Recent years have seen a growing number of publications that analyse Natural Language Understanding (NLU) datasets for superficial cues, whether they undermine the complexity of the tasks underlying those datasets and how they impact those models that are optimised and evaluated on this data. This structured survey provides an overview of the evolving research area by categorising reported weaknesses in models and datasets and the methods proposed to reveal and alleviate those weaknesses for the English language. We summarise and discuss the findings and conclude with a set of recommendations for possible future research directions. We hope that it will be a useful resource for researchers who propose new datasets to assess the suitability and quality of their data to evaluate various phenomena of interest, as well as those who propose novel NLU approaches, to further understand the implications of their improvements with respect to their model’s acquired capabilities.

We give an in-depth account of compositional matrix-space models (CMSMs), a type of generic models for natural language, wherein compositionality is realized via matrix multiplication. We argue for the structural plausibility of this model and show that it is able to cover and combine various common compositional natural language processing approaches. Then, we consider efficient task-specific learning methods for training CMSMs and evaluate their performance in compositionality prediction and sentiment analysis.

Convolutional sequence to sequence (CNN seq2seq) models have met success in abstractive summarization. However, their outputs often contain repetitive word sequences and logical inconsistencies, limiting the practicality of their application. In this paper, we find the reasons behind the repetition problem in CNN-based abstractive summarization through observing the attention map between the summaries with repetition and their corresponding source documents and mitigate the repetition problem. We propose to reduce the repetition in summaries by attention filter mechanism (ATTF) and sentence-level backtracking decoder (SBD), which dynamically redistributes attention over the input sequence as the output sentences are generated. The ATTF can record previously attended locations in the source document directly and prevent the decoder from attending to these locations. The SBD prevents the decoder from generating similar sentences more than once via backtracking at test. The proposed model outperforms the baselines in terms of ROUGE score, repeatedness, and readability. The results show that this approach generates high-quality summaries with minimal repetition and makes the reading experience better.

Authorship attribution – the computational task of identifying the author of a given text document within a set of possible candidates – has been attracting interest in Natural Language Processing research for many years. At the same time, significant advances have also been observed in the related field of author profiling, that is, the computational task of learning author demographics from text such as gender, age and others. The close relation between the two topics – both of which focused on gaining knowledge about the individual who wrote a piece of text – suggests that research in these fields may benefit from each other. To illustrate this, this work addresses the issue of author identification with the aid of author profiling methods, adding demographics predictions to an authorship attribution architecture that may be particularly suitable to extensions of this kind, namely, a stack of classifiers devoted to different aspects of the input text (words, characters and text distortion patterns.) The enriched model is evaluated across a range of text domains, languages and author profiling estimators, and its results are shown to compare favourably to those obtained by a standard authorship attribution method that does not have access to author demographics predictions.

Bilingual corpora are an essential resource used to cross the language barrier in multilingual natural language processing tasks. Among bilingual corpora, comparable corpora have been the subject of many studies as they are both frequent and easily available. In this paper, we propose to make use of formal concept analysis to first construct concept vectors which can be used to enhance comparable corpora through clustering techniques. We then show how one can extract bilingual lexicons of improved quality from these enhanced corpora. We finally show that the bilingual lexicons obtained can complement existing bilingual dictionaries and improve cross-language information retrieval systems.

It’s no secret that the commercial application of NLP technologies has exploded in recent years. From chatbots and virtual assistants to machine translation and sentiment analysis, NLP technologies are now being used in a wide variety of applications across a range of industries. With the increasing demand for technologies that can process human language, investors have been eager to get a piece of the action. In this article, we look at NLP startup funding over the past year, identifying the applications and domains that have received investment.