We study the problem of controlling the difficulty level of text generated by Large Language Models (LLMs) for contexts where end-users are not fully proficient, such as language learners. Using a novel framework, we evaluate the effectiveness of several key approaches for this task, including few-shot prompting, supervised finetuning, and reinforcement learning (RL), utilising both GPT-4 and open source alternatives like LLama2-7B and Mistral-7B.Our findings reveal a large performance gap between GPT-4 and the open source models when using prompt-based strategies. However, we show how to bridge this gap with a careful combination of finetuning and RL alignment. Our best model, CALM (CEFR-Aligned Language Model), surpasses the performance of GPT-4 and other strategies, at only a fraction of the cost. We further validate the quality of our results through a small-scale human study.

We introduce Universal NER (UNER), an open, community-driven project to develop gold-standard NER benchmarks in many languages. The overarching goal of UNER is to provide high-quality, cross-lingually consistent annotations to facilitate and standardize multilingual NER research. UNER v1 contains 19 datasets annotated with named entities in a cross-lingual consistent schema across 13 diverse languages. In this paper, we detail the dataset creation and composition of UNER; we also provide initial modeling baselines on both in-language and cross-lingual learning settings. We will release the data, code, and fitted models to the public.

We take a step towards addressing the under- representation of the African continent in NLP research by bringing together different stakeholders to create the first large, publicly available, high-quality dataset for named entity recognition (NER) in ten African languages. We detail the characteristics of these languages to help researchers and practitioners better understand the challenges they pose for NER tasks. We analyze our datasets and conduct an extensive empirical evaluation of state- of-the-art methods across both supervised and transfer learning settings. Finally, we release the data, code, and models to inspire future research on African NLP.1

In low-resource natural language processing (NLP), the key problems are a lack of target language training data, and a lack of native speakers to create it. Cross-lingual methods have had notable success in addressing these concerns, but in certain common circumstances, such as insufficient pre-training corpora or languages far from the source language, their performance suffers. In this work we propose a complementary approach to building low-resource Named Entity Recognition (NER) models using “non-speaker” (NS) annotations, provided by annotators with no prior experience in the target language. We recruit 30 participants in a carefully controlled annotation experiment with Indonesian, Russian, and Hindi. We show that use of NS annotators produces results that are consistently on par or better than cross-lingual methods built on modern contextual representations, and have the potential to outperform with additional effort. We conclude with observations of common annotation patterns and recommended implementation practices, and motivate how NS annotations can be used in addition to prior methods for improved performance.

We present the task of Simultaneous Translation and Paraphrasing for Language Education (STAPLE). Given a prompt in one language, the goal is to generate a diverse set of correct translations that language learners are likely to produce. This is motivated by the need to create and maintain large, high-quality sets of acceptable translations for exercises in a language-learning application, and synthesizes work spanning machine translation, MT evaluation, automatic paraphrasing, and language education technology. We developed a novel corpus with unique properties for five languages (Hungarian, Japanese, Korean, Portuguese, and Vietnamese), and report on the results of a shared task challenge which attracted 20 teams to solve the task. In our meta-analysis, we focus on three aspects of the resulting systems: external training corpus selection, model architecture and training decisions, and decoding and filtering strategies. We find that strong systems start with a large amount of generic training data, and then fine-tune with in-domain data, sampled according to our provided learner response frequencies.

Multilingual BERT (M-BERT) has been a huge success in both supervised and zero-shot cross-lingual transfer learning. However, this success is focused only on the top 104 languages in Wikipedia it was trained on. In this paper, we propose a simple but effective approach to extend M-BERT E-MBERT so it can benefit any new language, and show that our approach aids languages that are already in M-BERT as well. We perform an extensive set of experiments with Named Entity Recognition (NER) on 27 languages, only 16 of which are in M-BERT, and show an average increase of about 6% F1 on M-BERT languages and 23% F1 increase on new languages. We release models and code at http://cogcomp.org/page/publication_view/912.

Supervised machine learning assumes the availability of fully-labeled data, but in many cases, such as low-resource languages, the only data available is partially annotated. We study the problem of Named Entity Recognition (NER) with partially annotated training data in which a fraction of the named entities are labeled, and all other tokens, entities or otherwise, are labeled as non-entity by default. In order to train on this noisy dataset, we need to distinguish between the true and false negatives. To this end, we introduce a constraint-driven iterative algorithm that learns to detect false negatives in the noisy set and downweigh them, resulting in a weighted training set. With this set, we train a weighted NER model. We evaluate our algorithm with weighted variants of neural and non-neural NER models on data in 8 languages from several language and script families, showing strong ability to learn from partial data. Finally, to show real-world efficacy, we evaluate on a Bengali NER corpus annotated by non-speakers, outperforming the prior state-of-the-art by over 5 points F1.

