The field of natural language processing has seen impressive progress in recent years, with
neural network models replacing many of the traditional systems. A plethora of new models …

Existing paraphrase identification datasets lack sentence pairs that have high lexical overlap
without being paraphrases. Models trained on such data fail to distinguish pairs like flights …

Many natural language questions require qualitative, quantitative or logical comparisons
between two entities or events. This paper addresses the problem of improving the accuracy …

It is standard practice in speech & language technology to rank systems according to
performance on a test set held out for evaluation. However, few researchers apply statistical …

Temporary syntactic ambiguities arise when the beginning of a sentence is compatible with
multiple syntactic analyses. We inspect to which extent neural language models (LMs) …

This systematic literature review aims to evaluate and synthesize the effectiveness of various
embedding techniques—word embeddings, contextual word embeddings, and context …

Neural models often exploit superficial features to achieve good performance, rather than
deriving more general features. Overcoming this tendency is a central challenge in areas …

Abstract Machine learning (ML) and artificial intelligence (AI) approaches are often criticized
for their inherent bias and for their lack of control, accountability, and transparency …

Semitic morphologically-rich languages (MRLs) are characterized by extreme word
ambiguity. Because most vowels are omitted in standard texts, many of the words are …

Neural models often exploit superficial (“weak”) features to achieve good performance,
rather than deriving the more general (“strong”) features that we'd prefer a model to use …