Knowledge Distillation (KD) compresses computationally expensive pre-trained language models (PLMs) by transferring their knowledge to smaller models, allowing their use in resource-constrained or real-time settings. However, most smaller models fail to surpass the performance of the original larger model, resulting in sacrificing performance to improve inference speed. To address this issue, we propose Co-Training and Co-Distillation (CTCD), a novel framework that improves performance and inference speed together by co-training two models while mutually distilling knowledge. The CTCD framework successfully achieves this based on two significant findings: 1) Distilling knowledge from the smaller model to the larger model during co-training improves the performance of the larger model. 2) The enhanced performance of the larger model further boosts the performance of the smaller model. The CTCD framework shows promise as it can be combined with existing techniques like architecture design or data augmentation, replacing one-way KD methods, to achieve further performance improvement. Extensive ablation studies demonstrate the effectiveness of CTCD, and the small model distilled by CTCD outperforms the original larger model by a significant margin of 1.66 on the GLUE benchmark.
论文检索
输入标题、作者或关键词，从 2,106 篇学术成果中精准定位
Reasoning Makes Good Annotators : An Automatic Task-specific Rules Distilling Framework for Low-resource Relation Extraction
PDF ↗Relation extraction is often challenged by insufficient labeled data. Previous methods exploit knowledge from unlabeled data by generating pseudo labels in a self-training pipeline, which suffers a gradual drift problem. Logic rules, a transferable and explainable form of expert knowledge, have achieved promising success by improving the model with weak labels. But manually writing comprehensive rules set is challenging and tedious. To alleviate the human labor of writing high-quality rules, in this work, we propose ARIA, an Automatic task-specific Rules distilling framework. Specifically, we guide the pre-trained language model to reason rules as experts and compose them into robust compound rules for data labeling. Besides, ARIA could continuously enrich the rules set to power the labeling ability by discovering reliable model-labeled data for distinguishable rules generation. Experiments on two public datasets demonstrate the effectiveness of ARIA in a low-resource scenario.
Model-agnostic meta-learning has garnered attention as a promising technique for enhancing few-shot cross-lingual transfer learning in low-resource scenarios. However, little attention was paid to the impact of data selection strategies on this cross-lingual meta-transfer method, particularly the sampling of cross-lingual meta-training data (i.e. meta-tasks) at the syntactic level to reduce language gaps. In this paper, we propose a Meta-Task Collector-based Cross-lingual Meta-Transfer framework (MeTaCo-XMT) to adapt different data selection strategies to construct meta-tasks for meta-transfer learning. Syntactic differences have an effect on transfer performance, so we consider a syntactic similarity sampling strategy and propose a syntactic distance metric model consisting of a syntactic encoder block based on the pre-trained model and a distance metric block using Word Move’s Distance (WMD). Additionally, we conduct experiments with three different data selection strategies to instantiate our framework and analyze their performance impact. Experimental results on two multilingual NLP datasets, Wikiann and TydiQA, demonstrate the significant superiority of our approach compared to existing strong baselines.
Learning Easily Updated General Purpose Text Representations with Adaptable Task-Specific Prefix
PDF ↗Many real-world applications require making multiple predictions from the same text. Fine-tuning a large pre-trained language model for each downstream task causes computational burdens in the inference time due to several times of forward passes. To amortize the computational cost, freezing the language model and building lightweight models for downstream tasks based on fixed text representations are common solutions. Accordingly, how to learn fixed but general text representations that can generalize well to unseen downstream tasks becomes a challenge. Previous works have shown that the generalizability of representations can be improved by fine-tuning the pre-trained language model with some source tasks in a multi-tasking way. In this work, we propose a prefix-based method to learn the fixed text representations with source tasks. We learn a task-specific prefix for each source task independently and combine them to get the final representations. Our experimental results show that prefix-based training performs better than multi-tasking training and can update the text representations at a smaller computational cost than multi-tasking training.
Exploring the Potential of Large Language Models in Generating Code-Tracing Questions for Introductory Programming Courses
PDF ↗In this paper, we explore the application of large language models (LLMs) for generating code-tracing questions in introductory programming courses. We designed targeted prompts for GPT4, guiding it to generate code-tracing questions based on code snippets and descriptions. We established a set of human evaluation metrics to assess the quality of questions produced by the model compared to those created by human experts. Our analysis provides insights into the capabilities and potential of LLMs in generating diverse code-tracing questions. Additionally, we present a unique dataset of human and LLM-generated tracing questions, serving as a valuable resource for both the education and NLP research communities. This work contributes to the ongoing dialogue on the potential uses of LLMs in educational settings.
