Relation extraction is essentially a text classification problem, which can be tackled by fine-tuning a pre-trained language model (LM). However, a key challenge arises from the fact that relation extraction cannot straightforwardly be reduced to sequence or token classification. Existing approaches therefore solve the problem in an indirect way: they fine-tune an LM to learn embeddings of the head and tail entities, and then predict the relationship from these entity embeddings. Our hypothesis in this paper is that relation extraction models can be improved by capturing relationships in a more direct way. In particular, we experiment with appending a prompt with a [MASK] token, whose contextualised representation is treated as a relation embedding. While, on its own, this strategy significantly underperforms the aforementioned approach, we find that the resulting relation embeddings are highly complementary to what is captured by embeddings of the head and tail entity. By jointly considering both types of representations, we end up with a simple model that outperforms the state-of-the-art across several relation extraction benchmarks.
We explore the possibility of improving probabilistic models in structured prediction. Specifically, we combine the models with constrained decoding approaches in the context of token classification for information extraction. The decoding methods search for constraint-satisfying label-assignments while maximizing the total probability. To do this, we evaluate several existing approaches, as well as propose a novel decoding method called Lazy-$k$. Our findings demonstrate that constrained decoding approaches can significantly improve the models' performances, especially when using smaller models. The Lazy-$k$ approach allows for more flexibility between decoding time and accuracy. The code for using Lazy-$k$ decoding can be found here: https://github.com/ArthurDevNL/lazyk.
Recent advances in multimodal pre-trained models have significantly improved information extraction from visually-rich documents (VrDs), in which named entity recognition (NER) is treated as a sequence-labeling task of predicting the BIO entity tags for tokens, following the typical setting of NLP. However, BIO-tagging scheme relies on the correct order of model inputs, which is not guaranteed in real-world NER on scanned VrDs where text are recognized and arranged by OCR systems. Such reading order issue hinders the accurate marking of entities by BIO-tagging scheme, making it impossible for sequence-labeling methods to predict correct named entities. To address the reading order issue, we introduce Token Path Prediction (TPP), a simple prediction head to predict entity mentions as token sequences within documents. Alternative to token classification, TPP models the document layout as a complete directed graph of tokens, and predicts token paths within the graph as entities. For better evaluation of VrD-NER systems, we also propose two revised benchmark datasets of NER on scanned documents which can reflect real-world scenarios. Experiment results demonstrate the effectiveness of our method, and suggest its potential to be a universal solution to various information extraction tasks on documents.
Multilingual language models enable zero-shot cross-lingual transfer (ZS-XLT): fine-tuned on sizable source-language task data, they perform the task in target languages without labeled instances. The effectiveness of ZS-XLT hinges on the linguistic proximity between languages and the amount of pretraining data for a language. Because of this, model selection based on source-language validation is unreliable: it picks model snapshots with suboptimal target-language performance. As a remedy, some work optimizes ZS-XLT by extensively tuning hyperparameters: the follow-up work then routinely struggles to replicate the original results. Other work searches over narrower hyperparameter grids, reporting substantially lower performance. In this work, we therefore propose an unsupervised evaluation protocol for ZS-XLT that decouples performance maximization from hyperparameter tuning. As a robust and more transparent alternative to extensive hyperparameter tuning, we propose to accumulatively average snapshots from different runs into a single model. We run broad ZS-XLT experiments on both higher-level semantic tasks (NLI, extractive QA) and a lower-level token classification task (NER) and find that conventional model selection based on source-language validation quickly plateaus to suboptimal ZS-XLT performance. On the other hand, our accumulative run-by-run averaging of models trained with different hyperparameters boosts ZS-XLT performance and closely correlates with "oracle" ZS-XLT, i.e., model selection based on target-language validation performance.
