The ability to identify important entities in a text, known as Named Entity Recognition (NER), is useful in a large variety of downstream tasks in the biomedical domain. This is a considerably difficult task when working with Consumer Health Questions (CHQs), which consist of informal language used in day-to-day life by patients. These difficulties are amplified in the case of Bengali, which allows for a huge amount of flexibility in sentence structures and has significant variances in regional dialects. Unfortunately, the complexity of the language is not accurately reflected in the limited amount of available data, which makes it difficult to build a reliable decision-making system. To address the scarcity of data, this paper presents ‘Bangla-HealthNER’, a comprehensive dataset designed to identify named entities in health-related texts in the Bengali language. It consists of 31,783 samples sourced from a popular online public health platform, which allows it to capture the diverse range of linguistic styles and dialects used by native speakers from various regions in their day-to-day lives. The insight into this diversity in language will prove useful to any medical decision-making systems that are developed for use in real-world applications. To highlight the difficulty of the dataset, it has been benchmarked on state-of-the-art token classification models, where BanglishBERT achieved the highest performance with an F1-score of 56.13 \pm 0.75%. The dataset and all relevant code used in this work have been made publicly available.
论文检索
输入标题、作者或关键词，从 7,876 篇学术成果中精准定位
Prompting approaches have been recently explored in text style transfer, where a textual prompt is used to query a pretrained language model (PLM) to generate style-transferred texts word by word in an autoregressive manner. However, such a generation process is less controllable and early prediction errors may affect future word predictions. In this paper, we propose a prompt-based editing approach to text style transfer. Specifically, we prompt a PLM for style classification and use the classification probability to compute a style score. Then, we perform discrete search with word-level editing to maximize a comprehensive scoring function for the style-transfer task. In this way, we transform a prompt-based generation problem into a classification one, which does not suffer from the error accumulation problem and is more controllable than the autoregressive generation of sentences. In our experiments, we performed both automatic and human evaluation on three style-transfer benchmark datasets, and show that our approach largely outperforms the existing systems that have 20 times more parameters. Additional empirical analyses further demonstrate the effectiveness of our approach.
Disentangling Structure and Style: Political Bias Detection in News by Inducing Document Hierarchy
PDF ↗We address an important gap in detecting political bias in news articles. Previous works that perform document classification can be influenced by the writing style of each news outlet, leading to overfitting and limited generalizability. Our approach overcomes this limitation by considering both the sentence-level semantics and the document-level rhetorical structure, resulting in a more robust and style-agnostic approach to detecting political bias in news articles. We introduce a novel multi-head hierarchical attention model that effectively encodes the structure of long documents through a diverse ensemble of attention heads. While journalism follows a formalized rhetorical structure, the writing style may vary by news outlet. We demonstrate that our method overcomes this domain dependency and outperforms previous approaches for robustness and accuracy. Further analysis and human evaluation demonstrate the ability of our model to capture common discourse structures in journalism.
Enhancing Reasoning Capabilities by Instruction Learning and Chain-of-Thoughts for Implicit Discourse Relation Recognition
PDF ↗The aim of implicit discourse relation recognition is to comprehend the sense of connection between two arguments. In this work, we present a classification method that is solely based on generative models. Our proposed approach employs a combination of instruction templates and in-context learning to refine the generative model for effectively addressing the implicit discourse relation recognition task. Furthermore, we utilize Chain-of-Thoughts to partition the inference process into a sequence of three successive stages. This strategy enables us to fully utilize the autoregressive generative model’s potential for knowledge acquisition and inference, ultimately leading to enhanced performance on this natural language understanding task. The results of our experiments, evaluated on benchmark datasets PDTB 2.0, PDTB 3.0, and the CoNLL16 shared task, demonstrate superior performance compared to previous state-of-the-art models.
