PyTorchKR Papers

최신 논문

총 15,266편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2305.03101

Hybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text Tasks

Transducer and Attention based Encoder-Decoder (AED) are two widely used frameworks for speech-to-text tasks. They are designed for different purposes and each has its own benefits and drawbacks for speech-to-text tasks. In order to leverage strengths of both modeling methods, we propose a solution by combining Transducer and Attention based Encoder-Decoder (TAED) for speech-to-text tasks. The new method leverages AED's strength in non-monotonic sequence to sequence learning while retaining Transducer's streaming property. In the proposed framework, Transducer and AED share the same speech encoder. The predictor in Transducer is replaced by the decoder in the AED model, and the outputs of the decoder are conditioned on the speech inputs instead of outputs from an unconditioned language model. The proposed solution ensures that the model is optimized by covering all possible read/write scenarios and creates a matched environment for streaming applications. We evaluate the proposed approach on the \textsc{MuST-C} dataset and the findings demonstrate that TAED performs significantly better than Transducer for offline automatic speech recognition (ASR) and speech-to-text translation (ST) tasks. In the streaming case, TAED outperforms Transducer in the ASR task and one ST direction while comparable results are achieved in another translation direction.

arXiv:2305.03530

Exploring Softly Masked Language Modelling for Controllable Symbolic Music Generation

This document presents some early explorations of applying Softly Masked Language Modelling (SMLM) to symbolic music generation. SMLM can be seen as a generalisation of masked language modelling (MLM), where instead of each element of the input set being either known or unknown, each element can be known, unknown or partly known. We demonstrate some results of applying SMLM to constrained symbolic music generation using a transformer encoder architecture. Several audio examples are available at https://erl-j.github.io/smlm-web-supplement/

arXiv:2305.03513공식 코드 · Papers with Code

ChatGraph: Interpretable Text Classification by Converting ChatGPT Knowledge to Graphs

ChatGPT, as a recently launched large language model (LLM), has shown superior performance in various natural language processing (NLP) tasks. However, two major limitations hinder its potential applications: (1) the inflexibility of finetuning on downstream tasks and (2) the lack of interpretability in the decision-making process. To tackle these limitations, we propose a novel framework that leverages the power of ChatGPT for specific tasks, such as text classification, while improving its interpretability. The proposed framework conducts a knowledge graph extraction task to extract refined and structural knowledge from the raw data using ChatGPT. The rich knowledge is then converted into a graph, which is further used to train an interpretable linear classifier to make predictions. To evaluate the effectiveness of our proposed method, we conduct experiments on four datasets. The result shows that our method can significantly improve the performance compared to directly utilizing ChatGPT for text classification tasks. And our method provides a more transparent decision-making process compared with previous text classification methods.

arXiv:2305.03353공식 코드 · Papers with Code

MindGames: Targeting Theory of Mind in Large Language Models with Dynamic Epistemic Modal Logic

Theory of Mind (ToM) is a critical component of intelligence but its assessment remains the subject of heated debates. Prior research applied human ToM assessments to natural language processing models using either human-created standardized tests or rule-based templates. However, these methods primarily focus on simplistic reasoning and require further validation. Here, we leverage dynamic epistemic logic to isolate a particular component of ToM and to generate controlled problems. We also introduce new verbalization techniques to express these problems in English natural language. Our findings indicate that some language model scaling (from 70M to 6B and 350M to 174B) does not consistently yield results better than random chance. While GPT-4 demonstrates superior epistemic reasoning capabilities, there is still room for improvement. Our code and datasets are publicly available (https://huggingface.co/datasets/sileod/mindgames , https://github.com/sileod/llm-theory-of-mind )

arXiv:2305.03195

Gpt-4: A Review on Advancements and Opportunities in Natural Language Processing

Generative Pre-trained Transformer 4 (GPT-4) is the fourth-generation language model in the GPT series, developed by OpenAI, which promises significant advancements in the field of natural language processing (NLP). In this research article, we have discussed the features of GPT-4, its potential applications, and the challenges that it might face. We have also compared GPT-4 with its predecessor, GPT-3. GPT-4 has a larger model size (more than one trillion), better multilingual capabilities, improved contextual understanding, and reasoning capabilities than GPT-3. Some of the potential applications of GPT-4 include chatbots, personal assistants, language translation, text summarization, and question-answering. However, GPT-4 poses several challenges and limitations such as computational requirements, data requirements, and ethical concerns.

