This paper presents our submission to the WMT 2023 Quality Estimation (QE) shared task 1 (sentence-level subtask). We propose a straightforward training data augmentation approach aimed at improving the correlation between QE model predictions and human quality assessments. Utilising eleven data augmentation approaches and six distinct language pairs, we systematically create augmented training sets by individually applying each method to the original training set of each respective language pair. By evaluating the performance gap between the model before and after training on the augmented dataset, as measured on the development set, we assess the effectiveness of each augmentation method. Experimental results reveal that synonym replacement via the Paraphrase Database (PPDB) yields the most substantial performance boost for language pairs English-German, English-Marathi and English-Gujarati, while for the remaining language pairs, methods such as contextual word embeddings-based words insertion, back translation, and direct paraphrasing prove to be more effective. Training the model on a more diverse and larger set of samples does confer further performance improvements for certain language pairs, albeit to a marginal extent, and this phenomenon is not universally applicable. At the time of submission, we select the model trained on the augmented dataset constructed using the respective most effective method to generate predictions for the test set in each language pair, except for the English-German. Despite not being highly competitive, our system consistently surpasses the baseline performance on most language pairs and secures a third-place ranking in the English-Marathi.

Performance prediction for Natural Language Processing (NLP) seeks to reduce the experimental burden resulting from the myriad of different evaluation scenarios, e.g., the combination of languages used in multilingual transfer. In this work, we explore the framework ofBayesian matrix factorisation for performance prediction, as many experimental settings in NLP can be naturally represented in matrix format. Our approach outperforms the state-of-the-art in several NLP benchmarks, including machine translation and cross-lingual entity linking. Furthermore, it also avoids hyperparameter tuning and is able to provide uncertainty estimates over predictions.

Most previous work in music emotion recognition assumes a single or a few song-level labels for the whole song. While it is known that different emotions can vary in intensity within a song, annotated data for this setup is scarce and difficult to obtain. In this work, we propose a method to predict emotion dynamics in song lyrics without song-level supervision. We frame each song as a time series and employ a State Space Model (SSM), combining a sentence-level emotion predictor with an Expectation-Maximization (EM) procedure to generate the full emotion dynamics. Our experiments show that applying our method consistently improves the performance of sentence-level baselines without requiring any annotated songs, making it ideal for limited training data scenarios. Further analysis through case studies shows the benefits of our method while also indicating the limitations and pointing to future directions.

Medical progress notes play a crucial role in documenting a patient’s hospital journey, including his or her condition, treatment plan, and any updates for healthcare providers. Automatic summarisation of a patient’s problems in the form of a “problem list” can aid stakeholders in understanding a patient’s condition, reducing workload and cognitive bias. BioNLP 2023 Shared Task 1A focusses on generating a list of diagnoses and problems from the provider’s progress notes during hospitalisation. In this paper, we introduce our proposed approach to this task, which integrates two complementary components. One component employs large language models (LLMs) for data augmentation; the other is an abstractive summarisation LLM with a novel pre-training objective for generating the patients’ problems summarised as a list. Our approach was ranked second among all submissions to the shared task. The performance of our model on the development and test datasets shows that our approach is more robust on unknown data, with an improvement of up to 3.1 points over the same size of the larger model.

State-of-the-art classification and regression models are often not well calibrated, and cannot reliably provide uncertainty estimates, limiting their utility in safety-critical applications such as clinical decision-making. While recent work has focused on calibration of classifiers, there is almost no work in NLP on calibration in a regression setting. In this paper, we quantify the calibration of pre- trained language models for text regression, both intrinsically and extrinsically. We further apply uncertainty estimates to augment training data in low-resource domains. Our experiments on three regression tasks in both self-training and active-learning settings show that uncertainty estimation can be used to increase overall performance and enhance model generalization.

Images are core components of multi-modal learning in natural language processing (NLP), and results have varied substantially as to whether images improve NLP tasks or not. One confounding effect has been that previous NLP research has generally focused on sophisticated tasks (in varying settings), generally applied to English only. We focus on text classification, in the context of assigning named entity classes to a given Wikipedia page, where images generally complement the text and the Wikipedia page can be in one of a number of different languages. Our experiments across a range of languages show that images complement NLP models (including BERT) trained without external pre-training, but when combined with BERT models pre-trained on large-scale external data, images contribute nothing.

Text generation from semantic graphs is traditionally performed with deterministic methods, which generate a unique description given an input graph. However, the generation problem admits a range of acceptable textual outputs, exhibiting lexical, syntactic and semantic variation. To address this disconnect, we present two main contributions. First, we propose a stochastic graph-to-text model, incorporating a latent variable in an encoder-decoder model, and its use in an ensemble. Second, to assess the diversity of the generated sentences, we propose a new automatic evaluation metric which jointly evaluates output diversity and quality in a multi-reference setting. We evaluate the models on WebNLG datasets in English and Russian, and show an ensemble of stochastic models produces diverse sets of generated sentences while, retaining similar quality to state-of-the-art models.

Hierarchical document categorisation is a special case of multi-label document categorisation, where there is a taxonomic hierarchy among the labels. While various approaches have been proposed for hierarchical document categorisation, there is no standard benchmark dataset, resulting in different methods being evaluated independently and there being no empirical consensus on what methods perform best. In this work, we examine different combinations of neural text encoders and hierarchical methods in an end-to-end framework, and evaluate over three datasets. We find that the performance of hierarchical document categorisation is determined not only by how the hierarchical information is modelled, but also the structure of the label hierarchy and class distribution.