While recently developed NLP explainability methods let us open the black box in various ways (Madsen et al., 2022), a missing ingredient in this endeavor is an interactive tool offering a conversational interface. Such a dialogue system can help users explore datasets and models with explanations in a contextualized manner, e.g. via clarification or follow-up questions, and through a natural language interface. We adapt the conversational explanation framework TalkToModel (Slack et al., 2022) to the NLP domain, add new NLP-specific operations such as free-text rationalization, and illustrate its generalizability on three NLP tasks (dialogue act classification, question answering, hate speech detection). To recognize user queries for explanations, we evaluate fine-tuned and few-shot prompting models and implement a novel adapter-based approach. We then conduct two user studies on (1) the perceived correctness and helpfulness of the dialogues, and (2) the simulatability, i.e. how objectively helpful dialogical explanations are for humans in figuring out the model’s predicted label when it’s not shown. We found rationalization and feature attribution were helpful in explaining the model behavior. Moreover, users could more reliably predict the model outcome based on an explanation dialogue rather than one-off explanations.
Concept Learning requires learning the definition of a general category from given training examples. Most of the existing methods focus on learning concepts from images. However, the visual information cannot present abstract concepts exactly, which struggles the introduction of novel concepts related to known concepts (e.g., ‘Plant’\rightarrow‘Asteroids’). In this paper, inspired by the fact that humans learn most concepts through linguistic description, we introduce Linguistic Concept Learning benchmark (Licon), where concepts in diverse forms (e.g., plain attributes, images, and text) are defined by linguistic descriptions. The difficulty to learn novel concepts can be controlled by the number of attributes or the hierarchical relationships between concepts. The diverse and controllable concepts are used to support challenging evaluation tasks, including concept classification, attribute prediction, and concept relationship recognition. In addition, we design an entailment-based concept learning method (EnC) to model the relationship among concepts. Extensive experiments demonstrate the effectiveness of EnC. The benchmark will be released to the public soon.
In this paper, we address the limitations of the common data annotation and training methods for objective single-label classification tasks. Typically, when annotating such tasks annotators are only asked to provide a single label for each sample and annotator disagreement is discarded when a final hard label is decided through majority voting. We challenge this traditional approach, acknowledging that determining the appropriate label can be difficult due to the ambiguity and lack of context in the data samples. Rather than discarding the information from such ambiguous annotations, our soft label method makes use of them for training. Our findings indicate that additional annotator information, such as confidence, secondary label and disagreement, can be used to effectively generate soft labels. Training classifiers with these soft labels then leads to improved performance and calibration on the hard label test set.
MuG: A Multimodal Classification Benchmark on Game Data with Tabular, Textual, and Visual Fields
PDF ↗Previous research has demonstrated the advantages of integrating data from multiple sources over traditional unimodal data, leading to the emergence of numerous novel multimodal applications. We propose a multimodal classification benchmark MuG with eight datasets that allows researchers to evaluate and improve their models. These datasets are collected from four various genres of games that cover tabular, textual, and visual modalities. We conduct multi-aspect data analysis to provide insights into the benchmark, including label balance ratios, percentages of missing features, distributions of data within each modality, and the correlations between labels and input modalities. We further present experimental results obtained by several state-of-the-art unimodal classifiers and multimodal classifiers, which demonstrate the challenging and multimodal-dependent properties of the benchmark. MuG is released at https://github.com/lujiaying/MUG-Bench with the data, tutorials, and implemented baselines.
The ability to identify and control different kinds of linguistic information encoded in vector representations of words has many use cases, especially for explainability and bias removal. This is usually done via a set of simple classification tasks, termed probes, to evaluate the information encoded in the embedding space. However, the involvement of a trainable classifier leads to entanglement between the probe’s results and the classifier’s nature. As a result, contemporary works on probing include tasks that do not involve training of auxiliary models. In this work we introduce the term indicator tasks for non-trainable tasks which are used to query embedding spaces for the existence of certain properties, and claim that this kind of tasks may point to a direction opposite to probes, and that this contradiction complicates the decision on whether a property exists in an embedding space. We demonstrate our claims with two test cases, one dealing with gender debiasing and another with the erasure of morphological information from embedding spaces. We show that the application of a suitable indicator provides a more accurate picture of the information captured and removed compared to probes. We thus conclude that indicator tasks should be implemented and taken into consideration when eliciting information from embedded representations.
