Transformer architectures have achieved state- of-the-art results on a variety of natural language processing (NLP) tasks. However, their attention mechanism comes with a quadratic complexity in sequence lengths, making the computational overhead prohibitive, especially for long sequences. Attention context can be seen as a random-access memory with each token taking a slot. Under this perspective, the memory size grows linearly with the sequence length, and so does the overhead of reading from it. One way to improve the efficiency is to bound the memory size. We show that disparate approaches can be subsumed into one abstraction, attention with bounded-memory control (ABC), and they vary in their organization of the memory. ABC reveals new, unexplored possibilities. First, it connects several efficient attention variants that would otherwise seem apart. Second, this abstraction gives new insights—an established approach (Wang et al., 2020b) previously thought to not be applicable in causal attention, actually is. Last, we present a new instance of ABC, which draws inspiration from existing ABC approaches, but replaces their heuristic memory-organizing functions with a learned, contextualized one. Our experiments on language modeling, machine translation, and masked language model finetuning show that our approach outperforms previous efficient attention models; compared to the strong transformer baselines, it significantly improves the inference time and space efficiency with no or negligible accuracy loss.

Representation learning for text via pretraining a language model on a large corpus has become a standard starting point for building NLP systems. This approach stands in contrast to autoencoders, also trained on raw text, but with the objective of learning to encode each input as a vector that allows full reconstruction. Autoencoders are attractive because of their latent space structure and generative properties. We therefore explore the construction of a sentence-level autoencoder from a pretrained, frozen transformer language model. We adapt the masked language modeling objective as a generative, denoising one, while only training a sentence bottleneck and a single-layer modified transformer decoder. We demonstrate that the sentence representations discovered by our model achieve better quality than previous methods that extract representations from pretrained transformers on text similarity tasks, style transfer (an example of controlled generation), and single-sentence classification tasks in the GLUE benchmark, while using fewer parameters than large pretrained models.

Transformers have outperformed recurrent neural networks (RNNs) in natural language generation. But this comes with a signifi- cant computational cost, as the attention mechanism’s complexity scales quadratically with sequence length. Efficient transformer variants have received increasing interest in recent works. Among them, a linear-complexity recurrent variant has proven well suited for autoregressive generation. It approximates the softmax attention with randomized or heuristic feature maps, but can be difficult to train and may yield suboptimal accuracy. This work aims to convert a pretrained transformer into its efficient recurrent counterpart, improving efficiency while maintaining accuracy. Specifically, we propose a swap-then-finetune procedure: in an off-the-shelf pretrained transformer, we replace the softmax attention with its linear-complexity recurrent alternative and then finetune. With a learned feature map, our approach provides an improved tradeoff between efficiency and accuracy over the standard transformer and other recurrent variants. We also show that the finetuning process has lower training cost relative to training these recurrent variants from scratch. As many models for natural language tasks are increasingly dependent on large-scale pretrained transformers, this work presents a viable approach to improving inference efficiency without repeating the expensive pretraining process.

Language models have emerged as a central component across NLP, and a great deal of progress depends on the ability to cheaply adapt them (e.g., through finetuning) to new domains and tasks. A language model’s vocabulary—typically selected before training and permanently fixed later—affects its size and is part of what makes it resistant to such adaptation. Prior work has used compositional input embeddings based on surface forms to ameliorate this issue. In this work, we go one step beyond and propose a fully compositional output embedding layer for language models, which is further grounded in information from a structured lexicon (WordNet), namely semantically related words and free-text definitions. To our knowledge, the result is the first word-level language model with a size that does not depend on the training vocabulary. We evaluate the model on conventional language modeling as well as challenging cross-domain settings with an open vocabulary, finding that it matches or outperforms previous state-of-the-art output embedding methods and adaptation approaches. Our analysis attributes the improvements to sample efficiency: our model is more accurate for low-frequency words.

Text alignment finds application in tasks such as citation recommendation and plagiarism detection. Existing alignment methods operate at a single, predefined level and cannot learn to align texts at, for example, sentence and document levels. We propose a new learning approach that equips previously established hierarchical attention encoders for representing documents with a cross-document attention component, enabling structural comparisons across different levels (document-to-document and sentence-to-document). Our component is weakly supervised from document pairs and can align at multiple levels. Our evaluation on predicting document-to-document relationships and sentence-to-document relationships on the tasks of citation recommendation and plagiarism detection shows that our approach outperforms previously established hierarchical, attention encoders based on recurrent and transformer contextualization that are unaware of structural correspondence between documents.

Text autoencoders are commonly used for conditional generation tasks such as style transfer. We propose methods which are plug and play, where any pretrained autoencoder can be used, and only require learning a mapping within the autoencoder’s embedding space, training embedding-to-embedding (Emb2Emb). This reduces the need for labeled training data for the task and makes the training procedure more efficient. Crucial to the success of this method is a loss term for keeping the mapped embedding on the manifold of the autoencoder and a mapping which is trained to navigate the manifold by learning offset vectors. Evaluations on style transfer tasks both with and without sequence-to-sequence supervision show that our method performs better than or comparable to strong baselines while being up to four times faster.

