论文检索

Applications/Language, Speech and Dialog

Yuanzhi Wang, Yong Li, Zhen Cui

Human multimodal emotion recognition (MER) aims to perceive and understand human emotions via various heterogeneous modalities, such as language, vision, and acoustic. Compared with unimodality, the complementary information in the multimodalities facilitates robust emotion understanding. Nevertheless, in real-world scenarios, the missing modalities hinder multimodal understanding and result in degraded MER performance. In this paper, we propose an Incomplete Multimodality-Diffused emotion recognition (IMDer) method to mitigate the challenge of MER under incomplete multimodalities. To recover the missing modalities, IMDer exploits the score-based diffusion model that maps the input Gaussian noise into the desired distribution space of the missing modalities and recovers missing data abided by their original distributions. Specially, to reduce semantic ambiguity between the missing and the recovered modalities, the available modalities are embedded as the condition to guide and refine the diffusion-based recovering process. In contrast to previous work, the diffusion-based modality recovery mechanism in IMDer allows to simultaneously reach both distribution consistency and semantic disambiguation. Feature visualization of the recovered modalities illustrates the consistent modality-specific distribution and semantic alignment. Besides, quantitative experimental results verify that IMDer obtains state-of-the-art MER accuracy under various missing modality patterns.

Applications/Language, Speech and Dialog

Xin Cheng, Di Luo, Xiuying Chen, Lemao Liu, Dongyan Zhao, Rui Yan

With direct access to human-written reference as memory, retrieval-augmented generation has achieved much progress in a wide range of text generation tasks. Since better memory would typically prompt better generation (we define this as primal problem). The traditional approach for memory retrieval involves selecting memory that exhibits the highest similarity to the input. However, this method is constrained by the quality of the fixed corpus from which memory is retrieved. In this paper, by exploring the duality of the primal problem: better generation also prompts better memory, we propose a novel framework, selfmem, which addresses this limitation by iteratively employing a retrieval-augmented generator to create an unbounded memory pool and using a memory selector to choose one output as memory for the subsequent generation round. This enables the model to leverage its own output, referred to as self-memory, for improved generation. We evaluate the effectiveness of selfmem on three distinct text generation tasks: neural machine translation, abstractive text summarization, and dialogue generation, under two generation paradigms: fine-tuned small model and few-shot LLM. Our approach achieves state-of-the-art results in four directions in JRC-Acquis translation dataset, 50.3 ROUGE-1 in XSum, and 62.9 ROUGE-1 in BigPatent, demonstrating the potential of self-memory in enhancing retrieval-augmented generation models. Furthermore, we conduct thorough analyses of each component in the selfmem framework to identify current system bottlenecks and provide insights for future research.

Applications/Language, Speech and Dialog

Haobo Wang, Yiwen Dong, Ruixuan Xiao, Fei Huang, Gang Chen, Junbo Zhao

While distant supervision has been extensively explored and exploited in NLP tasks like named entity recognition, a major obstacle stems from the inevitable noisy distant labels tagged unsupervisedly. A few past works approach this problem by adopting a self-training framework with a sample-selection mechanism. In this work, we innovatively identify two types of biases that were omitted by prior work, and these biases lead to inferior performance of the distant-supervised NER setup. First, we characterize the noise concealed in the distant labels as highly structural rather than fully randomized. Second, the self-training framework would ubiquitously introduce an inherent bias that causes erroneous behavior in both sample selection and eventually prediction. To cope with these problems, we propose a novel self-training framework, dubbed DesERT. This framework augments the conventional NER predicative pathway to a dual form that effectively adapts the sample-selection process to conform to its innate distributional-bias structure. The other crucial component of DesERT composes a debiased module aiming to enhance the token representations, hence the quality of the pseudo-labels. Extensive experiments are conducted to validate the DesERT. The results show that our framework establishes a new state-of-art performance, it achieves a +2.22% average F1 score improvement on five standardized benchmarking datasets. Lastly, DesERT demonstrates its effectiveness under a new DSNER benchmark where additional distant supervision comes from the ChatGPT model.