The remarkable advancements in large language models (LLMs) have significantly enhanced predictive performance in few-shot learning settings. By using only a small number of labeled examples, referred to as demonstrations, LLMs can effectively perform the task at hand through in-context learning. However, the process of selecting demonstrations for maximizing performance has received limited attention in prior work. This paper addresses the issue of identifying the most informative demonstrations for few-shot learning by approaching it as a pool-based Active Learning (AL) problem over a single iteration. We compare standard AL algorithms based on uncertainty, diversity, and similarity, and consistently observe that the latter outperforms all other methods, including random sampling. Our extensive experimentation involving a diverse range of GPT and OPT models across 24 classification and multi-choice tasks, coupled with thorough analysis, unambiguously demonstrates the importance of using demonstrations that are semantically similar to the domain of the test examples. In fact, we show higher average classification performance using “similar” demonstrations with GPT-2 (124M) than random demonstrations with GPT-Neox (20B). Notably, while diversity sampling shows promise, uncertainty sampling, despite its success in conventional supervised learning AL scenarios, performs poorly in in-context learning.
Improving End-to-End Speech Processing by Efficient Text Data Utilization with Latent Synthesis
PDF ↗Training a high performance end-to-end speech (E2E) processing model requires an enormous amount of labeled speech data, especially in the era of data-centric artificial intelligence. However, labeled speech data are usually scarcer and more expensive for collection, compared to textual data. We propose Latent Synthesis (LaSyn), an efficient textual data utilization framework for E2E speech processing models. We train a latent synthesizer to convert textual data into an intermediate latent representation of a pre-trained speech model. These pseudo acoustic representations of textual data augment acoustic data for model training. We evaluate LaSyn on low-resource automatic speech recognition (ASR) and spoken language understanding (SLU) tasks. For ASR, LaSyn improves an E2E baseline trained on LibriSpeech train-clean-100, with relative word error rate reductions over 22.3% on different test sets. For SLU, LaSyn improves our E2E baseline by absolute 4.1% for intent classification accuracy and 3.8% for slot filling SLU-F1 on SLURP, and absolute 4.49% and 2.25% for exact match (EM) and EM-Tree accuracies on STOP respectively. With fewer parameters, the results of LaSyn are competitive to published state-of-the-art works. The results demonstrate the quality of the augmented training data.
In this work, we study the language model backbone replacement problem for personalized downstream tasks in a non-stationary on-device scenario. In real world, company may periodically update the knowledge and architectures of backbones to keep the competitive in the market, meanwhile, to accommodate the users’ own preference, models are personalized to fit users’ own distribution locally. Traditional full model tuning or transfer learning for such replacements often incur considerable local device training costs and necessitate extensive backpropagation within deep transformer layers. Addressing this issue, we propose a novel, lightweight tuning method for personalized NLP classification tasks post-backbone replacement. Our approach leverages a personalized matrix calculated from documents corresponding to users’ old and new backbones. This matrix facilitates top-layer parameter tuning, drastically reducing backpropagation computation. To further mitigate training costs associated with matrix linear optimization, we employ correlation clustering to curate a few examples from personalized cluster sets for individuals. Our method achieves over 1000 times computation reduction in Flops for backpropagation and brings the user-specific initialization for personal matrix yielding significant performance boost compared with popular transfer learning methods.
