PyTorchKR Papers

최신 논문

총 1,841편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2304.11406

LaMP: When Large Language Models Meet Personalization

This paper highlights the importance of personalization in large language models and introduces the LaMP benchmark -- a novel benchmark for training and evaluating language models for producing personalized outputs. LaMP offers a comprehensive evaluation framework with diverse language tasks and multiple entries for each user profile. It consists of seven personalized tasks, spanning three text classification and four text generation tasks. We additionally propose two retrieval augmentation approaches that retrieve personal items from each user profile for personalizing language model outputs. To this aim, we study various retrieval models, including term matching, semantic matching, and time-aware methods. Extensive experiments on LaMP for zero-shot and fine-tuned language models demonstrate the efficacy of the proposed retrieval augmentation approach and highlight the impact of personalization in various natural language tasks.

arXiv:2304.11062공식 코드 · Papers with Code

Scaling Transformer to 1M tokens and beyond with RMT

A major limitation for the broader scope of problems solvable by transformers is the quadratic scaling of computational complexity with input size. In this study, we investigate the recurrent memory augmentation of pre-trained transformer models to extend input context length while linearly scaling compute. Our approach demonstrates the capability to store information in memory for sequences of up to an unprecedented two million tokens while maintaining high retrieval accuracy. Experiments with language modeling tasks show perplexity improvement as the number of processed input segments increases. These results underscore the effectiveness of our method, which has significant potential to enhance long-term dependency handling in natural language understanding and generation tasks, as well as enable large-scale context processing for memory-intensive applications.

arXiv:2304.10663

Meta Semantics: Towards better natural language understanding and reasoning

Natural language understanding is one of the most challenging topics in artificial intelligence. Deep neural network methods, particularly large language module (LLM) methods such as ChatGPT and GPT-3, have powerful flexibility to adopt informal text but are weak on logical deduction and suffer from the out-of-vocabulary (OOV) problem. On the other hand, rule-based methods such as Mathematica, Semantic web, and Lean, are excellent in reasoning but cannot handle the complex and changeable informal text. Inspired by pragmatics and structuralism, we propose two strategies to solve the OOV problem and a semantic model for better natural language understanding and reasoning.

arXiv:2304.09957공식 코드 · Papers with Code

Low-resource Bilingual Dialect Lexicon Induction with Large Language Models

Bilingual word lexicons are crucial tools for multilingual natural language understanding and machine translation tasks, as they facilitate the mapping of words in one language to their synonyms in another language. To achieve this, numerous papers have explored bilingual lexicon induction (BLI) in high-resource scenarios, using a typical pipeline consisting of two unsupervised steps: bitext mining and word alignment, both of which rely on pre-trained large language models~(LLMs). In this paper, we present an analysis of the BLI pipeline for German and two of its dialects, Bavarian and Alemannic. This setup poses several unique challenges, including the scarcity of resources, the relatedness of the languages, and the lack of standardization in the orthography of dialects. To evaluate the BLI outputs, we analyze them with respect to word frequency and pairwise edit distance. Additionally, we release two evaluation datasets comprising 1,500 bilingual sentence pairs and 1,000 bilingual word pairs. They were manually judged for their semantic similarity for each Bavarian-German and Alemannic-German language pair.

arXiv:2304.06623공식 코드 · Papers with Code

Exploring the State of the Art in Legal QA Systems

Answering questions related to the legal domain is a complex task, primarily due to the intricate nature and diverse range of legal document systems. Providing an accurate answer to a legal query typically necessitates specialized knowledge in the relevant domain, which makes this task all the more challenging, even for human experts. Question answering (QA) systems are designed to generate answers to questions asked in human languages. QA uses natural language processing to understand questions and search through information to find relevant answers. QA has various practical applications, including customer service, education, research, and cross-lingual communication. However, QA faces challenges such as improving natural language understanding and handling complex and ambiguous questions. Answering questions related to the legal domain is a complex task, primarily due to the intricate nature and diverse range of legal document systems. Providing an accurate answer to a legal query typically necessitates specialized knowledge in the relevant domain, which makes this task all the more challenging, even for human experts. At this time, there is a lack of surveys that discuss legal question answering. To address this problem, we provide a comprehensive survey that reviews 14 benchmark datasets for question-answering in the legal field as well as presents a comprehensive review of the state-of-the-art Legal Question Answering deep learning models. We cover the different architectures and techniques used in these studies and the performance and limitations of these models. Moreover, we have established a public GitHub repository where we regularly upload the most recent articles, open data, and source code. The repository is available at: \url{https://github.com/abdoelsayed2016/Legal-Question-Answering-Review}.

