Foundational Hebrew NLP tasks such as segmentation, tagging and parsing, have relied to date on various versions of the Hebrew Treebank (HTB, Sima’an et al. 2001). However, the data in HTB, a single-source newswire corpus, is now over 30 years old, and does not cover many aspects of contemporary Hebrew on the web. This paper presents a new, freely available UD treebank of Hebrew stratified from a range of topics selected from Hebrew Wikipedia. In addition to introducing the corpus and evaluating the quality of its annotations, we deploy automatic validation tools based on grew (Guillaume, 2021), and conduct the first cross domain parsing experiments in Hebrew. We obtain new state-of-the-art (SOTA) results on UD NLP tasks, using a combination of the latest language modelling and some incremental improvements to existing transformer based approaches. We also release a new version of the UD HTB matching annotation scheme updates from our new corpus.
We study the performance of several popular neural part-of-speech taggers from the Universal Dependencies ecosystem on Mayan languages using a small corpus of 1435 annotated K’iche’ sentences consisting of approximately 10,000 tokens, with encouraging results: F1 scores 93%+ on lemmatisation, part-of-speech and morphological feature assignment. The high performance motivates a cross-language part-of-speech tagging study, where K’iche’-trained models are evaluated on two other Mayan languages, Kaqchikel and Uspanteko: performance on Kaqchikel is good, 63-85%, and on Uspanteko modest, 60-71%. Supporting experiments lead us to conclude the relative diversity of morphological features as a plausible explanation for the limiting factors in cross-language tagging performance, providing some direction for future sentence annotation and collection work to support these and other Mayan languages.
Linguistics predictability is the degree of confidence in which language unit (word, part of speech, etc.) will be the next in the sequence. Experiments have shown that the correct prediction simplifies the perception of a language unit and its integration into the context. As a result of an incorrect prediction, language processing slows down. Currently, to get a measure of the language unit predictability, a neurolinguistic experiment known as a cloze task has to be conducted on a large number of participants. Cloze tasks are resource-consuming and are criticized by some researchers as an insufficiently valid measure of predictability. In this paper, we compare different language models that attempt to simulate human respondents’ performance on the cloze task. Using a language model to create cloze task simulations would require significantly less time and conduct studies related to linguistic predictability.
Morphological analysis is one of the tasks that have been studied for years. Different techniques have been used to develop models for performing morphological analysis. Models based on finite state transducers have proved to be more suitable for languages with low available resources. In this paper, we have developed a method for weighting a morphological analyzer built using finite state transducers in order to disambiguate its results. The method is based on a word2vec model that is trained in a completely unsupervised way using raw untagged corpora and is able to capture the semantic meaning of the words. Most of the methods used for disambiguating the results of a morphological analyzer relied on having tagged corpora that need to manually built. Additionally, the method developed uses information about the token irrespective of its context unlike most of the other techniques that heavily rely on the word’s context to disambiguate its set of candidate analyses.