‘Common Law’ judicial systems follow the doctrine of precedent, which means the legal principles articulated in court judgements are binding in subsequent cases in lower courts. For this reason, lawyers must search prior judgements for the legal principles that are relevant to their case. The difficulty for those within the legal profession is that the information that they are looking for may be contained within a few paragraphs or sentences, but those few paragraphs may be buried within a hundred-page document. In this study, we create a schema based on the relevant information that legal professionals seek within judgements and perform text classification based on it, with the aim of not only assisting lawyers in researching cases, but eventually enabling large-scale analysis of legal judgements to find trends in court outcomes over time.

Speech translation systems usually follow a pipeline approach, using word lattices as an intermediate representation. However, previous work assume access to the original transcriptions used to train the ASR system, which can limit applicability in real scenarios. In this work we propose an approach for speech translation through lattice transformations and neural models based on graph networks. Experimental results show that our approach reaches competitive performance without relying on transcriptions, while also being orders of magnitude faster than previous work.

In the context of document quality assessment, previous work has mainly focused on predicting the quality of a document relative to a putative gold standard, without paying attention to the subjectivity of this task. To imitate people’s disagreement over inherently subjective tasks such as rating the quality of a Wikipedia article, a document quality assessment system should provide not only a prediction of the article quality but also the uncertainty over its predictions. This motivates us to measure the uncertainty in document quality predictions, in addition to making the label prediction. Experimental results show that both Gaussian processes (GPs) and random forests (RFs) can yield competitive results in predicting the quality of Wikipedia articles, while providing an estimate of uncertainty when there is inconsistency in the quality labels from the Wikipedia contributors. We additionally evaluate our methods in the context of a semi-automated document quality class assignment decision-making process, where there is asymmetric risk associated with overestimates and underestimates of document quality. Our experiments suggest that GPs provide more reliable estimates in this context.

Scene graphs represent semantic information in images, which can help image captioning system to produce more descriptive outputs versus using only the image as context. Recent captioning approaches rely on ad-hoc approaches to obtain graphs for images. However, those graphs introduce noise and it is unclear the effect of parser errors on captioning accuracy. In this work, we investigate to what extent scene graphs can help image captioning. Our results show that a state-of-the-art scene graph parser can boost performance almost as much as the ground truth graphs, showing that the bottleneck currently resides more on the captioning models than on the performance of the scene graph parser.

Many NLP applications can be framed as a graph-to-sequence learning problem. Previous work proposing neural architectures on graph-to-sequence obtained promising results compared to grammar-based approaches but still rely on linearisation heuristics and/or standard recurrent networks to achieve the best performance. In this work propose a new model that encodes the full structural information contained in the graph. Our architecture couples the recently proposed Gated Graph Neural Networks with an input transformation that allows nodes and edges to have their own hidden representations, while tackling the parameter explosion problem present in previous work. Experimental results shows that our model outperforms strong baselines in generation from AMR graphs and syntax-based neural machine translation.

Non-contiguous word sequences are widely known to be important in modelling natural language. However they not explicitly encoded in common text representations. In this work we propose a model for text processing using string kernels, capable of flexibly representing non-contiguous sequences. Specifically, we derive a vectorised version of the string kernel algorithm and their gradients, allowing efficient hyperparameter optimisation as part of a Gaussian Process framework. Experiments on synthetic data and text regression for emotion analysis show the promise of this technique.

Emotion Analysis is the task of modelling latent emotions present in natural language. Labelled datasets for this task are scarce so learning good input text representations is not trivial. Using averaged word embeddings is a simple way to leverage unlabelled corpora to build text representations but this approach can be prone to noise either coming from the embedding themselves or the averaging procedure. In this paper we propose a model for Emotion Analysis using Gaussian Processes and kernels that are better suitable for functions that exhibit noisy behaviour. Empirical evaluations in a emotion prediction task show that our model outperforms commonly used baselines for regression.

Structural kernels are a flexible learning paradigm that has been widely used in Natural Language Processing. However, the problem of model selection in kernel-based methods is usually overlooked. Previous approaches mostly rely on setting default values for kernel hyperparameters or using grid search, which is slow and coarse-grained. In contrast, Bayesian methods allow efficient model selection by maximizing the evidence on the training data through gradient-based methods. In this paper we show how to perform this in the context of structural kernels by using Gaussian Processes. Experimental results on tree kernels show that this procedure results in better prediction performance compared to hyperparameter optimization via grid search. The framework proposed in this paper can be adapted to other structures besides trees, e.g., strings and graphs, thereby extending the utility of kernel-based methods.

We describe SProUTomat, a tool for daily building, testing and evaluating a complex general-purpose multilingual natural language text processor including its linguistic resources (lingware). Software and lingware are developed, maintained and extended in a distributed manner by multiple authors and projects, i.e., the source code stored in a version control system is modified frequently. The modular design of different, dedicated lingware modules like tokenizers, morphology, gazetteers, type hierarchy, rule formalism on the one hand increases flexibility and re-usability, but on the other hand may lead to fragility with respect to changes. Therefore, frequent testing as known from software engineering is necessary also for lingware to warrant a high level of quality and overall stability of the system. We describe the build, testing and evaluation methods for LT software and lingware we have developed on the basis of the open source, platform-independent Apache Ant tool and the configurable evaluation tool JTaCo.