논문 ID: publication/3705285

Towards antigenic peptide discovery with better MHC-I binding prediction and improved benchmark methodology

The Major Histocompatibility Complex (MHC) is a crucial component of the cellular immune system in vertebrates, responsible for, among others, presenting peptides derived from intracellular proteins. The MHC-I presentation is vital in the immune response and holds great promise in vaccine development and cancer immunotherapy. In this study, we analyze the limitations of existing methods and benchmarks for MHC-I presentation. We introduce a new benchmark to measure crucial generalization properties and models’ reliability on unseen MHC molecules and peptides. Finally, we present HLABERT, a pre-trained language model which significantly surpasses prior methods on our benchmark and also sets new state-of-the-art on the old benchmarks.

arXiv:2305.03701공식 코드 · Papers with Code

LMEye: An Interactive Perception Network for Large Language Models

Training a Multimodal Large Language Model (MLLM) from scratch, like GPT-4, is resource-intensive. Regarding Large Language Models (LLMs) as the core processor for multimodal information, our paper introduces LMEye, a human-like eye with a play-and-plug interactive perception network, designed to enable dynamic interaction between LLMs and external vision information. Previous methods incorporate visual information into LLMs with a simple visual mapping network or Q-former from BLIP-2. Such networks project the image feature once yet do not consider the interaction between the image and the human input query. Hence, the obtained visual information without being connected to human intention may be inadequate for LLMs to generate intention-following responses, which we refer to as static visual information. LMEye addresses this issue by allowing the LLM to request the desired visual information aligned with various human instructions, which we term as the dynamic visual information interaction. Specifically, LMEye consists of a simple visual mapping network to provide the basic perception of an image for LLMs. It also contains additional modules responsible for acquiring requests from LLMs, performing request-based visual information interaction, and transmitting the resulting interacted visual information to LLMs, respectively. In this way, LLMs act to understand the human query, deliver the corresponding request to the request-based visual information interaction module, and generate the response based on the interleaved multimodal information. We evaluate LMEye through extensive experiments on some multimodal benchmarks, demonstrating that it significantly improves the zero-shot performance on various multimodal tasks compared to previous methods, with less parameters.

arXiv:2305.03660

Retrieval Augmented Chest X-Ray Report Generation using OpenAI GPT models

We propose Retrieval Augmented Generation (RAG) as an approach for automated radiology report writing that leverages multimodally aligned embeddings from a contrastively pretrained vision language model for retrieval of relevant candidate radiology text for an input radiology image and a general domain generative model like OpenAI text-davinci-003, gpt-3.5-turbo and gpt-4 for report generation using the relevant radiology text retrieved. This approach keeps hallucinated generations under check and provides capabilities to generate report content in the format we desire leveraging the instruction following capabilities of these generative models. Our approach achieves better clinical metrics with a BERTScore of 0.2865 ({\Delta}+ 25.88%) and Semb score of 0.4026 ({\Delta}+ 6.31%). Our approach can be broadly relevant for different clinical settings as it allows to augment the automated radiology report generation process with content relevant for that setting while also having the ability to inject user intents and requirements in the prompts as part of the report generation process to modulate the content and format of the generated reports as applicable for that clinical setting.