The sequence-to-sequence (Seq2Seq) approach has recently been widely used in grammatical error correction (GEC) and shows promising performance. However, the Seq2Seq GEC approach still suffers from two issues. First, a Seq2Seq GEC model can only be trained on parallel data, which, in GEC task, is often noisy and limited in quantity. Second, the decoder of a Seq2Seq GEC model lacks an explicit awareness of the correctness of the token being generated. In this paper, we propose a unified decoding intervention framework that employs an external critic to assess the appropriateness of the token to be generated incrementally, and then dynamically influence the choice of the next token. We discover and investigate two types of critics: a pre-trained left-to-right language model critic and an incremental target-side grammatical error detector critic. Through extensive experiments on English and Chinese datasets, our framework consistently outperforms strong baselines and achieves results competitive with state-of-the-art methods.
Formality is one of the most important linguistic properties to determine the naturalness of translation. Although a target-side context contains formality-related tokens, the sparsity within the context makes it difficult for context-aware neural machine translation (NMT) models to properly discern them. In this paper, we introduce a novel training method to explicitly inform the NMT model by pinpointing key informative tokens using a formality classifier. Given a target context, the formality classifier guides the model to concentrate on the formality-related tokens within the context. Additionally, we modify the standard cross-entropy loss, especially toward the formality-related tokens obtained from the classifier. Experimental results show that our approaches not only improve overall translation quality but also reflect the appropriate formality from the target context.
Table Understanding (TU) is a crucial aspect of information extraction that enables machines to comprehend the semantics behind tabular data. However, existing methods of TU cannot deal with the scarcity of labeled tabular data. In addition, these methods primarily focus on the textual content within the table, disregarding the inherent topological information of the table. This can lead to a misunderstanding of the tabular semantics. In this paper, we propose TabPrompt, a new framework to tackle the above challenges. Prompt-based learning has gained popularity due to its exceptional performance in few-shot learning. Thus, we introduce prompt-based learning to handle few-shot TU. Furthermore, Graph Contrastive Learning (Graph CL) demonstrates remarkable capabilities in capturing topological information, making Graph Neural Networks an ideal method for encoding tables. Hence, we develop a novel Graph CL method tailored to tabular data. This method serves as the pretext task during the pre-training phase, allowing the generation of vector representations that incorporate the table’s topological information. The experimental results of outperforming all strong baselines demonstrate the strength of our method in few-shot table understanding tasks.
Evaluation of dialogue systems requires assessing various aspects, among which appropriateness holds significance as a core element of communicative language competence. However, current evaluations heavily rely on human judgments, which are time-consuming, labor-intensive, prone to biases, and lacking objectivity. In this paper, we introduce Dialogue Act Appropriateness (DAA), a novel method that utilizes the underlying patterns of dialogue act transitions to evaluate the appropriateness of chatbot responses. We learn transition patterns from human-human dialogue corpora, evaluating chatbot appropriateness by measuring the similarity of their transition patterns to those observed in human-human dialogues. To validate DAA, we annotate a test dataset by manually evaluating the appropriateness of dialogues from multiple chatbot systems. The experimental results demonstrate a strong correlation between our evaluation metric and human ratings, establishing the reliability of DAA as a measure of dialogue appropriateness.
If a question cannot be answered with the available information, robust systems for question answering (QA) should know *not* to answer. One way to build QA models that do this is with additional training data comprised of unanswerable questions, created either by employing annotators or through automated methods for unanswerable question generation. To show that the model complexity of existing automated approaches is not justified, we examine a simpler data augmentation method for unanswerable question generation in English: performing antonym and entity swaps on answerable questions. Compared to the prior state-of-the-art, data generated with our training-free and lightweight strategy results in better models (+1.6 F1 points on SQuAD 2.0 data with BERT-large), and has higher human-judged relatedness and readability. We quantify the raw benefits of our approach compared to no augmentation across multiple encoder models, using different amounts of generated data, and also on TydiQA-MinSpan data (+9.3 F1 points with BERT-large). Our results establish swaps as a simple but strong baseline for future work.