Neural text classification models typically treat output labels as categorical variables that lack description and semantics. This forces their parametrization to be dependent on the label set size, and, hence, they are unable to scale to large label sets and generalize to unseen ones. Existing joint input-label text models overcome these issues by exploiting label descriptions, but they are unable to capture complex label relationships, have rigid parametrization, and their gains on unseen labels happen often at the expense of weak performance on the labels seen during training. In this paper, we propose a new input-label model that generalizes over previous such models, addresses their limitations, and does not compromise performance on seen labels. The model consists of a joint nonlinear input-label embedding with controllable capacity and a joint-space-dependent classification unit that is trained with cross-entropy loss to optimize classification performance. We evaluate models on full-resource and low- or zero-resource text classification of multilingual news and biomedical text with a large label set. Our model outperforms monolingual and multilingual models that do not leverage label semantics and previous joint input-label space models in both scenarios.

Neural sequence-to-sequence networks with attention have achieved remarkable performance for machine translation. One of the reasons for their effectiveness is their ability to capture relevant source-side contextual information at each time-step prediction through an attention mechanism. However, the target-side context is solely based on the sequence model which, in practice, is prone to a recency bias and lacks the ability to capture effectively non-sequential dependencies among words. To address this limitation, we propose a target-side-attentive residual recurrent network for decoding, where attention over previous words contributes directly to the prediction of the next word. The residual learning facilitates the flow of information from the distant past and is able to emphasize any of the previously translated words, hence it gains access to a wider context. The proposed model outperforms a neural MT baseline as well as a memory and self-attention network on three language pairs. The analysis of the attention learned by the decoder confirms that it emphasizes a wider context, and that it captures syntactic-like structures.

Neural Machine Translation (NMT) can be improved by including document-level contextual information. For this purpose, we propose a hierarchical attention model to capture the context in a structured and dynamic manner. The model is integrated in the original NMT architecture as another level of abstraction, conditioning on the NMT model’s own previous hidden states. Experiments show that hierarchical attention significantly improves the BLEU score over a strong NMT baseline with the state-of-the-art in context-aware methods, and that both the encoder and decoder benefit from context in complementary ways.

Tying the weights of the target word embeddings with the target word classifiers of neural machine translation models leads to faster training and often to better translation quality. Given the success of this parameter sharing, we investigate other forms of sharing in between no sharing and hard equality of parameters. In particular, we propose a structure-aware output layer which captures the semantic structure of the output space of words within a joint input-output embedding. The model is a generalized form of weight tying which shares parameters but allows learning a more flexible relationship with input word embeddings and allows the effective capacity of the output layer to be controlled. In addition, the model shares weights across output classifiers and translation contexts which allows it to better leverage prior knowledge about them. Our evaluation on English-to-Finnish and English-to-German datasets shows the effectiveness of the method against strong encoder-decoder baselines trained with or without weight tying.

This paper demonstrates that word sense disambiguation (WSD) can improve neural machine translation (NMT) by widening the source context considered when modeling the senses of potentially ambiguous words. We first introduce three adaptive clustering algorithms for WSD, based on k-means, Chinese restaurant processes, and random walks, which are then applied to large word contexts represented in a low-rank space and evaluated on SemEval shared-task data. We then learn word vectors jointly with sense vectors defined by our best WSD method, within a state-of-the-art NMT system. We show that the concatenation of these vectors, and the use of a sense selection mechanism based on the weighted average of sense vectors, outperforms several baselines including sense-aware ones. This is demonstrated by translation on five language pairs. The improvements are more than 1 BLEU point over strong NMT baselines, +4% accuracy over all ambiguous nouns and verbs, or +20% when scored manually over several challenging words.

We present the first prototype of the SUMMA Platform: an integrated platform for multilingual media monitoring. The platform contains a rich suite of low-level and high-level natural language processing technologies: automatic speech recognition of broadcast media, machine translation, automated tagging and classification of named entities, semantic parsing to detect relationships between entities, and automatic construction / augmentation of factual knowledge bases. Implemented on the Docker platform, it can easily be deployed, customised, and scaled to large volumes of incoming media streams.

Hierarchical attention networks have recently achieved remarkable performance for document classification in a given language. However, when multilingual document collections are considered, training such models separately for each language entails linear parameter growth and lack of cross-language transfer. Learning a single multilingual model with fewer parameters is therefore a challenging but potentially beneficial objective. To this end, we propose multilingual hierarchical attention networks for learning document structures, with shared encoders and/or shared attention mechanisms across languages, using multi-task learning and an aligned semantic space as input. We evaluate the proposed models on multilingual document classification with disjoint label sets, on a large dataset which we provide, with 600k news documents in 8 languages, and 5k labels. The multilingual models outperform monolingual ones in low-resource as well as full-resource settings, and use fewer parameters, thus confirming their computational efficiency and the utility of cross-language transfer.