arXiv:2305.03584

Now It Sounds Like You: Learning Personalized Vocabulary On Device

In recent years, Federated Learning (FL) has shown significant advancements in its ability to perform various natural language processing (NLP) tasks. This work focuses on applying personalized FL for on-device language modeling. Due to limitations of memory and latency, these models cannot support the complexity of sub-word tokenization or beam search decoding, resulting in the decision to deploy a closed-vocabulary language model. However, closed-vocabulary models are unable to handle out-of-vocabulary (OOV) words belonging to specific users. To address this issue, We propose a novel technique called "OOV expansion" that improves OOV coverage and increases model accuracy while minimizing the impact on memory and latency. This method introduces a personalized "OOV adapter" that effectively transfers knowledge from a central model and learns word embedding for personalized vocabulary. OOV expansion significantly outperforms standard FL personalization methods on a set of common FL benchmarks.

arXiv:2305.02869공식 코드 · Papers with Code

Masked Structural Growth for 2x Faster Language Model Pre-training

Accelerating large language model pre-training is a critical issue in present research. In this paper, we focus on speeding up pre-training by progressively growing from a small Transformer structure to a large one. There are two main research problems associated with progressive growth: determining the optimal growth schedule, and designing efficient growth operators. In terms of growth schedule, the impact of each single dimension on a schedule's efficiency is under-explored by existing work. Regarding the growth operators, existing methods rely on the initialization of new weights to inherit knowledge, and achieve only non-strict function preservation, limiting further improvements on training dynamics. To address these issues, we propose Masked Structural Growth (MSG), including (i) growth schedules involving all possible dimensions and (ii) strictly function-preserving growth operators that is independent of the initialization of new weights. Experiments show that MSG is significantly faster than related work: we achieve up to 2.2x speedup in pre-training different types of language models while maintaining comparable or better downstream performances. Code is publicly available at https://github.com/cofe-ai/MSG.

arXiv:2305.02607

DN at SemEval-2023 Task 12: Low-Resource Language Text Classification via Multilingual Pretrained Language Model Fine-tuning

In recent years, sentiment analysis has gained significant importance in natural language processing. However, most existing models and datasets for sentiment analysis are developed for high-resource languages, such as English and Chinese, leaving low-resource languages, particularly African languages, largely unexplored. The AfriSenti-SemEval 2023 Shared Task 12 aims to fill this gap by evaluating sentiment analysis models on low-resource African languages. In this paper, we present our solution to the shared task, where we employed different multilingual XLM-R models with classification head trained on various data, including those retrained in African dialects and fine-tuned on target languages. Our team achieved the third-best results in Subtask B, Track 16: Multilingual, demonstrating the effectiveness of our approach. While our model showed relatively good results on multilingual data, it performed poorly in some languages. Our findings highlight the importance of developing more comprehensive datasets and models for low-resource African languages to advance sentiment analysis research. We also provided the solution on the github repository.

arXiv:2305.02483공식 코드 · Papers with Code

Personalized Abstractive Summarization by Tri-agent Generation Pipeline

Tailoring outputs from large language models, like ChatGPT, to implicit user preferences remains a challenge despite their impressive generative capabilities. In this paper, we propose a tri-agent generation pipeline comprising a generator, an instructor, and an editor to enhance output personalization. The generator produces an initial output, the instructor automatically generates editing instructions based on user preferences, and the editor refines the output to align with those preferences. The inference-only large language model (ChatGPT) serves as both the generator and editor, with a smaller model acting as the instructor to guide output generation. We train the instructor using editor-steered reinforcement learning, leveraging feedback from a large-scale editor model to optimize instruction generation. Experimental results on two abstractive summarization datasets demonstrate the effectiveness of our approach in generating outputs that better meet user expectations. Code is available at \url{https://github.com/Wendy-Xiao/chatgpt_editing_summ}