Large language models (LLMs) have demonstrated great potential for domain-specific applications, such as the law domain. However, recent disputes over GPT-4’s law evaluation raise questions concerning their performance in real-world legal tasks. To systematically investigate their competency in the law, we design practical baseline solutions based on LLMs and test on the task of legal judgment prediction. In our solutions, LLMs can work alone to answer open questions or coordinate with an information retrieval (IR) system to learn from similar cases or solve simplified multi-choice questions. We show that similar cases and multi-choice options, namely label candidates, included in prompts can help LLMs recall domain knowledge that is critical for expertise legal reasoning. We additionally present an intriguing paradox wherein an IR system surpasses the performance of LLM+IR due to limited gains acquired by weaker LLMs from powerful IR systems. In such case, the role of LLMs becomes redundant. Our evaluation pipeline can be easily extended into other tasks to facilitate evaluations in other domains. Code is available at https://github.com/srhthu/LM-CompEval-Legal
Large Language Models (LLMs) have demonstrated impressive performance on a range of Natural Language Processing (NLP) tasks. Unfortunately, the immense amount of computations and memory accesses required for LLM training makes them prohibitively expensive in terms of hardware cost, and thus challenging to deploy in use cases such as on-device learning. In this paper, motivated by the observation that LLM training is memory-bound, we propose a novel dynamic quantization strategy, termed Dynamic Stashing Quantization (DSQ), that puts a special focus on reducing the memory operations, but also enjoys the other benefits of low precision training, such as the reduced arithmetic cost. We conduct a thorough study on two translation tasks (trained-from-scratch) and three classification tasks (fine-tuning). DSQ reduces the amount of arithmetic operations by 20.95\times and the number of DRAM operations by 2.55\times on IWSLT17 compared to the standard 16-bit fixed-point, which is widely used in on-device learning.
Knowledge graphs represent human knowledge using triplets composed of entities and relations. While most existing knowledge graph embedding methods only consider the structure of a knowledge graph, a few recently proposed multimodal methods utilize images or text descriptions of entities in a knowledge graph. In this paper, we propose visual-textual knowledge graphs (VTKGs), where not only entities but also triplets can be explained using images, and both entities and relations can accompany text descriptions. By compiling visually expressible commonsense knowledge, we construct new benchmark datasets where triplets themselves are explained by images, and the meanings of entities and relations are described using text. We propose VISTA, a knowledge graph representation learning method for VTKGs, which incorporates the visual and textual representations of entities and relations using entity encoding, relation encoding, and triplet decoding transformers. Experiments show that VISTA outperforms state-of-the-art knowledge graph completion methods in real-world VTKGs.
Implicit Discourse Relation Recognition (IDRR) involves identifying the sense label of an implicit connective between adjacent text spans. This has traditionally been approached as a classification task. However, some downstream tasks require more than just a sense label as well as the specific connective used. This paper presents Implicit Sense-labeled Connective Recognition (ISCR), which identifies the implicit connectives and their sense labels between adjacent text spans. ISCR can be treated as a classification task, but a large number of potential categories, sense labels, and uneven distribution of instances among them make this difficult. Instead, this paper handles the task as a text-generation task, using an encoder-decoder model to generate both connectives and their sense labels. Here, we explore a classification method and three kinds of text-generation methods. From our evaluation results on PDTB-3.0, we found that our method outperforms the conventional classification-based method.
Recent studies propose various data augmentation approaches to resolve the low-resource problem in natural language processing tasks. Data augmentation is a successful solution to this problem and recent strategies give variation on sentence structures to boost performance. However, these approaches can potentially lead to semantic errors and produce semantically noisy data due to the unregulated variation of sentence structures. In an effort to combat these semantic errors, we leverage slot information, the representation of the context of keywords from a sentence, and form a data augmentation strategy which we propose, called GDA. Our strategy employs algorithms that construct and manipulate rules of context-aware grammar, utilizing this slot information. The algorithms extract recurrent patterns by distinguishing words with slots and form the “rules of grammar”—a set of injective relations between a sentence’s semantics and its syntactical structure—to augment the dataset. The augmentation is done in an automated manner with the constructed rules and thus, GDA is explainable and reliable without any human intervention. We evaluate GDA with state-of-the-art data augmentation techniques, including those using pre-trained language models, and the result illustrates that GDA outperforms all other data augmentation methods by 19.38%. Extensive experiments show that GDA is an effective data augmentation strategy that incorporates word semantics for more accurate and diverse data.
