Modern classification models tend to struggle when the amount of annotated data is scarce. To overcome this issue, several neural few-shot classification models have emerged, yielding significant progress over time, both in Computer Vision and Natural Language Processing. In the latter, such models used to rely on fixed word embeddings, before the advent of transformers. Additionally, some models used in Computer Vision are yet to be tested in NLP applications. In this paper, we compare all these models, first adapting those made in the field of image processing to NLP, and second providing them access to transformers. We then test these models equipped with the same transformer-based encoder on the intent detection task, known for having a large amount of classes. Our results reveal that while methods perform almost equally on the ARSC dataset, this is not the case for the Intent Detection task, where most recent and supposedly best competitors perform worse than older and simpler ones (while all are are given access to transformers). We also show that a simple baseline is surprisingly strong. All the new developed models as well as the evaluation framework are made publicly available.

Recent research considers few-shot intent detection as a meta-learning problem: the model is learning to learn from a consecutive set of small tasks named episodes. In this work, we propose ProtAugment, a meta-learning algorithm for short texts classification (the intent detection task). ProtAugment is a novel extension of Prototypical Networks, that limits overfitting on the bias introduced by the few-shots classification objective at each episode. It relies on diverse paraphrasing: a conditional language model is first fine-tuned for paraphrasing, and diversity is later introduced at the decoding stage at each meta-learning episode. The diverse paraphrasing is unsupervised as it is applied to unlabelled data, and then fueled to the Prototypical Network training objective as a consistency loss. ProtAugment is the state-of-the-art method for intent detection meta-learning, at no extra labeling efforts and without the need to fine-tune a conditional language model on a given application domain.

In this paper, we introduce a state-of-the-art pseudo-labeling technique for few-shot intent detection. We devise a folding/unfolding hierarchical clustering algorithm which assigns weighted pseudo-labels to unlabeled user utterances. We show that our two-step method yields significant improvement over existing solutions. This performance is achieved on multiple intent detection datasets, even in more challenging situations where the number of classes is large or when the dataset is highly imbalanced. Moreover, we confirm this results on the more general text classification task. We also demonstrate that our approach nicely complements existing solutions, thereby providing an even stronger state-of-the-art ensemble method.

We present a neural model for question generation from knowledge graphs triples in a “Zero-shot” setup, that is generating questions for predicate, subject types or object types that were not seen at training time. Our model leverages triples occurrences in the natural language corpus in a encoder-decoder architecture, paired with an original part-of-speech copy action mechanism to generate questions. Benchmark and human evaluation show that our model outperforms state-of-the-art on this task.

While Wikipedia exists in 287 languages, its content is unevenly distributed among them. In this work, we investigate the generation of open domain Wikipedia summaries in underserved languages using structured data from Wikidata. To this end, we propose a neural network architecture equipped with copy actions that learns to generate single-sentence and comprehensible textual summaries from Wikidata triples. We demonstrate the effectiveness of the proposed approach by evaluating it against a set of baselines on two languages of different natures: Arabic, a morphological rich language with a larger vocabulary than English, and Esperanto, a constructed language known for its easy acquisition.

Relation Discovery discovers predicates (relation types) from a text corpus relying on the co-occurrence of two named entities in the same sentence. This is a very narrowing constraint: it represents only a small fraction of all relation mentions in practice. In this paper we propose a high recall approach for Open IE, which enables covering up to 16 times more sentences in a large corpus. Comparison against OpenIE systems shows that our proposed approach achieves 28% improvement over the highest recall OpenIE system and 6% improvement in precision than the same system.

Learning word embeddings on large unlabeled corpus has been shown to be successful in improving many natural language tasks. The most efficient and popular approaches learn or retrofit such representations using additional external data. Resulting embeddings are generally better than their corpus-only counterparts, although such resources cover a fraction of words in the vocabulary. In this paper, we propose a new approach, Dict2vec, based on one of the largest yet refined datasource for describing words – natural language dictionaries. Dict2vec builds new word pairs from dictionary entries so that semantically-related words are moved closer, and negative sampling filters out pairs whose words are unrelated in dictionaries. We evaluate the word representations obtained using Dict2vec on eleven datasets for the word similarity task and on four datasets for a text classification task.