The recent success of Large Language Models (LLMs) has gained significant attention in both academia and industry. Substantial efforts have been made to enhance the zero- and few-shot generalization capabilities of open-source LLMs through finetuning. Currently, the prevailing approach is instruction-tuning, which trains LLMs to complete real-world tasks by generating responses guided by natural language instructions. It is worth noticing that such an approach may underperform in sequence and token classification tasks. Unlike text generation tasks, classification tasks have a limited label space, where precise label prediction is more appreciated than generating diverse and human-like responses. Prior research has unveiled that instruction-tuned LLMs cannot outperform BERT, prompting us to explore the potential of leveraging latent representations from LLMs for supervised label prediction. In this paper, we introduce a label-supervised adaptation for LLMs, which aims to finetuning the model with discriminant labels. We evaluate this approach with Label Supervised LLaMA (LS-LLaMA), based on LLaMA-2-7B, a relatively small-scale LLM, and can be finetuned on a single GeForce RTX4090 GPU. We extract latent representations from the final LLaMA layer and project them into the label space to compute the cross-entropy loss. The model is finetuned by Low-Rank Adaptation (LoRA) to minimize this loss. Remarkably, without intricate prompt engineering or external knowledge, LS-LLaMA substantially outperforms LLMs ten times its size in scale and demonstrates consistent improvements compared to robust baselines like BERT-Large and RoBERTa-Large in text classification. Moreover, by removing the causal mask from decoders, LS-unLLaMA achieves the state-of-the-art performance in named entity recognition (NER). Our work will shed light on a novel approach to adapting LLMs for various downstream tasks.
We present new supertaggers trained on English grammar-based treebanks and test the effects of the best tagger on parsing speed and accuracy. The treebanks are produced automatically by large manually built grammars and feature high-quality annotation based on a well-developed linguistic theory (HPSG). The English Resource Grammar treebanks include diverse and challenging test datasets, beyond the usual WSJ section 23 and Wikipedia data. HPSG supertagging has previously relied on MaxEnt-based models. We use SVM and neural CRF- and BERT-based methods and show that both SVM and neural supertaggers achieve considerably higher accuracy compared to the baseline and lead to an increase not only in the parsing speed but also the parser accuracy with respect to gold dependency structures. Our fine-tuned BERT-based tagger achieves 97.26\% accuracy on 950 sentences from WSJ23 and 93.88% on the out-of-domain technical essay The Cathedral and the Bazaar (cb). We present experiments with integrating the best supertagger into an HPSG parser and observe a speedup of a factor of 3 with respect to the system which uses no tagging at all, as well as large recall gains and an overall precision gain. We also compare our system to an existing integrated tagger and show that although the well-integrated tagger remains the fastest, our experimental system can be more accurate. Finally, we hope that the diverse and difficult datasets we used for evaluation will gain more popularity in the field: we show that results can differ depending on the dataset, even if it is an in-domain one. We contribute the complete datasets reformatted for Huggingface token classification.
Transformer architectures and models have made significant progress in language-based tasks. In this area, is BERT one of the most widely used and freely available transformer architecture. In our work, we use BERT for context-based phrase recognition of magic spells in the Harry Potter novel series. Spells are a common part of active magic in fantasy novels. Typically, spells are used in a specific context to achieve a supernatural effect. A series of investigations were conducted to see if a Transformer architecture could recognize such phrases based on their context in the Harry Potter saga. For our studies a pre-trained BERT model was used and fine-tuned utilising different datasets and training methods to identify the searched context. By considering different approaches for sequence classification as well as token classification, it is shown that the context of spells can be recognised. According to our investigations, the examined sequence length for fine-tuning and validation of the model plays a significant role in context recognition. Based on this, we have investigated whether spells have overarching properties that allow a transfer of the neural network models to other fantasy universes as well. The application of our model showed promising results and is worth to be deepened in subsequent studies.
Bias in textual data can lead to skewed interpretations and outcomes when the data is used. These biases could perpetuate stereotypes, discrimination, or other forms of unfair treatment. An algorithm trained on biased data may end up making decisions that disproportionately impact a certain group of people. Therefore, it is crucial to detect and remove these biases to ensure the fair and ethical use of data. To this end, we develop a comprehensive and robust framework NBIAS that consists of four main layers: data, corpus construction, model development and an evaluation layer. The dataset is constructed by collecting diverse data from various domains, including social media, healthcare, and job hiring portals. As such, we applied a transformer-based token classification model that is able to identify bias words/ phrases through a unique named entity BIAS. In the evaluation procedure, we incorporate a blend of quantitative and qualitative measures to gauge the effectiveness of our models. We achieve accuracy improvements ranging from 1% to 8% compared to baselines. We are also able to generate a robust understanding of the model functioning. The proposed approach is applicable to a variety of biases and contributes to the fair and ethical use of textual data.
