Several methods have been proposed for classifying long textual documents using Transformers. However, there is a lack of consensus on a benchmark to enable a fair comparison among different approaches. In this paper, we provide a comprehensive evaluation of the relative efficacy measured against various baselines and diverse datasets — both in terms of accuracy as well as time and space overheads. Our datasets cover binary, multi-class, and multi-label classification tasks and represent various ways information is organized in a long text (e.g. information that is critical to making the classification decision is at the beginning or towards the end of the document). Our results show that more complex models often fail to outperform simple baselines and yield inconsistent performance across datasets. These findings emphasize the need for future studies to consider comprehensive baselines and datasets that better represent the task of long document classification to develop robust models.

Measuring bias is key for better understanding and addressing unfairness in NLP/ML models. This is often done via fairness metrics, which quantify the differences in a model’s behaviour across a range of demographic groups. In this work, we shed more light on the differences and similarities between the fairness metrics used in NLP. First, we unify a broad range of existing metrics under three generalized fairness metrics, revealing the connections between them. Next, we carry out an extensive empirical comparison of existing metrics and demonstrate that the observed differences in bias measurement can be systematically explained via differences in parameter choices for our generalized metrics.

Many existing approaches for interpreting text classification models focus on providing importance scores for parts of the input text, such as words, but without a way to test or improve the interpretation method itself. This has the effect of compounding the problem of understanding or building trust in the model, with the interpretation method itself adding to the opacity of the model. Further, importance scores on individual examples are usually not enough to provide a sufficient picture of model behavior. To address these concerns, we propose MOXIE (MOdeling conteXt-sensitive InfluencE of words) with an aim to enable a richer interface for a user to interact with the model being interpreted and to produce testable predictions. In particular, we aim to make predictions for importance scores, counterfactuals and learned biases with MOXIE. In addition, with a global learning objective, MOXIE provides a clear path for testing and improving itself. We evaluate the reliability and efficiency of MOXIE on the task of sentiment analysis.

Matching a seller listed item to an appropriate product has become a fundamental and one of the most significant step for e-commerce platforms for product based experience. It has a huge impact on making the search effective, search engine optimization, providing product reviews and product price estimation etc. along with many other advantages for a better user experience. As significant and vital it has become, the challenge to tackle the complexity has become huge with the exponential growth of individual and business sellers trading millions of products everyday. We explored two approaches; classification based on shallow neural network and similarity based on deep siamese network. These models outperform the baseline by more than 5% in term of accuracy and are capable of extremely efficient training and inference.

Statistical Machine Translation (SMT) relies on the availability of rich parallel corpora. However, in the case of under-resourced languages or some specific domains, parallel corpora are not readily available. This leads to under-performing machine translation systems in those sparse data settings. To overcome the low availability of parallel resources the machine translation community has recognized the potential of using comparable resources as training data. However, most efforts have been related to European languages and less in middle-east languages. In this study, we report comparable corpora created from news articles for the pair English ―{Arabic, Persian, Urdu} languages. The data has been collected over a period of a year, entails Arabic, Persian and Urdu languages. Furthermore using the English as a pivot language, comparable corpora that involve more than one language can be created, e.g. English- Arabic - Persian, English - Arabic - Urdu, English ― Urdu - Persian, etc. Upon request the data can be provided for research purposes.

The University of Sheffield (USFD) participated in the International Workshop for Spoken Language Translation (IWSLT) in 2014. In this paper, we will introduce the USFD SLT system for IWSLT. Automatic speech recognition (ASR) is achieved by two multi-pass deep neural network systems with adaptation and rescoring techniques. Machine translation (MT) is achieved by a phrase-based system. The USFD primary system incorporates state-of-the-art ASR and MT techniques and gives a BLEU score of 23.45 and 14.75 on the English-to-French and English-to-German speech-to-text translation task with the IWSLT 2014 data. The USFD contrastive systems explore the integration of ASR and MT by using a quality estimation system to rescore the ASR outputs, optimising towards better translation. This gives a further 0.54 and 0.26 BLEU improvement respectively on the IWSLT 2012 and 2014 evaluation data.

We present a new version of QUEST ― an open source framework for machine translation quality estimation ― which brings a number of improvements: (i) it provides a Web interface and functionalities such that non-expert users, e.g. translators or lay-users of machine translations, can get quality predictions (or internal features of the framework) for translations without having to install the toolkit, obtain resources or build prediction models; (ii) it significantly improves over the previous runtime performance by keeping resources (such as language models) in memory; (iii) it provides an option for users to submit the source text only and automatically obtain translations from Bing Translator; (iv) it provides a ranking of multiple translations submitted by users for each source text according to their estimated quality. We exemplify the use of this new version through some experiments with the framework.

We present a first attempt at predicting the quality of translations produced by human, professional translators. We examine datasets annotated for quality at sentence- and word-level for four language pairs and provide experiments with prediction models for these datasets. We compare the performance of such models against that of models built from machine translations, highlighting a number of challenges in estimating quality and detecting errors in human translations.

We present QUEST, an open source framework for translation quality estimation. QUEST provides a wide range of feature extractors from source and translation texts and external resources and tools. These go from simple, language-independent features, to advanced, linguistically motivated features. They include features that rely on information from the translation system and features that are oblivious to the way translations were produced. In addition, it provides wrappers for a well-known machine learning toolkit, scikit-learn, including techniques for feature selection and model building, as well as parameter optimisation. We also present a Web interface and functionalities for non-expert users. Using this interface, quality predictions (or internal features of the framework) can be obtained without the installation of the toolkit and the building of prediction models. The interface also provides a ranking method for multiple translations given for the same source text according to their predicted quality.

The standard procedure to train the translation model of a phrase-based SMT system is to concatenate all available parallel data, to perform word alignment, to extract phrase pairs and to calculate translation probabilities by simple relative frequency. However, parallel data is quite inhomogeneous in many practical applications with respect to several factors like data source, alignment quality, appropriateness to the task, etc. We propose a general framework to take into account these factors during the calculation of the phrase-table, e.g. by better distributing the probability mass of the individual phrase pairs. No additional feature functions are needed. We report results on two well-known tasks: the IWSLT’11 and WMT’11 evaluations, in both conditions translating from English to French. We give detailed results for different functions to weight the bitexts. Our best systems improve a strong baseline by up to one BLEU point without any impact on the computational complexity during training or decoding.