arXiv:2305.02363공식 코드 · Papers with Code

Entity Tracking in Language Models

Keeping track of how states of entities change as a text or dialog unfolds is a key prerequisite to discourse understanding. Yet, there have been few systematic investigations into the ability of large language models (LLMs) to track discourse entities. In this work, we present a task probing to what extent a language model can infer the final state of an entity given an English description of the initial state and a series of state-changing operations. We use this task to first investigate whether Flan-T5, GPT-3 and GPT-3.5 can track the state of entities, and find that only GPT-3.5 models, which have been pretrained on large amounts of code, exhibit this ability. We then investigate whether smaller models pretrained primarily on text can learn to track entities, through finetuning T5 on several training/evaluation splits. While performance degrades for more complex splits, we find that even when evaluated on a different set of entities from training or longer operation sequences, a finetuned model can perform non-trivial entity tracking. Taken together, these results suggest that language models can learn to track entities but pretraining on text corpora alone does not make this capacity surface.

arXiv:2305.02582공식 코드 · Papers with Code

On the Expressivity Role of LayerNorm in Transformers' Attention

Layer Normalization (LayerNorm) is an inherent component in all Transformer-based models. In this paper, we show that LayerNorm is crucial to the expressivity of the multi-head attention layer that follows it. This is in contrast to the common belief that LayerNorm's only role is to normalize the activations during the forward pass, and their gradients during the backward pass. We consider a geometric interpretation of LayerNorm and show that it consists of two components: (a) projection of the input vectors to a $d-1$ space that is orthogonal to the $\left[1,1,...,1\right]$ vector, and (b) scaling of all vectors to the same norm of $\sqrt{d}$. We show that each of these components is important for the attention layer that follows it in Transformers: (a) projection allows the attention mechanism to create an attention query that attends to all keys equally, offloading the need to learn this operation by the attention; and (b) scaling allows each key to potentially receive the highest attention, and prevents keys from being "un-select-able". We show empirically that Transformers do indeed benefit from these properties of LayeNorm in general language modeling and even in computing simple functions such as "majority". Our code is available at https://github.com/tech-srl/layer_norm_expressivity_role .

arXiv:2305.02350

Using Language Models on Low-end Hardware

This paper evaluates the viability of using fixed language models for training text classification networks on low-end hardware. We combine language models with a CNN architecture and put together a comprehensive benchmark with 8 datasets covering single-label and multi-label classification of topic, sentiment, and genre. Our observations are distilled into a list of trade-offs, concluding that there are scenarios, where not fine-tuning a language model yields competitive effectiveness at faster training, requiring only a quarter of the memory compared to fine-tuning.

arXiv:2305.02810

Interpretable Sentence Representation with Variational Autoencoders and Attention

In this thesis, we develop methods to enhance the interpretability of recent representation learning techniques in natural language processing (NLP) while accounting for the unavailability of annotated data. We choose to leverage Variational Autoencoders (VAEs) due to their efficiency in relating observations to latent generative factors and their effectiveness in data-efficient learning and interpretable representation learning. As a first contribution, we identify and remove unnecessary components in the functioning scheme of semi-supervised VAEs making them faster, smaller and easier to design. Our second and main contribution is to use VAEs and Transformers to build two models with inductive bias to separate information in latent representations into understandable concepts without annotated data. The first model, Attention-Driven VAE (ADVAE), is able to separately represent and control information about syntactic roles in sentences. The second model, QKVAE, uses separate latent variables to form keys and values for its Transformer decoder and is able to separate syntactic and semantic information in its neural representations. In transfer experiments, QKVAE has competitive performance compared to supervised models and equivalent performance to a supervised model using 50K annotated samples. Additionally, QKVAE displays improved syntactic role disentanglement capabilities compared to ADVAE. Overall, we demonstrate that it is possible to enhance the interpretability of state-of-the-art deep learning architectures for language modeling with unannotated data in situations where text data is abundant but annotations are scarce.