Traditional banks face increasing competition from FinTechs in the rapidly evolving financial ecosystem. Raising operational efficiency is vital to address this challenge. Our study aims to improve the efficiency of document-intensive business processes in banking. To that end, we first review the landscape of business documents in the retail segment. Banking documents often contain text, layout, and visuals, suggesting that document analytics and process automation require more than plain natural language processing (NLP). To verify this and assess the incremental value of visual cues when processing business documents, we compare a recently proposed multimodal model called LayoutXLM to powerful text classifiers (e.g., BERT) and large language models (e.g., GPT) in a case study related to processing company register extracts. The results confirm that incorporating layout information in a model substantially increases its performance. Interestingly, we also observed that more than 75% of the best model performance (in terms of the F1 score) can be achieved with as little as 30% of the training data. This shows that the demand for data labeled data to set up a multi-modal model can be moderate, which simplifies real-world applications of multimodal document analytics. Our study also sheds light on more specific practices in the scope of calibrating a multimodal banking document classifier, including the need for fine-tuning. In sum, the paper contributes original empirical evidence on the effectiveness and efficiency of multi-model models for document processing in the banking business and offers practical guidance on how to unlock this potential in day-to-day operations.
Aiming to support Retrieval Augmented Generation (RAG) in the design process, we present a method to identify explicit, engineering design facts - {head entity :: relationship :: tail entity} from patented artefact descriptions. Given a sentence with a pair of entities (based on noun phrases) marked in a unique manner, our method extracts the relationship that is explicitly communicated in the sentence. For this task, we create a dataset of 375,084 examples and fine-tune language models for relation identification (token classification) and elicitation (sequence-to-sequence). The token classification approach achieves up to 99.7% accuracy. Upon applying the method to a domain of 4,870 fan system patents, we populate a knowledge base of over 2.93 million facts. Using this knowledge base, we demonstrate how Large Language Models (LLMs) are guided by explicit facts to synthesise knowledge and generate technical and cohesive responses when sought out for knowledge retrieval tasks in the design process.
Massively multilingual language models have displayed strong performance in zero-shot (ZS-XLT) and few-shot (FS-XLT) cross-lingual transfer setups, where models fine-tuned on task data in a source language are transferred without any or with only a few annotated instances to the target language(s). However, current work typically overestimates model performance as fine-tuned models are frequently evaluated at model checkpoints that generalize best to validation instances in the target languages. This effectively violates the main assumptions of "true" ZS-XLT and FS-XLT. Such XLT setups require robust methods that do not depend on labeled target language data for validation and model selection. In this work, aiming to improve the robustness of "true" ZS-XLT and FS-XLT, we propose a simple and effective method that averages different checkpoints (i.e., model snapshots) during task fine-tuning. We conduct exhaustive ZS-XLT and FS-XLT experiments across higher-level semantic tasks (NLI, extractive QA) and lower-level token classification tasks (NER, POS). The results indicate that averaging model checkpoints yields systematic and consistent performance gains across diverse target languages in all tasks. Importantly, it simultaneously substantially desensitizes XLT to varying hyperparameter choices in the absence of target language validation. We also show that checkpoint averaging benefits performance when further combined with run averaging (i.e., averaging the parameters of models fine-tuned over independent runs).
Although pre-trained named entity recognition (NER) models are highly accurate on modern corpora, they underperform on historical texts due to differences in language OCR errors. In this work, we develop a new NER corpus of 3.6M sentences from late medieval charters written mainly in Czech, Latin, and German. We show that we can start with a list of known historical figures and locations and an unannotated corpus of historical texts, and use information retrieval techniques to automatically bootstrap a NER-annotated corpus. Using our corpus, we train a NER model that achieves entity-level Precision of 72.81-93.98% with 58.14-81.77% Recall on a manually-annotated test dataset. Furthermore, we show that using a weighted loss function helps to combat class imbalance in token classification tasks. To make it easy for others to reproduce and build upon our work, we publicly release our corpus, models, and experimental code.
