Language models have become a key step to achieve state-of-the art results in many
different Natural Language Processing (NLP) tasks. Leveraging the huge amount of …

We demonstrate that replacing an LSTM encoder with a self-attentive architecture can lead
to improvements to a state-of-the-art discriminative constituency parser. The use of attention …

We show that constituency parsing benefits from unsupervised pre-training across a variety
of languages and a range of pre-training conditions. We first compare the benefits of no pre …

Multiword expressions (MWEs) are a class of linguistic forms spanning conventional word
boundaries that are both idiosyncratic and pervasive across different languages. The …

We present extensions to a continuous-state dependency parsing method that makes it
applicable to morphologically rich languages. Starting with a high-performance transition …

The last few years have seen a surge in the number of accurate, fast, publicly available
dependency parsers. At the same time, the use of dependency parsing in NLP applications …

We present LEMMING, a modular log-linear model that jointly models lemmatization and
tagging and supports the integration of arbitrary global features. It is trainable on corpora …

Abstract Machine learning algorithms that automatically score scientific explanations can be
used to measure students' conceptual understanding, identify gaps in their reasoning, and …

Abstract Large Pre-trained Language Models (PLMs) have become ubiquitous in the
development of language understanding technology and lie at the heart of many artificial …

This paper describes a parsing model that combines the exact dynamic programming of
CRF parsing with the rich nonlinear featurization of neural net approaches. Our model is …