For those languages which use it, capitalization is an important signal for the fundamental NLP tasks of Named Entity Recognition (NER) and Part of Speech (POS) tagging. In fact, it is such a strong signal that model performance on these tasks drops sharply in common lowercased scenarios, such as noisy web text or machine translation outputs. In this work, we perform a systematic analysis of solutions to this problem, modifying only the casing of the train or test data using lowercasing and truecasing methods. While prior work and first impressions might suggest training a caseless model, or using a truecaser at test time, we show that the most effective strategy is a concatenation of cased and lowercased training data, producing a single model with high performance on both cased and uncased text. As shown in our experiments, this result holds across tasks and input representations. Finally, we show that our proposed solution gives an 8% F1 improvement in mention detection on noisy out-of-domain Twitter data.

This paper describes a dataset and baseline systems for linking paragraphs from court cases to clauses or amendments in the US Constitution. We implement a rule-based system, a linear model, and a neural architecture for matching pairs of paragraphs, taking training data from online databases in a distantly-supervised fashion. In experiments on a manually-annotated evaluation set, we find that our proposed neural system outperforms a rules-driven baseline. Qualitatively, this performance gap seems largest for abstract or indirect links between documents, which suggests that our system might be useful for answering political science and legal research questions or discovering novel links. We release the dataset along with the manually-annotated evaluation set to foster future work.

This paper describes the Cognitive Computation (CogComp) Group’s submissions to the multilingual named entity recognition shared task at the Balto-Slavic Natural Language Processing (BSNLP) Workshop. The final model submitted is a multi-source neural NER system with multilingual BERT embeddings, trained on the concatenation of training data in various Slavic languages (as well as English). The performance of our system on the official testing data suggests that multi-source approaches consistently outperform single-source approaches for this task, even with the noise of mismatching tagsets.

We present a new web-based interface, TALEN, designed for named entity annotation in low-resource settings where the annotators do not speak the language. To address this non-traditional scenario, TALEN includes such features as in-place lexicon integration, TF-IDF token statistics, Internet search, and entity propagation, all implemented so as to make this difficult task efficient and frictionless. We conduct a small user study to compare against a popular annotation tool, showing that TALEN achieves higher precision and recall against ground-truth annotations, and that users strongly prefer it over the alternative. TALEN is available at: github.com/CogComp/talen.

In this work, we address the problem of Named Entity Recognition (NER) in code-switched tweets as a part of the Workshop on Computational Approaches to Linguistic Code-switching (CALCS) at ACL’18. Code-switching is the phenomenon where a speaker switches between two languages or variants of the same language within or across utterances, known as intra-sentential or inter-sentential code-switching, respectively. Processing such data is challenging using state of the art methods since such technology is generally geared towards processing monolingual text. In this paper we explored ways to use language identification and translation to recognize named entities in such data, however, utilizing simple features (sans multi-lingual features) with Conditional Random Field (CRF) classifier achieved the best results. Our experiments were mainly aimed at the (ENG-SPA) English-Spanish dataset but we submitted a language-independent version of our system to the (MSA-EGY) Arabic-Egyptian dataset as well and achieved good results.

Character-level patterns have been widely used as features in English Named Entity Recognition (NER) systems. However, to date there has been no direct investigation of the inherent differences between name and nonname tokens in text, nor whether this property holds across multiple languages. This paper analyzes the capabilities of corpus-agnostic Character-level Language Models (CLMs) in the binary task of distinguishing name tokens from non-name tokens. We demonstrate that CLMs provide a simple and powerful model for capturing these differences, identifying named entity tokens in a diverse set of languages at close to the performance of full NER systems. Moreover, by adding very simple CLM-based features we can significantly improve the performance of an off-the-shelf NER system for multiple languages.

Recent work in NLP has attempted to deal with low-resource languages but still assumed a resource level that is not present for most languages, e.g., the availability of Wikipedia in the target language. We propose a simple method for cross-lingual named entity recognition (NER) that works well in settings with very minimal resources. Our approach makes use of a lexicon to “translate” annotated data available in one or several high resource language(s) into the target language, and learns a standard monolingual NER model there. Further, when Wikipedia is available in the target language, our method can enhance Wikipedia based methods to yield state-of-the-art NER results; we evaluate on 7 diverse languages, improving the state-of-the-art by an average of 5.5% F1 points. With the minimal resources required, this is an extremely portable cross-lingual NER approach, as illustrated using a truly low-resource language, Uyghur.

Natural Language Processing (NLP) continues to grow in popularity in a range of research and commercial applications. However, installing, maintaining, and running NLP tools can be time consuming, and many commercial and research end users have only intermittent need for large processing capacity. This paper describes ILLINOISCLOUDNLP, an on-demand framework built around NLPCURATOR and Amazon Web Services’ Elastic Compute Cloud (EC2). This framework provides a simple interface to end users via which they can deploy one or more NLPCURATOR instances on EC2, upload plain text documents, specify a set of Text Analytics tools (NLP annotations) to apply, and process and store or download the processed data. It can also allow end users to use a model trained on their own data: ILLINOISCLOUDNLP takes care of training, hosting, and applying it to new data just as it does with existing models within NLPCURATOR. As a representative use case, we describe our use of ILLINOISCLOUDNLP to process 3.05 million documents used in the 2012 and 2013 Text Analysis Conference Knowledge Base Population tasks at a relatively deep level of processing, in approximately 20 hours, at an approximate cost of US$500; this is about 20 times faster than doing so on a single server and requires no human supervision and no NLP or Machine Learning expertise.