Information flows by routes inside the network via mechanisms implemented in the model.These routes can be represented as graphs where nodes correspond to token representations and edges to computations.We automatically build these graphs in a top-down manner, for each prediction leaving only the most important nodes and edges.In contrast to the existing workflows relying on activation patching, we do this through attribution: this allows us to efficiently uncover existing circuits with just a single forward pass.Unlike with patching, we do not need a human to carefully design prediction templates, and we can extract information flow routes for any prediction (not just the ones among the allowed templates).As a result, we can analyze model behavior in general, for specific types of predictions, or different domains.We experiment with Llama 2 and show that some attention head roles are overall important, e.g.previous token heads and subword merging heads.Next, we find similarities in Llama 2 behavior when handling tokens of the same part of speech.Finally, we show that some model components can be specialized on domains such as coding or multilingual texts.

Ava Spataru, Eric Hambro, Elena Voita, Nicola Cancedda. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

While the problem of hallucinations in neural machine translation has long been recognized, so far the progress on its alleviation is very little.Indeed, recently it turned out that without artificially encouraging models to hallucinate, previously existing methods fall short and even the standard sequence log-probability is more informative.It means that internal characteristics of the model can give much more information than we expect, and before using external models and measures, we first need to ask: how far can we go if we use nothing but the translation model itself ?We propose to use a method that evaluates the percentage of the source contribution to a generated translation.Intuitively, hallucinations are translations "detached" from the source, hence they can be identified by low source contribution.This method improves detection accuracy for the most severe hallucinations by a factor of 2 and is able to alleviate hallucinations at test time on par with the previous best approach that relies on external models.Next, if we move away from internal model characteristics and allow external tools, we show that using sentence similarity from cross-lingual embeddings further improves these results.We release the code of our experiments.1

Although the problem of hallucinations in neural machine translation (NMT) has received some attention, research on this highly pathological phenomenon lacks solid ground.Previous work has been limited in several ways: it often resorts to artificial settings where the problem is amplified, it disregards some (common) types of hallucinations, and it does not validate adequacy of detection heuristics.In this paper, we set foundations for the study of NMT hallucinations.First, we work in a natural setting, i.e., in-domain data without artificial noise neither in training nor in inference.Next, we annotate a dataset of over 3.4k sentences indicating different kinds of critical errors and hallucinations.Then, we turn to detection methods and both revisit methods used previously and propose using glass-box uncertainty-based detectors.Overall, we show that for preventive settings, (i) previously used methods are largely inadequate, (ii) sequence log-probability works best and performs on par with reference-based methods.Finally, we propose DEHALLUCINATOR, a simple method for alleviating hallucinations at test time which significantly reduces the hallucinatory rate.

David Dale, Elena Voita, Janice Lam, Prangthip Hansanti, Christophe Ropers, Elahe Kalbassi, Cynthia Gao, Loic Barrault, Marta Costa-jussà. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

Elena Voita, Rico Sennrich, Ivan Titov. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Differently from the traditional statistical MT that decomposes the translation task into distinct separately learned components, neural machine translation uses a single neural network to model the entire translation process.Despite neural machine translation being defacto standard, it is still not clear how NMT models acquire different competences over the course of training, and how this mirrors the different models in traditional SMT.In this work, we look at the competences related to three core SMT components and find that during training, NMT first focuses on learning targetside language modeling, then improves translation quality approaching word-by-word translation, and finally learns more complicated reordering patterns.We show that this behavior holds for several models and language pairs.Additionally, we explain how such an understanding of the training process can be useful in practice and, as an example, show how it can be used to improve vanilla nonautoregressive neural machine translation by guiding teacher model selection.

Subword segmentation is widely used to address the open vocabulary problem in machine translation.The dominant approach to subword segmentation is Byte Pair Encoding (BPE), which keeps the most frequent words intact while splitting the rare ones into multiple tokens.While multiple segmentations are possible even with the same vocabulary, BPE splits words into unique sequences; this may prevent a model from better learning the compositionality of words and being robust to segmentation errors.So far, the only way to overcome this BPE imperfection, its deterministic nature, was to create another subword segmentation algorithm (Kudo, 2018).In contrast, we show that BPE itself incorporates the ability to produce multiple segmentations of the same word.We introduce BPE-dropout -simple and effective subword regularization method based on and compatible with conventional BPE.It stochastically corrupts the segmentation procedure of BPE, which leads to producing multiple segmentations within the same fixed BPE framework.Using BPE-dropout during training and the standard BPE during inference improves translation quality up to 2.3 BLEU compared to BPE and up to 0.9 BLEU compared to the previous subword regularization.