The Interpreter Understands Your Meaning: End-to-end Spoken Language Understanding Aided by Speech Translation
PDF ↗End-to-end spoken language understanding (SLU) remains elusive even with current large pretrained language models on text and speech, especially in multilingual cases. Machine translation has been established as a powerful pretraining objective on text as it enables the model to capture high-level semantics of the input utterance and associations between different languages, which is desired for speech models that work on lower-level acoustic frames. Motivated particularly by the task of cross-lingual SLU, we demonstrate that the task of speech translation (ST) is a good means of pretraining speech models for end-to-end SLU on both intra- and cross-lingual scenarios. By introducing ST, our models reach higher performance over baselines on monolingual and multilingual intent classification as well as spoken question answering using SLURP, MINDS-14, and NMSQA benchmarks. To verify the effectiveness of our methods, we also create new benchmark datasets from both synthetic and real sources, for speech summarization and low-resource/zero-shot transfer from English to French or Spanish. We further show the value of preserving knowledge for the ST pretraining task for better downstream performance, possibly using Bayesian transfer regularizers.
Target-Oriented Multimodal Sentiment Classification (TMSC) aims to perform sentiment polarity on a target jointly considering its corresponding multiple modalities including text, image, and others. Current researches mainly work on either of two types of targets in a decentralized manner. One type is entity, such as a person name, a location name, etc. and the other is aspect, such as ‘food’, ‘service’, etc. We believe that this target type based division in task modelling is not necessary because the sentiment polarity of the specific target is not governed by its type but its context. For this reason, we propose a unified model for target-oriented multimodal sentiment classification, so called UnifiedTMSC. It is prompt-based language modelling and performs well on four datasets spanning the above two target types. Specifically, we design descriptive prompt paraphrasing to reformulate TMSC task via (1) task paraphrasing, which obtains paraphrased prompts based on the task description through a paraphrasing rule, and (2) image prefix tuning, which optimizes a small continuous image vector throughout the multimodal representation space of text and images. Conducted on two entity-level multimodal datasets: Twitter-2015 and Twitter-2017, and two aspect-level multimodal datasets: Multi-ZOL and MASAD, the experimental results show the effectiveness of our UnifiedTMSC.
Emotion arcs capture how an individual (or a population) feels over time. They are widely used in industry and research; however, there is little work on evaluating the automatically generated arcs. This is because of the difficulty of establishing the true (gold) emotion arc. Our work, for the first time, systematically and quantitatively evaluates automatically generated emotion arcs. We also compare two common ways of generating emotion arcs: Machine-Learning (ML) models and Lexicon-Only (LexO) methods. By running experiments on 18 diverse datasets in 9 languages, we show that despite being markedly poor at instance level emotion classification, LexO methods are highly accurate at generating emotion arcs when aggregating information from hundreds of instances. We also show, through experiments on six indigenous African languages, as well as Arabic, and Spanish, that automatic translations of English emotion lexicons can be used to generate high-quality emotion arcs in less-resource languages. This opens up avenues for work on emotions in languages from around the world; which is crucial for commerce, public policy, and health research in service of speakers often left behind. Code and resources: https://github.com/dteodore/EmotionArcs
Large language models have recently risen in popularity due to their ability to perform many natural language tasks without requiring any fine-tuning. In this work, we focus on two novel ideas: (1) generating definitions from examples and using them for zero-shot classification, and (2) investigating how an LLM makes use of the definitions. We thoroughly analyze the performance of GPT-3 model for fine-grained multi-label conspiracy theory classification of tweets using zero-shot labeling. In doing so, we asses how to improve the labeling by providing minimal but meaningful context in the form of the definitions of the labels. We compare descriptive noun phrases, human-crafted definitions, introduce a new method to help the model generate definitions from examples, and propose a method to evaluate GPT-3’s understanding of the definitions. We demonstrate that improving definitions of class labels has a direct consequence on the downstream classification results.