Slot labeling (SL) is a core component of task-oriented dialogue (ToD) systems, where slots and corresponding values are usually language-, task- and domain-specific. Therefore, extending the system to any new language-domain-task configuration requires (re)running an expensive and resource-intensive data annotation process. To mitigate the inherent data scarcity issue, current research on multilingual ToD assumes that sufficient English-language annotated data are always available for particular tasks and domains, and thus operates in a standard cross-lingual transfer setup. In this work, we depart from this often unrealistic assumption. We examine challenging scenarios where such transfer-enabling English annotated data cannot be guaranteed, and focus on bootstrapping multilingual data-efficient slot labelers in transfer-free scenarios directly in the target languages without any English-ready data. We propose a two-stage slot labeling approach (termed TWOSL) which transforms standard multilingual sentence encoders into effective slot labelers. In Stage 1, relying on SL-adapted contrastive learning with only a handful of SL-annotated examples, we turn sentence encoders into task-specific span encoders. In Stage 2, we recast SL from a token classification into a simpler, less data-intensive span classification task. Our results on two standard multilingual TOD datasets and across diverse languages confirm the effectiveness and robustness of TWOSL. It is especially effective for the most challenging transfer-free few-shot setups, paving the way for quick and data-efficient bootstrapping of multilingual slot labelers for ToD.
Spelling correction is a remarkable challenge in the field of natural language processing. The objective of spelling correction tasks is to recognize and rectify spelling errors automatically. The development of applications that can effectually diagnose and correct Persian spelling and grammatical errors has become more important in order to improve the quality of Persian text. The Typographical Error Type Detection in Persian is a relatively understudied area. Therefore, this paper presents a compelling approach for detecting typographical errors in Persian texts. Our work includes the presentation of a publicly available dataset called FarsTypo, which comprises 3.4 million words arranged in chronological order and tagged with their corresponding part-of-speech. These words cover a wide range of topics and linguistic styles. We develop an algorithm designed to apply Persian-specific errors to a scalable portion of these words, resulting in a parallel dataset of correct and incorrect words. By leveraging FarsTypo, we establish a strong foundation and conduct a thorough comparison of various methodologies employing different architectures. Additionally, we introduce a groundbreaking Deep Sequential Neural Network that utilizes both word and character embeddings, along with bidirectional LSTM layers, for token classification aimed at detecting typographical errors across 51 distinct classes. Our approach is contrasted with highly advanced industrial systems that, unlike this study, have been developed using a diverse range of resources. The outcomes of our final method proved to be highly competitive, achieving an accuracy of 97.62%, precision of 98.83%, recall of 98.61%, and surpassing others in terms of speed.
Background & Objective: Biomedical text data are increasingly available for research. Tokenization is an initial step in many biomedical text mining pipelines. Tokenization is the process of parsing an input biomedical sentence (represented as a digital character sequence) into a discrete set of word/token symbols, which convey focused semantic/syntactic meaning. The objective of this study is to explore variation in tokenizer outputs when applied across a series of challenging biomedical sentences. Method: Diaz [2015] introduce 24 challenging example biomedical sentences for comparing tokenizer performance. In this study, we descriptively explore variation in outputs of eight tokenizers applied to each example biomedical sentence. The tokenizers compared in this study are the NLTK white space tokenizer, the NLTK Penn Tree Bank tokenizer, Spacy and SciSpacy tokenizers, Stanza/Stanza-Craft tokenizers, the UDPipe tokenizer, and R-tokenizers. Results: For many examples, tokenizers performed similarly effectively; however, for certain examples, there were meaningful variation in returned outputs. The white space tokenizer often performed differently than other tokenizers. We observed performance similarities for tokenizers implementing rule-based systems (e.g. pattern matching and regular expressions) and tokenizers implementing neural architectures for token classification. Oftentimes, the challenging tokens resulting in the greatest variation in outputs, are those words which convey substantive and focused biomedical/clinical meaning (e.g. x-ray, IL-10, TCR/CD3, CD4+ CD8+, and (Ca2+)-regulated). Conclusion: When state-of-the-art, open-source tokenizers from Python and R were applied to a series of challenging biomedical example sentences, we observed subtle variation in the returned outputs.
Supervised named entity recognition (NER) in the biomedical domain depends on large sets of annotated texts with the given named entities. The creation of such datasets can be time-consuming and expensive, while extraction of new entities requires additional annotation tasks and retraining the model. To address these challenges, this paper proposes a method for zero- and few-shot NER in the biomedical domain. The method is based on transforming the task of multi-class token classification into binary token classification and pre-training on a large amount of datasets and biomedical entities, which allow the model to learn semantic relations between the given and potentially novel named entity labels. We have achieved average F1 scores of 35.44% for zero-shot NER, 50.10% for one-shot NER, 69.94% for 10-shot NER, and 79.51% for 100-shot NER on 9 diverse evaluated biomedical entities with fine-tuned PubMedBERT-based model. The results demonstrate the effectiveness of the proposed method for recognizing new biomedical entities with no or limited number of examples, outperforming previous transformer-based methods, and being comparable to GPT3-based models using models with over 1000 times fewer parameters. We make models and developed code publicly available.
