The healthcare domain suffers from the spread of poor quality articles on the Internet. While manual efforts exist to check the quality of online healthcare articles, they are not sufficient to assess all those in circulation. Such quality assessment can be automated as a text classification task, however, explanations for the labels are necessary for the users to trust the model predictions. While current explainable systems tackle explanation generation as summarization, we propose a new approach based on question answering (QA) that allows us to generate explanations for multiple criteria using a single model. We show that this QA-based approach is competitive with the current state-of-the-art, and complements summarization-based models for explainable quality assessment. We also introduce a human evaluation protocol more appropriate than automatic metrics for the evaluation of explanation generation models.

Challenging problems such as open-domain question answering, fact checking, slot filling and entity linking require access to large, external knowledge sources. While some models do well on individual tasks, developing general models is difficult as each task might require computationally expensive indexing of custom knowledge sources, in addition to dedicated infrastructure. To catalyze research on models that condition on specific information in large textual resources, we present a benchmark for knowledge-intensive language tasks (KILT). All tasks in KILT are grounded in the same snapshot of Wikipedia, reducing engineering turnaround through the re-use of components, as well as accelerating research into task-agnostic memory architectures. We test both task-specific and general baselines, evaluating downstream performance in addition to the ability of the models to provide provenance. We find that a shared dense vector index coupled with a seq2seq model is a strong baseline, outperforming more tailor-made approaches for fact checking, open-domain question answering and dialogue, and yielding competitive results on entity linking and slot filling, by generating disambiguated text. KILT data and code are available at https://github.com/facebookresearch/KILT.

Recent progress in pre-trained language models led to systems that are able to generate text of an increasingly high quality. While several works have investigated the fluency and grammatical correctness of such models, it is still unclear to which extent the generated text is consistent with factual world knowledge. Here, we go beyond fluency and also investigate the verifiability of text generated by state-of-the-art pre-trained language models. A generated sentence is verifiable if it can be corroborated or disproved by Wikipedia, and we find that the verifiability of generated text strongly depends on the decoding strategy. In particular, we discover a tradeoff between factuality (i.e., the ability of generating Wikipedia corroborated text) and repetitiveness. While decoding strategies such as top-k and nucleus sampling lead to less repetitive generations, they also produce less verifiable text. Based on these finding, we introduce a simple and effective decoding strategy which, in comparison to previously used decoding strategies, produces less repetitive and more verifiable text.

The widespread use of word embeddings is associated with the recent successes of many natural language processing (NLP) systems. The key approach of popular models such as word2vec and GloVe is to learn dense vector representations from the context of words. More recently, other approaches have been proposed that incorporate different types of contextual information, including topics, dependency relations, n-grams, and sentiment. However, these models typically integrate only limited additional contextual information, and often in ad hoc ways. In this work, we introduce attr2vec, a novel framework for jointly learning embeddings for words and contextual attributes based on factorization machines. We perform experiments with different types of contextual information. Our experimental results on a text classification task demonstrate that using attr2vec to jointly learn embeddings for words and Part-of-Speech (POS) tags improves results compared to learning the embeddings independently. Moreover, we use attr2vec to train dependency-based embeddings and we show that they exhibit higher similarity between functionally related words compared to traditional approaches.

Taxonomies are often used to look up the concepts they contain in text documents (for instance, to classify a document). The more comprehensive the taxonomy, the higher recall the application has that uses the taxonomy. In this paper, we explore automatic taxonomy augmentation with paraphrases. We compare two state-of-the-art paraphrase models based on Moses, a statistical Machine Translation system, and a sequence-to-sequence neural network, trained on a paraphrase datasets with respect to their abilities to add novel nodes to an existing taxonomy from the risk domain. We conduct component-based and task-based evaluations. Our results show that paraphrasing is a viable method to enrich a taxonomy with more terms, and that Moses consistently outperforms the sequence-to-sequence neural model. To the best of our knowledge, this is the first approach to augment taxonomies with paraphrases.

Natural language processing (NLP) systems analyze and/or generate human language, typically on users’ behalf. One natural and necessary question that needs to be addressed in this context, both in research projects and in production settings, is the question how ethical the work is, both regarding the process and its outcome. Towards this end, we articulate a set of issues, propose a set of best practices, notably a process featuring an ethics review board, and sketch and how they could be meaningfully applied. Our main argument is that ethical outcomes ought to be achieved by design, i.e. by following a process aligned by ethical values. We also offer some response options for those facing ethics issues. While a number of previous works exist that discuss ethical issues, in particular around big data and machine learning, to the authors’ knowledge this is the first account of NLP and ethics from the perspective of a principled process.

We discuss the ethical implications of Natural Language Generation systems. We use one particular system as a case study to identify and classify issues, and we provide an ethics checklist, in the hope that future system designers may benefit from conducting their own ethics reviews based on our checklist.