United States

Multilingual language models such as mBERT have seen impressive cross-lingual transfer to a variety of languages, but many languages remain excluded from these models. In this paper, we analyse the effect of pre-training with monolingual data for a low-resource language that is not included in mBERT — Maltese — with a range of pre-training set ups. We conduct evaluations with the newly pre-trained models on three morphosyntactic tasks — dependency parsing, part-of-speech tagging, and named-entity recognition — and one semantic classification task — sentiment analysis. We also present a newly created corpus for Maltese, and determine the effect that the pre-training data size and domain have on the downstream performance. Our results show that using a mixture of pre-training domains is often superior to using Wikipedia text only. We also find that a fraction of this corpus is enough to make significant leaps in performance over Wikipedia-trained models. We pre-train and compare two models on the new corpus: a monolingual BERT model trained from scratch (BERTu), and a further pre-trained multilingual BERT (mBERTu). The models achieve state-of-the-art performance on these tasks, despite the new corpus being considerably smaller than typically used corpora for high-resourced languages. On average, BERTu outperforms or performs competitively with mBERTu, and the largest gains are observed for higher-level tasks.

NAACL 2022

Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltese

maltese

multilingual models

low-resource languages

pre-trained language models

bert

## Welcome to NAACL 2022!
The Annual Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL) is taking place July 10-15, 2022 as a hybrid event, in Seattle, WA and online. We are happy to welcome all of you to conference! 
 
The main conference program features oral presentations, in-person and virtual posters and demo sessions, a plenary session for our best paper presentations and awards, keynote presentations, a plenary panel on the place of linguistics and symbolic structures in NLP, and an Industrial Track panel on Careers in NLP.
 
Posters (including Findings of NAACL 2022) and demos are grouped by areas for both the in-person and the virtual sessions. For the virtual component, the talks will be on Zoom and the posters and the demos will be in GatherTown. The Student Research Workshop and will have an oral session and a poster session.
 
The program also features 6 Tutorials and 26 Workshops.
 
 We wish you a wonderful conference!
 
[The NAACL 2022 Organizing Committee](https://2022.naacl.org/committees/organization/)

2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics

workshop paper

Supervised event extraction models require a substantial amount of training data to perform well. However, event annotation requires a lot of human effort and costs much time, which limits the application of existing supervised approaches to new event types. In order to reduce manual labor and shorten the time to build an event extraction system for an arbitrary event ontology, we present a new framework to train such systems much more efficiently without large annotations. Our event trigger labeling model uses a weak supervision approach, which only requires a set of keywords, a small number of examples, and an unlabeled corpus, on which our approach automatically collects weakly supervised annotations. Our argument role labeling component performs zero-shot learning, which only requires the names of the argument roles of new event types. The source codes of our event trigger detection and event argument extraction models are publicly available for research purposes. We also release a dockerized system connecting the two models into a unified event extraction pipeline.

Building an Event Extractor with Only a Few Examples

Pretrained language models have shown success in various areas of natural language processing, including reading comprehension tasks. However, when applying machine learning methods to new domains, labeled data may not always be available. To address this, we use supervised pre-training on source-domain data to reduce sample complexity on domain-specific downstream tasks. We evaluate zero-shot performance on domain-specific reading comprehension tasks by combining task transfer with domain adaptation to fine-tune a pretrained model with no labelled data from the target task. Our approach outperforms Domain-Adaptive Pretraining on downstream domain-specific reading comprehension tasks in 3 out of 4 domains.

Task Transfer and Domain Adaptation for Zero-Shot Question Answering

Curriculum learning strategies in prior multi-task learning approaches arrange datasets in a difficulty hierarchy either based on human perception or by exhaustively searching the optimal arrangement. However, human perception of difficulty may not always correlate well with machine interpretation leading to poor performance and exhaustive search is computationally expensive. Addressing these concerns, we propose two classes of techniques to arrange training instances into a learning curriculum based on difficulty scores computed via model-based approaches. The two classes i.e Dataset-level and Instance-level differ in granularity of arrangement. Through comprehensive experiments with 12 datasets, we show that instance-level and dataset-level techniques result in strong representations as they lead to an average performance improvement of 4.17% and 3.15% over their respective baselines. Furthermore, we find that most of this improvement comes from correctly answering the difficult instances, implying a greater efficacy of our techniques on difficult tasks.

Let the Model Decide its Curriculum for Multitask Learning

The presentation will present our work of using few-shot learning models, Proto-BERT and NNShot in particular, to the Sumerian Named Entity Recognition Task, in low-shot settings. We will introduce the background of the task, including the Sumerian Language and its available digital corpus, and the task itself. We will also talk about the approaches, experimental setup, and experimental results.

Few-shot Learning for Sumerian Named Entity Recognition

Recent advances in the field of deep learning have led to a growing interest in the development of NLP approaches for low-resource and endangered languages. Nevertheless, relatively little research, related to NLP, has been conducted on indigenous languages. These languages are considered to be filled with complexities and challenges that make their study incredibly difficult in the NLP and AI fields. This paper focuses on the morphological segmentation of indigenous languages, an extremely challenging task because of polysynthesis, dialectal variations with rich morpho-phonemics, misspellings and resource-limited scenario issues. The proposed approach, towards a morphological segmentation of Innu-Aimun, an extremely low-resource indigenous language of Canada, is based on deep learning. 
Experiments and evaluations have shown promising results, compared to state-of-the-art rule-based and unsupervised approaches.