Language Models (LMs) have shown state-of-the-art performance in Natural Language Processing (NLP) tasks. Downstream tasks such as Named Entity Recognition (NER) or Part-of-Speech (POS) tagging are known to suffer from data imbalance issues, particularly regarding the ratio of positive to negative examples and class disparities. This paper investigates an often-overlooked issue of encoder models, specifically the position bias of positive examples in token classification tasks. For completeness, we also include decoders in the evaluation. We evaluate the impact of position bias using different position embedding techniques, focusing on BERT with Absolute Position Embedding (APE), Relative Position Embedding (RPE), and Rotary Position Embedding (RoPE). Therefore, we conduct an in-depth evaluation of the impact of position bias on the performance of LMs when fine-tuned on token classification benchmarks. Our study includes CoNLL03 and OntoNote5.0 for NER, English Tree Bank UD\_en, and TweeBank for POS tagging. We propose an evaluation approach to investigate position bias in transformer models. We show that LMs can suffer from this bias with an average drop ranging from 3\% to 9\% in their performance. To mitigate this effect, we propose two methods: Random Position Shifting and Context Perturbation, that we apply on batches during the training process. The results show an improvement of $\approx$ 2\% in the performance of the model on CoNLL03, UD\_en, and TweeBank.
Research in Document Intelligence and especially in Document Key Information Extraction (DocKIE) has been mainly solved as Token Classification problem. Recent breakthroughs in both natural language processing (NLP) and computer vision helped building document-focused pre-training methods, leveraging a multimodal understanding of the document text, layout and image modalities. However, these breakthroughs also led to the emergence of a new DocKIE subtask of extractive document Question Answering (DocQA), as part of the Machine Reading Comprehension (MRC) research field. In this work, we compare the Question Answering approach with the classical token classification approach for document key information extraction. We designed experiments to benchmark five different experimental setups : raw performances, robustness to noisy environment, capacity to extract long entities, fine-tuning speed on Few-Shot Learning and finally Zero-Shot Learning. Our research showed that when dealing with clean and relatively short entities, it is still best to use token classification-based approach, while the QA approach could be a good alternative for noisy environment or long entities use-cases.
In this report, we describe our ClassBases submissions to a shared task on multilingual protest event detection. For the multilingual protest news detection, we participated in subtask-1, subtask-2, and subtask-4, which are document classification, sentence classification, and token classification. In subtask-1, we compare XLM-RoBERTa-base, mLUKE-base, and XLM-RoBERTa-large on finetuning in a sequential classification setting. We always use a combination of the training data from every language provided to train our multilingual models. We found that larger models seem to work better and entity knowledge helps but at a non-negligible cost. For subtask-2, we only submitted an mLUKE-base system for sentence classification. For subtask-4, we only submitted an XLM-RoBERTa-base for token classification system for sequence labeling. For automatically replicating manually created event datasets, we participated in COVID-related protest events from the New York Times news corpus. We created a system to process the crawled data into a dataset of protest events.
Unsupervised Machine Learning techniques have been applied to Natural Language Processing tasks and surpasses the benchmarks such as GLUE with great success. Building language models approach achieves good results in one language and it can be applied to multiple NLP task such as classification, summarization, generation and etc as an out of box model. Among all the of the classical approaches used in NLP, the masked language modeling is the most used. In general, the only requirement to build a language model is presence of the large corpus of textual data. Text classification engines uses a variety of models from classical and state of art transformer models to classify texts for in order to save costs. Sequence Classifiers are mostly used in the domain of text classification. However Token classifiers also are viable candidate models as well. Sequence Classifiers and Token Classifier both tend to improve the classification predictions due to the capturing the context information differently. This work aims to compare the performance of Sequence Classifier and Token Classifiers and evaluate each model on the same set of data. In this work, we are using a pre-trained model as the base model and Token Classifier and Sequence Classier heads results of these two scoring paradigms with be compared..