Document-Level Relation Extraction aims at predicting relations between entities from multiple sentences. A common practice is to select multi-label classification thresholds to decide whether a relation exists between an entity pair. However, in the document-level task, most entity pairs do not express any relations, resulting in a highly imbalanced distribution between positive and negative classes. We argue that the imbalance problem affects threshold selection and may lead to incorrect “no-relation” predictions. In this paper, we propose to down-weight the easy negatives by utilizing a distance between the classification threshold and the predicted score of each relation. Our novel Adaptive Hinge Balance Loss measures the difficulty of each relation class with the distance, putting more focus on hard, misclassified relations, i.e. the minority positive relations. Experiment results on Re-DocRED demonstrate the superiority of our approach over other balancing methods. Source codes are available at https://github.com/Jize-W/HingeABL.
Pre-trained language models (PLMs) are often deployed as cloud services, enabling users to upload textual data and perform inference remotely. However, users’ personal text often contains sensitive information, and sharing such data directly with the service providers can lead to serious privacy leakage. To address this problem, we introduce a novel privacy-preserving inference framework called MixPi , which prevents plaintext leakage during the inference phase. Inspired by k-anonymity, MixPi aims to obfuscate a user’s private input by mixing it with multiple other inputs, thereby confounding potential privacy attackers. To achieve this, our approach involves: (1) proposing a novel encryption module, Privacy Mixer, which encrypts input from three distinct dimensions: mixing, representation, and position. (2) adopting a pre-trained Multi-input Multi-output network to handle mixed representations and obtain multiple predictions. (3) employing a Privacy Demixer to ensure only the user can decrypt the real output among the multiple predictions. Furthermore, we explore different ways to automatically generate synthetic inputs required for mixing. Experimental results on token and sentence classification tasks demonstrate that MixPi greatly surpasses existing privacy-preserving methods in both performance and privacy.
Watermarking PLMs on Classification Tasks by Combining Contrastive Learning with Weight Perturbation
PDF ↗Large pre-trained language models (PLMs) have achieved remarkable success, making them highly valuable intellectual property due to their expensive training costs. Consequently, model watermarking, a method developed to protect the intellectual property of neural models, has emerged as a crucial yet underexplored technique. The problem of watermarking PLMs has remained unsolved since the parameters of PLMs will be updated when fine-tuned on downstream datasets, and then embedded watermarks could be removed easily due to the catastrophic forgetting phenomenon. This study investigates the feasibility of watermarking PLMs by embedding backdoors that can be triggered by specific inputs. We employ contrastive learning during the watermarking phase, allowing the representations of specific inputs to be isolated from others and mapped to a particular label after fine-tuning. Moreover, we demonstrate that by combining weight perturbation with the proposed method, watermarks can be embedded in a flatter region of the loss landscape, thereby increasing their robustness to watermark removal. Extensive experiments on multiple datasets demonstrate that the embedded watermarks can be robustly extracted without any knowledge about downstream tasks, and with a high success rate.
Multi-head self-attention-based Transformers have shown promise in different learning tasks. Albeit these models exhibit significant improvement in understanding short-term and long-term contexts from sequences, encoders of Transformers and their variants fail to preserve layer-wise contextual information. Transformers usually project tokens onto sparse manifolds and fail to preserve mathematical equivalence among the token representations. In this work, we propose TransJect, an encoder model that guarantees a theoretical bound for layer-wise distance preservation between a pair of tokens. We propose a simple alternative to dot-product attention to ensure Lipschitz continuity. This allows TransJect to learn injective mappings to transform token representations to different manifolds with similar topology and preserve Euclidean distance between every pair of tokens in subsequent layers. Evaluations across multiple benchmark short- and long-sequence classification tasks show maximum improvements of 6.8% and 5.9%, respectively, over the variants of Transformers. Additionally, TransJect displays 79% better performance than Transformer on the language modeling task. We further highlight the shortcomings of multi-head self-attention from the statistical physics viewpoint. Although multi-head self-attention was incepted to learn different abstraction levels within the networks, our empirical analyses suggest that different attention heads learn randomly and unorderly. In contrast, TransJect adapts a mixture of experts for regularization; these experts are more orderly and balanced and learn different sparse representations from the input sequences. TransJect exhibits very low entropy and can be efficiently scaled to larger depths.