf3bedb7143868954f1e1478d7/contextualized_topic_models/evaluation/measures.py#L166 This line throws an error with gensim>=4.0.0 ``` AttributeError: The vocab...
Hi there! Quick clarification question. To find topic words, it seems like you compute similarities between topic vectors and word vectors using the full-dimensionality vectors (i.e., not what you get...
Trying to build an analysis where dense predictors with NAs (e.g., word norms) are *not* adequately transformed should trigger a warning, but it currently doesn't. See for example `biue4`, where...
studyforrest comes with a number of pre-computed features that could be ingested. On top of that, transcripts are now available which makes it possible to extract language features for this...