Semi-parametric models, which augment generation with retrieval, have led to impressive results in language modeling and machine translation, due to their ability to retrieve fine-grained information from a datastore of examples. One of the most prominent approaches, kNN-MT, exhibits strong domain adaptation capabilities by retrieving tokens from domain-specific datastores (Khandelwal et al., 2021). However, kNN-MT requires an expensive retrieval operation for every single generated token, leading to a very low decoding speed (around 8 times slower than a parametric model). In this paper, we introduce a chunk-based kNN-MT model which retrieves chunks of tokens from the datastore, instead of a single token. We propose several strategies for incorporating the retrieved chunks into the generation process, and for selecting the steps at which the model needs to search for neighbors in the datastore. Experiments on machine translation in two settings, static and “on-the-fly” domain adaptation, show that the chunk-based kNN-MT model leads to significant speed-ups (up to 4 times) with only a small drop in translation quality.

Machine translation models struggle when translating out-of-domain text, which makes domain adaptation a topic of critical importance. However, most domain adaptation methods focus on fine-tuning or training the entire or part of the model on every new domain, which can be costly. On the other hand, semi-parametric models have been shown to successfully perform domain adaptation by retrieving examples from an in-domain datastore (Khandelwal et al., 2021). A drawback of these retrieval-augmented models, however, is that they tend to be substantially slower. In this paper, we explore several approaches to speed up nearest neighbors machine translation. We adapt the methods recently proposed by He et al. (2021) for language modeling, and introduce a simple but effective caching strategy that avoids performing retrieval when similar contexts have been seen before. Translation quality and runtimes for several domains show the effectiveness of the proposed solutions.

Transformers are unable to model long-term memories effectively, since the amount of computation they need to perform grows with the context length. While variations of efficient transformers have been proposed, they all have a finite memory capacity and are forced to drop old information. In this paper, we propose the ∞-former, which extends the vanilla transformer with an unbounded long-term memory. By making use of a continuous-space attention mechanism to attend over the long-term memory, the ∞-former’s attention complexity becomes independent of the context length, trading off memory length with precision.In order to control where precision is more important, ∞-former maintains “sticky memories,” being able to model arbitrarily long contexts while keeping the computation budget fixed.Experiments on a synthetic sorting task, language modeling, and document grounded dialogue generation demonstrate the ∞-former’s ability to retain information from long sequences.

Current state-of-the-art text generators build on powerful language models such as GPT-2, achieving impressive performance. However, to avoid degenerate text, they require sampling from a modified softmax, via temperature parameters or ad-hoc truncation techniques, as in top-k or nucleus sampling. This creates a mismatch between training and testing conditions. In this paper, we use the recently introduced entmax transformation to train and sample from a natively sparse language model, avoiding this mismatch. The result is a text generator with favorable performance in terms of fluency and consistency, fewer repetitions, and n-gram diversity closer to human text. In order to evaluate our model, we propose three new metrics for comparing sparse or truncated distributions: 𝜖-perplexity, sparsemax score, and Jensen-Shannon divergence. Human-evaluated experiments in story completion and dialogue generation show that entmax sampling leads to more engaging and coherent stories and conversations.

This paper presents our contribution to the Offensive Language Classification Task (English SubTask A) of Semeval 2020. We propose different Bert models trained on several offensive language classification and profanity datasets, and combine their output predictions in an ensemble model. We experimented with different ensemble approaches, such as SVMs, Gradient boosting, AdaBoosting and Logistic Regression. We further propose an under-sampling approach of the current SOLID dataset, which removed the most uncertain partitions of the dataset, increasing the recall of the dataset. Our best model, an average ensemble of four different Bert models, achieved 11th place out of 82 participants with a macro F1 score of 0.91344 in the English SubTask A.

In the medical domain and other scientific areas, it is often important to recognize different levels of hierarchy in mentions, such as those related to specific symptoms or diseases associated with different anatomical regions. Unlike previous approaches, we build a transition-based parser that explicitly models an arbitrary number of hierarchical and nested mentions, and propose a loss that encourages correct predictions of higher-level mentions. We further introduce a set of modifier classes which introduces certain concepts that change the meaning of an entity, such as absence, or uncertainty about a given disease. Our proposed model achieves state-of-the-art results in medical entity recognition datasets, using both nested and hierarchical mentions.

Named entity recognition (NER) and entity linking (EL) are two fundamentally related tasks, since in order to perform EL, first the mentions to entities have to be detected. However, most entity linking approaches disregard the mention detection part, assuming that the correct mentions have been previously detected. In this paper, we perform joint learning of NER and EL to leverage their relatedness and obtain a more robust and generalisable system. For that, we introduce a model inspired by the Stack-LSTM approach. We observe that, in fact, doing multi-task learning of NER and EL improves the performance in both tasks when comparing with models trained with individual objectives. Furthermore, we achieve results competitive with the state-of-the-art in both NER and EL.

We present a new neural model for text summarization that first extracts sentences from a document and then compresses them. The pro-posed model offers a balance that sidesteps thedifficulties in abstractive methods while gener-ating more concise summaries than extractivemethods. In addition, our model dynamically determines the length of the output summary based on the gold summaries it observes during training and does not require length constraints typical to extractive summarization. The model achieves state-of-the-art results on the CNN/DailyMail and Newsroom datasets, improving over current extractive and abstractive methods. Human evaluations demonstratethat our model generates concise and informa-tive summaries. We also make available a new dataset of oracle compressive summaries derived automatically from the CNN/DailyMailreference summaries.