arXiv:2305.02549

FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction

The recent advent of self-supervised pre-training techniques has led to a surge in the use of multimodal learning in form document understanding. However, existing approaches that extend the mask language modeling to other modalities require careful multi-task tuning, complex reconstruction target designs, or additional pre-training data. In FormNetV2, we introduce a centralized multimodal graph contrastive learning strategy to unify self-supervised pre-training for all modalities in one loss. The graph contrastive objective maximizes the agreement of multimodal representations, providing a natural interplay for all modalities without special customization. In addition, we extract image features within the bounding box that joins a pair of tokens connected by a graph edge, capturing more targeted visual cues without loading a sophisticated and separately pre-trained image embedder. FormNetV2 establishes new state-of-the-art performance on FUNSD, CORD, SROIE and Payment benchmarks with a more compact model size.

arXiv:2305.02823

Surveying Generative AI's Economic Expectations

I introduce a survey of economic expectations formed by querying a large language model (LLM)'s expectations of various financial and macroeconomic variables based on a sample of news articles from the Wall Street Journal between 1984 and 2021. I find the resulting expectations closely match existing surveys including the Survey of Professional Forecasters (SPF), the American Association of Individual Investors, and the Duke CFO Survey. Importantly, I document that LLM based expectations match many of the deviations from full-information rational expectations exhibited in these existing survey series. The LLM's macroeconomic expectations exhibit under-reaction commonly found in consensus SPF forecasts. Additionally, its return expectations are extrapolative, disconnected from objective measures of expected returns, and negatively correlated with future realized returns. Finally, using a sample of articles outside of the LLM's training period I find that the correlation with existing survey measures persists -- indicating these results do not reflect memorization but generalization on the part of the LLM. My results provide evidence for the potential of LLMs to help us better understand human beliefs and navigate possible models of nonrational expectations.

arXiv:2305.03017공식 코드 · Papers with Code

Improving Code Example Recommendations on Informal Documentation Using BERT and Query-Aware LSH: A Comparative Study

Our research investigates the recommendation of code examples to aid software developers, a practice that saves developers significant time by providing ready-to-use code snippets. The focus of our study is Stack Overflow, a commonly used resource for coding discussions and solutions, particularly in the context of the Java programming language. We applied BERT, a powerful Large Language Model (LLM) that enables us to transform code examples into numerical vectors by extracting their semantic information. Once these numerical representations are prepared, we identify Approximate Nearest Neighbors (ANN) using Locality-Sensitive Hashing (LSH). Our research employed two variants of LSH: Random Hyperplane-based LSH and Query-Aware LSH. We rigorously compared these two approaches across four parameters: HitRate, Mean Reciprocal Rank (MRR), Average Execution Time, and Relevance. Our study revealed that the Query-Aware (QA) approach showed superior performance over the Random Hyperplane-based (RH) method. Specifically, it exhibited a notable improvement of 20\% to 35\% in HitRate for query pairs compared to the RH approach. Furthermore, the QA approach proved significantly more time-efficient, with its speed in creating hashing tables and assigning data samples to buckets being at least four times faster. It can return code examples within milliseconds, whereas the RH approach typically requires several seconds to recommend code examples. Due to the superior performance of the QA approach, we tested it against PostFinder and FaCoY, the state-of-the-art baselines. Our QA method showed comparable efficiency proving its potential for effective code recommendation.

arXiv:2305.03010공식 코드 · Papers with Code

Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentence

Sentence-level representations are beneficial for various natural language processing tasks. It is commonly believed that vector representations can capture rich linguistic properties. Currently, large language models (LMs) achieve state-of-the-art performance on sentence embedding. However, some recent works suggest that vector representations from LMs can cause information leakage. In this work, we further investigate the information leakage issue and propose a generative embedding inversion attack (GEIA) that aims to reconstruct input sequences based only on their sentence embeddings. Given the black-box access to a language model, we treat sentence embeddings as initial tokens' representations and train or fine-tune a powerful decoder model to decode the whole sequences directly. We conduct extensive experiments to demonstrate that our generative inversion attack outperforms previous embedding inversion attacks in classification metrics and generates coherent and contextually similar sentences as the original inputs.