Deep Learning-Based Morphological Segmentation for Indigenous Languages: A Study Case on Innu-Aimun

Crowdsourcing platforms are often used to collect datasets for training machine learning models, despite higher levels of inaccurate labeling compared to expert labeling. There are two common strategies to manage the impact of such noise: The first involves aggregating redundant annotations, but comes at the expense of labeling substantially fewer examples. Secondly, prior works have also considered using the entire annotation budget to label as many examples as possible and subsequently apply denoising algorithms to implicitly clean the dataset. We find a middle ground and propose an approach which reserves a fraction of annotations to explicitly clean up highly probable error samples to optimize the annotation process. In particular, we allocate a large portion of the labeling budget to form an initial dataset used to train a model. This model is then used to identify specific examples that appear most likely to be incorrect, which we spend the remaining budget to relabel. Experiments across three model variations and four natural language processing tasks show our approach outperforms or matches both label aggregation and advanced denoising methods designed to handle noisy labels when allocated the same finite annotation budget.

Clean or Annotate: How to Spend a Limited Data Collection Budget

Our collective attention span is shortened by the flood of online information. With FarFetched, we address the need for automated claim validation based on the aggregated evidence derived from multiple online news sources. We introduce an entity-centric reasoning framework in which latent connections between events, actions, or statements are revealed via entity mentions and represented in a graph database. Using entity linking and semantic similarity, we offer a way for collecting and combining information from diverse sources in order to generate evidence relevant to the user’s claim. Then, we leverage textual entailment recognition to quantitatively determine whether this assertion is credible, based on the created evidence. Our approach tries to fill the gap in automated claim validation for less-resourced languages and is showcased on the Greek language, complemented by the training of relevant semantic textual similarity (STS) and natural language inference (NLI) models that are evaluated on translated versions of common benchmarks.

FarFetched: Entity centric Reasoning and Claim Validation for the Greek Language based on Textually Represented Environments

Aspect Term Extraction (ATE) is the task of identifying the word(s) in a review text toward which the author express an opinion. A major challenges for ATE involve data scarcity that hinder the training of deep sequence taggers to identify rare targets. To overcome these issues, we propose a novel method to better exploit the available labeled data for ATE by computing effective complement sentences to augment the input data and facilitate the aspect term prediction. In particular, we introduce a multi-step training procedure that first obtains optimal complement representations and sentences for training data with respect to a deep ATE model. Afterward, we fine-tune the generative language model GPT-2 to allow complement sentence generation at test data. The REINFORCE algorithm is employed to incorporate different expected properties into the reward function to perform the fine-tuning. We perform extensive experiments on the benchmark datasets to demonstrate the benefits of the proposed method that achieve the state-of-the-art performance on different datasets.

Generating Complement Data for Aspect Term Extraction with GPT-2

Highly accurate machine translation systems are very important in societies and countries where multilinguality is very common, and where English often does not suffice. The Indian subcontinent (or South Asia) is such a region, with all the Indic languages currently being under-represented in the NLP ecosystem. It is thus essential to thoroughly explore various techniques to improve the performance of such low-resource languages at least using the data available in open-source, which itself is something not very explored in the Indic ecosystem. In our work, we perform a study with a focus on improving the performance of very-low-resource South Asian languages, especially of countries in addition to India. Specifically, we propose how unified models can be built that can exploit the data from comparatively resource-rich languages of the same region. We propose strategies to unify different types of unexplored scripts, especially Perso--Arabic scripts and Brahmic scripts to build multilingual models for all the South Asian languages despite the script barrier. We also study how augmentation techniques like back-translation can be made use-of to build unified models just using openly available raw data, to understand what levels of improvements can be expected for these Indic languages.

Unified NMT models for the Indian subcontinent, transcending script barriers

Natural Language Processing (NLP) tasks in non-dominant and low-resource languages have not experienced significant progress. Although pre-trained BERT models are available, GPU-dependency, large memory requirement, and data scarcity often limit their applicability. As a solution, this paper proposes a fusion chain architecture comprised of one or more layers of CNN, LSTM, and BiLSTM and identifies precise configuration and chain length. The study shows that a simpler, CPU-trainable non-BERT fusion CNN + BiLSTM + CNN is sufficient to surpass the textual classification performance of the BERT-related models in resource-limited languages and environments. The fusion architecture competitively approaches the state-of-the-art accuracy in several Bengali NLP tasks and a six-class emotion detection task for a newly developed Bengali dataset. Interestingly, the performance of the identified fusion model, for instance, CNN+ BiLSTM + CNN, also holds for other low-resource languages and environments. Efficacy study shows that the CNN + BiLSTM+ CNN model outperforms BERT implementation for Vietnamese languages and performs almost equally in English NLP tasks experiencing artificial data scarcity. For the GLUE benchmark and other datasets such as Emotion, IMDB, and Intent classification, the CNN + BiLSTM + CNN model often surpasses or competes with BERT-base, TinyBERT, DistilBERT, and mBERT. Besides, a position-sensitive self-attention layer role further improves the fusion models’ performance in the Bengali emotion classification. The models are also compressible to as low as ≈ 5× smaller through pruning and retraining, making them more viable for resource-constrained environments. Together, this study may help NLP practitioners and serve as a blueprint for NLP model choices in textual classification for low-resource languages and environments.

Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltese

Downloads

Next from NAACL 2022

Building an Event Extractor with Only a Few Examples

Similar lecture

SwahBERT: Language Model of Swahili

Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltese

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from NAACL 2022

Building an Event Extractor with Only a Few Examples

Similar lecture

SwahBERT: Language Model of Swahili

Downloads