With large language models surpassing human performance on an increasing number of benchmarks, we must take a principled approach for targeted evaluation of model capabilities. Inspired by pseudorandomness, we propose pseudointelligence, which captures the maxim that “(perceived) intelligence lies in the eye of the beholder.” That is, that claims of intelligence are meaningful only when their evaluator is taken into account. Concretely, we propose a complexity-theoretic framework of model evaluation cast as a dynamic interaction between a model and a learned evaluator. We demonstrate that this framework can be used to reason about two case studies in language model evaluation, as well as analyze existing evaluation methods.
Lexical Repetitions Lead to Rote Learning: Unveiling the Impact of Lexical Overlap in Train and Test Reference Summaries
PDF ↗Ideal summarization models should generalize to novel summary-worthy content without remembering reference training summaries by rote. However, a single average performance score on the entire test set is inadequate in determining such model competencies. We propose a fine-grained evaluation protocol by partitioning a test set based on the lexical similarity of reference test summaries with training summaries. We observe up to a 5x (1.2x) difference in ROUGE-2 (entity recall) scores between the subsets with the lowest and highest similarity. Next, we show that such training repetitions also make a model vulnerable to rote learning, reproducing data artifacts such as factual errors, especially when reference test summaries are lexically close to training summaries. Consequently, we propose to limit lexical repetitions in training summaries during both supervised fine-tuning and likelihood calibration stages to improve the performance on novel test cases while retaining average performance. Our automatic and human evaluations on novel test subsets and recent news articles show that limiting lexical repetitions in training summaries can prevent rote learning and improve generalization.
Parameter-Efficient Cross-lingual Transfer of Vision and Language Models via Translation-based Alignment
PDF ↗Pre-trained vision and language models such as CLIP have witnessed remarkable success in connecting images and texts with a primary focus on English texts. Despite recent efforts to extend CLIP to support other languages, disparities in performance among different languages have been observed due to uneven resource availability. Additionally, current cross-lingual transfer methods of those pre-trained models would consume excessive resources for a large number of languages. Therefore, we propose a new parameter-efficient cross-lingual transfer learning framework that utilizes a translation-based alignment method to mitigate multilingual disparities and explores parameter-efficient fine-tuning methods for parameter-efficient cross-lingual transfer. Extensive experiments on XTD and Multi30K datasets, covering 11 languages under zero-shot, few-shot, and full-dataset learning scenarios, show that our framework significantly reduces the multilingual disparities among languages and improves cross-lingual transfer results, especially in low-resource scenarios, while only keeping and fine-tuning an extremely small number of parameters compared to the full model (e.g., Our framework only requires 0.16% additional parameters of a full-model for each language in the few-shot learning scenario).
Tabular-format data is widely adopted in various real-world applications. Various machine learning models have achieved remarkable success in both industrial applications and data-science competitions. Despite these successes, most current machine learning methods for tabular data lack accurate confidence estimation, which is needed by some high-risk sensitive applications such as credit modeling and financial fraud detection. In this paper, we study the confidence estimation of machine learning models applied to tabular data. The key finding of our paper is that a real-world tabular dataset typically contains implicit sample relations, and this can further help to obtain a more accurate estimation. To this end, we introduce a general post-training confidence calibration framework named RECAL to calibrate the predictive confidence of current machine learning models by employing graph neural networks to model the relations between different samples. We perform extensive experiments on tabular datasets with both implicit and explicit graph structures and show that RECAL can significantly improve the calibration quality compared to the conventional method without considering the sample relations.
Historically, researchers and consumers have noticed a decrease in quality when applying NLP tools to minority variants of languages (i.e. Puerto Rican Spanish or Swiss German), but studies exploring this have been limited to a select few languages. Additionally, past studies have mainly been conducted in a monolingual context, so cross-linguistic trends have not been identified and tied to external factors. In this work, we conduct a comprehensive evaluation of the most influential, state-of-the-art large language models (LLMs) across two high-use applications, machine translation and automatic speech recognition, to assess their functionality on the regional dialects of several high- and low-resource languages. Additionally, we analyze how the regional dialect gap is correlated with economic, social, and linguistic factors. The impact of training data, including related factors like dataset size and its construction procedure, is shown to be significant but not consistent across models or languages, meaning a one-size-fits-all approach cannot be taken in solving the dialect gap. This work will lay the foundation for furthering the field of dialectal NLP by laying out evident disparities and identifying possible pathways for addressing them through mindful data collection.