Related papers: Evaluating historical text normalization systems: …
There is no consensus on the state-of-the-art approach to historical text normalization. Many techniques have been proposed, including rule-based methods, distance metrics, character-based statistical machine translation, and neural…
To be informative, an evaluation must measure how well systems generalize to realistic unseen data. We identify limitations of and propose improvements to current evaluations of text-to-SQL systems. First, we compare human-generated and…
Natural-language processing of historical documents is complicated by the abundance of variant spellings and lack of annotated data. A common approach is to normalize the spelling of historical words to modern forms. We explore the…
Neural network models have been very successful in natural language inference, with the best models reaching 90% accuracy in some benchmarks. However, the success of these models turns out to be largely benchmark specific. We show that…
How well do neural networks generalize? Even for grammar induction tasks, where the target generalization is fully known, previous works have left the question open, testing very limited ranges beyond the training set and using different…
The continued rise of neural networks and large language models in the more recent past has altered the natural language processing landscape, enabling new approaches towards typical language tasks and achieving mainstream success. Despite…
Historical text normalization often relies on small training datasets. Recent work has shown that multi-task learning can lead to significant improvements by exploiting synergies with related datasets, but there has been no systematic study…
Deep learning models for semantics are generally evaluated using naturalistic corpora. Adversarial methods, in which models are evaluated on new examples with known semantic properties, have begun to reveal that good performance at these…
Prior knowledge has been shown very useful to address many natural language processing tasks. Many approaches have been proposed to formalise a variety of knowledge, however, whether the proposed approach is robust or sensitive to the…
One of the challenges with finetuning pretrained language models (PLMs) is that their tokenizer is optimized for the language(s) it was pretrained on, but brittle when it comes to previously unseen variations in the data. This can for…
In this thesis, I refine our understanding as to what conclusions we can reach from coreference-based evaluations by expanding existing evaluation practices and considering the extent to which evaluation results are either converging or…
To what extent can neural network models learn generalizations about language structure, and how do we find out what they have learned? We explore these questions by training neural models for a range of natural language processing tasks on…
We propose neural models that can normalize text by considering the similarities of word strings and sounds. We experimentally compared a model that considers the similarities of both word strings and sounds, a model that considers only the…
In this paper, we apply different NMT models to the problem of historical spelling normalization for five languages: English, German, Hungarian, Icelandic, and Swedish. The NMT models are at different levels, have different attention…
This paper presents an in-depth investigation on integrating neural language models in translation systems. Scaling neural language models is a difficult task, but crucial for real-world applications. This paper evaluates the impact on…
A recent line of work in natural language processing has aimed to combine language models and topic models. These topic-guided language models augment neural language models with topic models, unsupervised learning methods that can discover…
Does normalization help Part-of-Speech (POS) tagging accuracy on noisy, non-canonical data? To the best of our knowledge, little is known on the actual impact of normalization in a real-world scenario, where gold error detection is not…
Historic variations of spelling poses a challenge for full-text search or natural language processing on historical digitized texts. To minimize the gap between the historic orthography and contemporary spelling, usually an automatic…
Numerous models for grounded language understanding have been recently proposed, including (i) generic models that can be easily adapted to any given task and (ii) intuitively appealing modular models that require background knowledge to be…
Recently, there has been much interest in the question of whether deep natural language understanding models exhibit systematicity; generalizing such that units like words make consistent contributions to the meaning of the sentences in…