arXiv:2304.06184

LINGO : Visually Debiasing Natural Language Instructions to Support Task Diversity

Cross-task generalization is a significant outcome that defines mastery in natural language understanding. Humans show a remarkable aptitude for this, and can solve many different types of tasks, given definitions in the form of textual instructions and a small set of examples. Recent work with pre-trained language models mimics this learning style: users can define and exemplify a task for the model to attempt as a series of natural language prompts or instructions. While prompting approaches have led to higher cross-task generalization compared to traditional supervised learning, analyzing 'bias' in the task instructions given to the model is a difficult problem, and has thus been relatively unexplored. For instance, are we truly modeling a task, or are we modeling a user's instructions? To help investigate this, we develop LINGO, a novel visual analytics interface that supports an effective, task-driven workflow to (1) help identify bias in natural language task instructions, (2) alter (or create) task instructions to reduce bias, and (3) evaluate pre-trained model performance on debiased task instructions. To robustly evaluate LINGO, we conduct a user study with both novice and expert instruction creators, over a dataset of 1,616 linguistic tasks and their natural language instructions, spanning 55 different languages. For both user groups, LINGO promotes the creation of more difficult tasks for pre-trained models, that contain higher linguistic diversity and lower instruction bias. We additionally discuss how the insights learned in developing and evaluating LINGO can aid in the design of future dashboards that aim to minimize the effort involved in prompt creation across multiple domains.

arXiv:2304.05489

User Adaptive Language Learning Chatbots with a Curriculum

Along with the development of systems for natural language understanding and generation, dialog systems have been widely adopted for language learning and practicing. Many current educational dialog systems perform chitchat, where the generated content and vocabulary are not constrained. However, for learners in a school setting, practice through dialog is more effective if it aligns with students' curriculum and focuses on textbook vocabulary. Therefore, we adapt lexically constrained decoding to a dialog system, which urges the dialog system to include curriculum-aligned words and phrases in its generated utterances. We adopt a generative dialog system, BlenderBot3, as our backbone model and evaluate our curriculum-based dialog system with middle school students learning English as their second language. The constrained words and phrases are derived from their textbooks, suggested by their English teachers. The evaluation result demonstrates that the dialog system with curriculum infusion improves students' understanding of target words and increases their interest in practicing English.

arXiv:2304.05221공식 코드 · Papers with Code

Towards preserving word order importance through Forced Invalidation

Large pre-trained language models such as BERT have been widely used as a framework for natural language understanding (NLU) tasks. However, recent findings have revealed that pre-trained language models are insensitive to word order. The performance on NLU tasks remains unchanged even after randomly permuting the word of a sentence, where crucial syntactic information is destroyed. To help preserve the importance of word order, we propose a simple approach called Forced Invalidation (FI): forcing the model to identify permuted sequences as invalid samples. We perform an extensive evaluation of our approach on various English NLU and QA based tasks over BERT-based and attention-based models over word embeddings. Our experiments demonstrate that Forced Invalidation significantly improves the sensitivity of the models to word order.

arXiv:2304.04726공식 코드 · Papers with Code

Uncertainty-Aware Natural Language Inference with Stochastic Weight Averaging

This paper introduces Bayesian uncertainty modeling using Stochastic Weight Averaging-Gaussian (SWAG) in Natural Language Understanding (NLU) tasks. We apply the approach to standard tasks in natural language inference (NLI) and demonstrate the effectiveness of the method in terms of prediction accuracy and correlation with human annotation disagreements. We argue that the uncertainty representations in SWAG better reflect subjective interpretation and the natural variation that is also present in human language understanding. The results reveal the importance of uncertainty modeling, an often neglected aspect of neural language modeling, in NLU tasks.

