The prevalence of social media presents a growing opportunity to collect and analyse examples of English varieties. Whilst usage of these varieties is often used only in spoken contexts or hard-to-access private messages, social media sites like Twitter provide a platform for users to communicate informally in a scrapeable format. Notably, Indian English (Hinglish), Singaporean English (Singlish), and African-American English (AAE) can be commonly found online. These varieties pose a challenge to existing natural language processing (NLP) tools as they often differ orthographically and syntactically from standard English for which the majority of these tools are built. NLP models trained on standard English texts produced biased outcomes for users of underrepresented varieties (Blodgett and O’Connor, 2017). Some research has aimed to overcome the inherent biases caused by unrepresentative data through techniques like data augmentation or adjusting training models. We aim to address the issue of bias at its root - the data itself. We curate a dataset of tweets from countries with high proportions of underserved English variety speakers, and propose an annotation framework of six categorical classifications along a pseudo-spectrum that measures the degree of standard English and that thereby indirectly aims to surface the manifestations of English varieties in these tweets.

Models based on bidirectional encoder representations from transformers (BERT) produce state of the art (SOTA) results on many natural language processing (NLP) tasks such as named entity recognition (NER), part-of-speech (POS) tagging etc. An interesting phenomenon occurs when classifying long documents such as those from the US supreme court where BERT-based models can be considered difficult to use on a first-pass or out-of-the-box basis. In this paper, we experiment with several BERT-based classification techniques for US supreme court decisions or supreme court database (SCDB) and compare them with the previous SOTA results. We then compare our results specifically with SOTA models for long documents. We compare our results for two classification tasks: (1) a broad classification task with 15 categories and (2) a fine-grained classification task with 279 categories. Our best result produces an accuracy of 80% on the 15 broad categories and 60% on the fine-grained 279 categories which marks an improvement of 8% and 28% respectively from previously reported SOTA results.

Automatic Terminology Extraction (ATE) methods are a class of linguistic, statistical, machine learning or hybrid techniques for identifying terminology in a set of documents. Most modern ATE methods use a statistical measure of how important or characteristic a potential term is to a foreground corpus by using a second background corpus as a baseline. While many variables with ATE methods have been carefully evaluated and tuned in the literature, the effects of choosing a particular background corpus over another are not obvious. In this paper, we propose a methodology that allows us to adjust the relative breadth of the foreground and background corpora in patent documents by taking advantage of the Cooperative Patent Classification (CPC) scheme. Our results show that for every foreground corpus, the broadest background corpus gave the worst performance, in the worst case that difference is 17%. Similarly, the least broad background corpus gave suboptimal performance in all three experiments. We also demonstrate qualitative differences between background corpora – narrower background corpora tend towards more technical output. We expect our results to generalize to terminology extraction for other legal and technical documents and, generally, to the foreground/background approach to ATE.

While systems using the Neural Network-based Machine Translation (NMT) paradigm achieve the highest scores on recent shared tasks, phrase-based (PBMT) systems, rule-based (RBMT) systems and other systems may get better results for individual examples. Therefore, combined systems should achieve the best results for MT, particularly if the system combination method can take advantage of the strengths of each paradigm. In this paper, we describe a system that predicts whether a NMT, PBMT or RBMT will get the best Spanish translation result for a particular English sentence in DGT-TM 20161. Then we use fuzzy-match repair (FMR) as a mechanism to show that the combined system outperforms individual systems in a black-box machine translation setting.

We attempt to identify citations in non-academic text such as patents. Unlike academic articles which often provide bibliographies and follow consistent citation styles, non-academic text cites scientific research in a more ad-hoc manner. We manually annotate citations in 50 patents, train a CRF classifier to find new citations, and apply a reranker to incorporate non-local information. Our best system achieves 0.83 F-score on 5-fold cross validation.

Relations (ABBREVIATE, EXEMPLIFY, ORIGINATE, REL_WORK, OPINION) between entities (citations, jargon, people, organizations) are annotated for PubMed scientific articles. We discuss our specifications, pre-processing and evaluation

This paper describes a sentence alignment technique based on a machine readable dictionary. Alignment takes place in a single pass through the text, based on the scores of matches between pairs of source and target sentences. Pairings consisting of sets of matches are evaluated using a version of the Gale-Shapely solution to the stable marriage problem. An algorithm is described which can handle N-to-1 (or 1-to-N) matches, for n ≥ 0, i.e., deletions, 1-to-1 (including scrambling), and 1-to-many matches. A simple frequency based method for acquiring supplemental dictionary entries is also discussed. We achieve high quality alignments using available bilingual dictionaries, both for closely related language pairs (Spanish/English) and more distantly related pairs (Japanese/English).