It has become a de-facto standard to represent words as elements of a vector space (word2vec, GloVe).While this approach is convenient, it is unnatural for language: words form a graph with a latent hierarchical structure, and this structure has to be revealed and encoded by word embeddings.We introduce Graph-Glove: unsupervised graph word representations which are learned end-to-end.In our setting, each word is a node in a weighted graph and the distance between words is the shortest path distance between the corresponding nodes.We adopt a recent method learning a representation of data in the form of a differentiable weighted graph and use it to modify the GloVe training algorithm.We show that our graph-based representations substantially outperform vector-based methods on word similarity and analogy tasks.Our analysis reveals that the structure of the learned graphs is hierarchical and similar to that of WordNet, the geometry is highly non-trivial and contains subgraphs with different local topology.1

To measure how well pretrained representations encode some linguistic property, it is common to use accuracy of a probe, i.e. a classifier trained to predict the property from the representations.Despite widespread adoption of probes, differences in their accuracy fail to adequately reflect differences in representations.For example, they do not substantially favour pretrained representations over randomly initialized ones.Analogously, their accuracy can be similar when probing for genuine linguistic labels and probing for random synthetic tasks.To see reasonable differences in accuracy with respect to these random baselines, previous work had to constrain either the amount of probe training data or its model size.Instead, we propose an alternative to the standard probes, information-theoretic probing with minimum description length (MDL).With MDL probing, training a probe to predict labels is recast as teaching it to effectively transmit the data.Therefore, the measure of interest changes from probe accuracy to the description length of labels given representations.In addition to probe quality, the description length evaluates 'the amount of effort' needed to achieve the quality.This amount of effort characterizes either (i) size of a probing model, or (ii) the amount of data needed to achieve the high quality.We consider two methods for estimating MDL which can be easily implemented on top of the standard probing pipelines: variational coding and online coding.We show that these methods agree in results and are more informative and stable than the standard probes.1

Though machine translation errors caused by the lack of context beyond one sentence have long been acknowledged, the development of context-aware NMT systems is hampered by several problems.Firstly, standard metrics are not sensitive to improvements in consistency in document-level translations.Secondly, previous work on context-aware NMT assumed that the sentence-aligned parallel data consisted of complete documents while in most practical scenarios such document-level data constitutes only a fraction of the available parallel data.To address the first issue, we perform a human study on an English-Russian subtitles dataset and identify deixis, ellipsis and lexical cohesion as three main sources of inconsistency.We then create test sets targeting these phenomena.To address the second shortcoming, we consider a set-up in which a much larger amount of sentence-level data is available compared to that aligned at the document level.We introduce a model that is suitable for this scenario and demonstrate major gains over a context-agnostic baseline on our new benchmarks without sacrificing performance as measured with BLEU. 1

Multi-head self-attention is a key component of the Transformer, a state-of-the-art architecture for neural machine translation.In this work we evaluate the contribution made by individual attention heads in the encoder to the overall performance of the model and analyze the roles played by them.We find that the most important and confident heads play consistent and often linguistically-interpretable roles.When pruning heads using a method based on stochastic gates and a differentiable relaxation of the L 0 penalty, we observe that specialized heads are last to be pruned.Our novel pruning method removes the vast majority of heads without seriously affecting performance.For example, on the English-Russian WMT dataset, pruning 38 out of 48 encoder heads results in a drop of only 0.15 BLEU. 1

Elena Voita, Rico Sennrich, Ivan Titov. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Elena Voita, Rico Sennrich, Ivan Titov. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

The dominant approach to sequence generation is to produce a sequence in some predefined order, e.g. left to right. In contrast, we propose a more general model that can generate the output sequence by inserting tokens in any arbitrary order. Our model learns decoding order as a result of its training procedure. Our experiments show that this model is superior to fixed order models on a number of sequence generation tasks, such as Machine Translation, Image-to-LaTeX and Image Captioning.

Standard machine translation systems process sentences in isolation and hence ignore extra-sentential information, even though extended context can both prevent mistakes in ambiguous cases and improve translation coherence.We introduce a context-aware neural machine translation model designed in such way that the flow of information from the extended context to the translation model can be controlled and analyzed.We experiment with an English-Russian subtitles dataset, and observe that much of what is captured by our model deals with improving pronoun translation.We measure correspondences between induced attention distributions and coreference relations and observe that the model implicitly captures anaphora.It is consistent with gains for sentences where pronouns need to be gendered in translation.Beside improvements in anaphoric cases, the model also improves in overall BLEU, both over its context-agnostic version (+0.7) and over simple concatenation of the context and source sentences (+0.6).