arXiv:2304.03439공식 코드 · Papers with Code

Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4

Harnessing logical reasoning ability is a comprehensive natural language understanding endeavor. With the release of Generative Pretrained Transformer 4 (GPT-4), highlighted as "advanced" at reasoning tasks, we are eager to learn the GPT-4 performance on various logical reasoning tasks. This report analyses multiple logical reasoning datasets, with popular benchmarks like LogiQA and ReClor, and newly-released datasets like AR-LSAT. We test the multi-choice reading comprehension and natural language inference tasks with benchmarks requiring logical reasoning. We further construct a logical reasoning out-of-distribution dataset to investigate the robustness of ChatGPT and GPT-4. We also make a performance comparison between ChatGPT and GPT-4. Experiment results show that ChatGPT performs significantly better than the RoBERTa fine-tuning method on most logical reasoning benchmarks. With early access to the GPT-4 API we are able to conduct intense experiments on the GPT-4 model. The results show GPT-4 yields even higher performance on most logical reasoning datasets. Among benchmarks, ChatGPT and GPT-4 do relatively well on well-known datasets like LogiQA and ReClor. However, the performance drops significantly when handling newly released and out-of-distribution datasets. Logical reasoning remains challenging for ChatGPT and GPT-4, especially on out-of-distribution and natural language inference datasets. We release the prompt-style logical reasoning datasets as a benchmark suite and name it LogiEval.

arXiv:2304.02182

How to Design Translation Prompts for ChatGPT: An Empirical Study

The recently released ChatGPT has demonstrated surprising abilities in natural language understanding and natural language generation. Machine translation relies heavily on the abilities of language understanding and generation. Thus, in this paper, we explore how to assist machine translation with ChatGPT. We adopt several translation prompts on a wide range of translations. Our experimental results show that ChatGPT with designed translation prompts can achieve comparable or better performance over commercial translation systems for high-resource language translations. We further evaluate the translation quality using multiple references, and ChatGPT achieves superior performance compared to commercial systems. We also conduct experiments on domain-specific translations, the final results show that ChatGPT is able to comprehend the provided domain keyword and adjust accordingly to output proper translations. At last, we perform few-shot prompts that show consistent improvement across different base prompts. Our work provides empirical evidence that ChatGPT still has great potential in translations.

arXiv:2304.01577공식 코드 · Papers with Code

Form-NLU: Dataset for the Form Natural Language Understanding

Compared to general document analysis tasks, form document structure understanding and retrieval are challenging. Form documents are typically made by two types of authors; A form designer, who develops the form structure and keys, and a form user, who fills out form values based on the provided keys. Hence, the form values may not be aligned with the form designer's intention (structure and keys) if a form user gets confused. In this paper, we introduce Form-NLU, the first novel dataset for form structure understanding and its key and value information extraction, interpreting the form designer's intent and the alignment of user-written value on it. It consists of 857 form images, 6k form keys and values, and 4k table keys and values. Our dataset also includes three form types: digital, printed, and handwritten, which cover diverse form appearances and layouts. We propose a robust positional and logical relation-based form key-value information extraction framework. Using this dataset, Form-NLU, we first examine strong object detection models for the form layout understanding, then evaluate the key information extraction task on the dataset, providing fine-grained results for different types of forms and keys. Furthermore, we examine it with the off-the-shelf pdf layout extraction tool and prove its feasibility in real-world cases.

arXiv:2304.01282공식 코드 · Papers with Code

PEACH: Pre-Training Sequence-to-Sequence Multilingual Models for Translation with Semi-Supervised Pseudo-Parallel Document Generation

Multilingual pre-training significantly improves many multilingual NLP tasks, including machine translation. Most existing methods are based on some variants of masked language modeling and text-denoising objectives on monolingual data. Multilingual pre-training on monolingual data ignores the availability of parallel data in many language pairs. Also, some other works integrate the available human-generated parallel translation data in their pre-training. This kind of parallel data is definitely helpful, but it is limited even in high-resource language pairs. This paper introduces a novel semi-supervised method, SPDG, that generates high-quality pseudo-parallel data for multilingual pre-training. First, a denoising model is pre-trained on monolingual data to reorder, add, remove, and substitute words, enhancing the pre-training documents' quality. Then, we generate different pseudo-translations for each pre-training document using dictionaries for word-by-word translation and applying the pre-trained denoising model. The resulting pseudo-parallel data is then used to pre-train our multilingual sequence-to-sequence model, PEACH. Our experiments show that PEACH outperforms existing approaches used in training mT5 and mBART on various translation tasks, including supervised, zero- and few-shot scenarios. Moreover, PEACH's ability to transfer knowledge between similar languages makes it particularly useful for low-resource languages. Our results demonstrate that with high-quality dictionaries for generating accurate pseudo-parallel, PEACH can be valuable for low-resource languages.

arXiv:2303.17071공식 코드 · Papers with Code

DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving Agents

Large language models (LLMs) have emerged as valuable tools for many natural language understanding tasks. In safety-critical applications such as healthcare, the utility of these models is governed by their ability to generate outputs that are factually accurate and complete. In this work, we present dialog-enabled resolving agents (DERA). DERA is a paradigm made possible by the increased conversational abilities of LLMs, namely GPT-4. It provides a simple, interpretable forum for models to communicate feedback and iteratively improve output. We frame our dialog as a discussion between two agent types - a Researcher, who processes information and identifies crucial problem components, and a Decider, who has the autonomy to integrate the Researcher's information and makes judgments on the final output. We test DERA against three clinically-focused tasks. For medical conversation summarization and care plan generation, DERA shows significant improvement over the base GPT-4 performance in both human expert preference evaluations and quantitative metrics. In a new finding, we also show that GPT-4's performance (70%) on an open-ended version of the MedQA question-answering (QA) dataset (Jin et al. 2021, USMLE) is well above the passing level (60%), with DERA showing similar performance. We release the open-ended MEDQA dataset at https://github.com/curai/curai-research/tree/main/DERA.

arXiv:2303.15621

ChatGPT as a Factual Inconsistency Evaluator for Text Summarization

The performance of text summarization has been greatly boosted by pre-trained language models. A main concern of existing methods is that most generated summaries are not factually inconsistent with their source documents. To alleviate the problem, many efforts have focused on developing effective factuality evaluation metrics based on natural language inference, question answering, and syntactic dependency et al. However, these approaches are limited by either their high computational complexity or the uncertainty introduced by multi-component pipelines, resulting in only partial agreement with human judgement. Most recently, large language models(LLMs) have shown excellent performance in not only text generation but also language comprehension. In this paper, we particularly explore ChatGPT's ability to evaluate factual inconsistency under a zero-shot setting by examining it on both coarse-grained and fine-grained evaluation tasks including binary entailment inference, summary ranking, and consistency rating. Experimental results indicate that ChatGPT generally outperforms previous evaluation metrics across the three tasks, indicating its great potential for factual inconsistency evaluation. However, a closer inspection of ChatGPT's output reveals certain limitations including its preference for more lexically similar candidates, false reasoning, and inadequate understanding of instructions.

arXiv:2303.15727

Evaluation of ChatGPT for NLP-based Mental Health Applications

Large language models (LLM) have been successful in several natural language understanding tasks and could be relevant for natural language processing (NLP)-based mental health application research. In this work, we report the performance of LLM-based ChatGPT (with gpt-3.5-turbo backend) in three text-based mental health classification tasks: stress detection (2-class classification), depression detection (2-class classification), and suicidality detection (5-class classification). We obtained annotated social media posts for the three classification tasks from public datasets. Then ChatGPT API classified the social media posts with an input prompt for classification. We obtained F1 scores of 0.73, 0.86, and 0.37 for stress detection, depression detection, and suicidality detection, respectively. A baseline model that always predicted the dominant class resulted in F1 scores of 0.35, 0.60, and 0.19. The zero-shot classification accuracy obtained with ChatGPT indicates a potential use of language models for mental health classification tasks.

arXiv:2303.13809공식 코드 · Papers with Code

Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models

Generative large language models (LLMs), e.g., ChatGPT, have demonstrated remarkable proficiency across several NLP tasks, such as machine translation, text summarization. Recent research (Kocmi and Federmann, 2023) has shown that utilizing LLMs for assessing the quality of machine translation (MT) achieves state-of-the-art performance at the system level but \textit{performs poorly at the segment level}. To further improve the performance of LLMs on MT quality assessment, we investigate several prompting designs, and propose a new prompting method called \textbf{\texttt{Error Analysis Prompting}} (EAPrompt) by combining Chain-of-Thoughts (Wei et al., 2022) and Error Analysis (Lu et al., 2023). This technique emulates the commonly accepted human evaluation framework - Multidimensional Quality Metrics (MQM, Freitag et al. (2021)) and \textit{produces explainable and reliable MT evaluations at both the system and segment level}. Experimental Results from the WMT22 metrics shared task validate the effectiveness of EAPrompt on various LLMs, with different structures. Further analysis confirms that EAPrompt effectively distinguishes major errors from minor ones, while also sharing a similar distribution of the number of errors with MQM. These findings highlight the potential of EAPrompt as a human-like evaluator prompting technique for MT evaluation.

arXiv:2303.13310공식 코드 · Papers with Code

SwissBERT: The Multilingual Language Model for Switzerland

We present SwissBERT, a masked language model created specifically for processing Switzerland-related text. SwissBERT is a pre-trained model that we adapted to news articles written in the national languages of Switzerland -- German, French, Italian, and Romansh. We evaluate SwissBERT on natural language understanding tasks related to Switzerland and find that it tends to outperform previous models on these tasks, especially when processing contemporary news and/or Romansh Grischun. Since SwissBERT uses language adapters, it may be extended to Swiss German dialects in future work. The model and our open-source code are publicly released at https://github.com/ZurichNLP/swissbert.

arXiv:2303.13375

Capabilities of GPT-4 on Medical Challenge Problems

Large language models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation across various domains, including medicine. We present a comprehensive evaluation of GPT-4, a state-of-the-art LLM, on medical competency examinations and benchmark datasets. GPT-4 is a general-purpose model that is not specialized for medical problems through training or engineered to solve clinical tasks. Our analysis covers two sets of official practice materials for the USMLE, a three-step examination program used to assess clinical competency and grant licensure in the United States. We also evaluate performance on the MultiMedQA suite of benchmark datasets. Beyond measuring model performance, experiments were conducted to investigate the influence of test questions containing both text and images on model performance, probe for memorization of content during training, and study probability calibration, which is of critical importance in high-stakes applications like medicine. Our results show that GPT-4, without any specialized prompt crafting, exceeds the passing score on USMLE by over 20 points and outperforms earlier general-purpose models (GPT-3.5) as well as models specifically fine-tuned on medical knowledge (Med-PaLM, a prompt-tuned version of Flan-PaLM 540B). In addition, GPT-4 is significantly better calibrated than GPT-3.5, demonstrating a much-improved ability to predict the likelihood that its answers are correct. We also explore the behavior of the model qualitatively through a case study that shows the ability of GPT-4 to explain medical reasoning, personalize explanations to students, and interactively craft new counterfactual scenarios around a medical case. Implications of the findings are discussed for potential uses of GPT-4 in medical education, assessment, and clinical practice, with appropriate attention to challenges of accuracy and safety.

arXiv:2303.12489

Few-shot Multimodal Multitask Multilingual Learning

While few-shot learning as a transfer learning paradigm has gained significant traction for scenarios with limited data, it has primarily been explored in the context of building unimodal and unilingual models. Furthermore, a significant part of the existing literature in the domain of few-shot multitask learning perform in-context learning which requires manually generated prompts as the input, yielding varying outcomes depending on the level of manual prompt-engineering. In addition, in-context learning suffers from substantial computational, memory, and storage costs which eventually leads to high inference latency because it involves running all of the prompt's examples through the model every time a prediction is made. In contrast, methods based on the transfer learning via the fine-tuning paradigm avoid the aforementioned issues at a one-time cost of fine-tuning weights on a per-task basis. However, such methods lack exposure to few-shot multimodal multitask learning. In this paper, we propose few-shot learning for a multimodal multitask multilingual (FM3) setting by adapting pre-trained vision and language models using task-specific hypernetworks and contrastively fine-tuning them to enable few-shot learning. FM3's architecture combines the best of both worlds of in-context and fine-tuning based learning and consists of three major components: (i) multimodal contrastive fine-tuning to enable few-shot learning, (ii) hypernetwork task adaptation to perform multitask learning, and (iii) task-specific output heads to cater to a plethora of diverse tasks. FM3 learns the most prominent tasks in the vision and language domains along with their intersections, namely visual entailment (VE), visual question answering (VQA), and natural language understanding (NLU) tasks such as neural entity recognition (NER) and the GLUE benchmark including QNLI, MNLI, QQP, and SST-2.