Social Aspects/Accountability, Transparency and Interpretability

Nora Belrose, David Schneider-Joseph, Shauli Ravfogel, Ryan Cotterell, Edward Raff, Stella Biderman

Concept erasure aims to remove specified features from a representation. It can improve fairness (e.g. preventing a classifier from using gender or race) and interpretability (e.g. removing a concept to observe changes in model behavior). We introduce LEAst-squares Concept Erasure (LEACE), a closed-form method which provably prevents all linear classifiers from detecting a concept while changing the representation as little as possible, as measured by a broad class of norms. We apply LEACE to large language models with a novel procedure called concept scrubbing, which erases target concept information from _every_ layer in the network. We demonstrate our method on two tasks: measuring the reliance of language models on part-of-speech information, and reducing gender bias in BERT embeddings. Our code is available at https://github.com/EleutherAI/concept-erasure.

Applications/Language, Speech and Dialog

Baohao Liao, Shaomu Tan, Christof Monz

Parameter-efficient fine-tuning (PEFT) of pre-trained language models (PLMs) has emerged as a highly successful approach, with training only a small number of parameters without sacrificing performance and becoming the de-facto learning paradigm with the increasing size of PLMs. However, existing PEFT methods are not memory-efficient, because they still require caching most of the intermediate activations for the gradient calculation, akin to fine-tuning. One effective way to reduce the activation memory is to apply a reversible model, so the intermediate activations are not necessary to be cached and can be recomputed. Nevertheless, modifying a PLM to its reversible variant is not straightforward, since the reversible model has a distinct architecture from the currently released PLMs. In this paper, we first investigate what is a key factor for the success of existing PEFT methods, and realize that it's essential to preserve the PLM's starting point when initializing a PEFT method. With this finding, we propose memory-efficient fine-tuning (MEFT) that inserts adapters into a PLM, preserving the PLM's starting point and making it reversible without additional pre-training. We evaluate MEFT on the GLUE benchmark and five question-answering tasks with various backbones, BERT, RoBERTa, BART and OPT. MEFT significantly reduces the activation memory up to 84% of full fine-tuning with a negligible amount of trainable parameters. Moreover, MEFT achieves the same score on GLUE and a comparable score on the question-answering tasks as full fine-tuning. A similar finding is also observed for the image classification task.

Applications/Language, Speech and Dialog

Matthew Le, Apoorv Vyas, Bowen Shi, Brian Karrer, Leda Sari, Rashel Moritz, Mary Williamson, Vimal Manohar, Yossi Adi, Jay Mahadeokar 等

Large-scale generative models such as GPT and DALL-E have revolutionized the research community. These models not only generate high fidelity outputs, but are also generalists which can solve tasks not explicitly taught. In contrast, speech generative models are still primitive in terms of scale and task generalization. In this paper, we present Voicebox, the most versatile text-guided generative model for speech at scale. Voicebox is a non-autoregressive flow-matching model trained to infill speech, given audio context and text, trained on over 50K hours of speech that are not filtered or enhanced. Similar to GPT, Voicebox can perform many different tasks through in-context learning, but is more flexible as it can also condition on future context. Voicebox can be used for mono or cross-lingual zero-shot text-to-speech synthesis, noise removal, content editing, style conversion, and diverse sample generation. In particular, Voicebox outperforms the state-of-the-art zero-shot TTS model VALL-E on both intelligibility (5.9\% vs 1.9\% word error rates) and audio similarity (0.580 vs 0.681) while being up to 20 times faster. Audio samples can be found in \url{https://voicebox.metademolab.com}.

Applications/Language, Speech and Dialog

Alberto Bietti, Vivien Cabannes, Diane Bouchacourt, Herve Jegou, Leon Bottou

Large language models based on transformers have achieved great empirical successes. However, as they are deployed more widely, there is a growing need to better understand their internal mechanisms in order to make them more reliable. These models appear to store vast amounts of knowledge from their training data, and to adapt quickly to new information provided in their context or prompt. We study how transformers balance these two types of knowledge by considering a synthetic setup where tokens are generated from either global or context-specific bigram distributions. By a careful empirical analysis of the training process on a simplified two-layer transformer, we illustrate the fast learning of global bigrams and the slower development of an "induction head" mechanism for the in-context bigrams. We highlight the role of weight matrices as associative memories, provide theoretical insights on how gradients enable their learning during training, and study the role of data-distributional properties.

Applications/Language, Speech and Dialog

Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, Karthik Narasimhan

Language models are increasingly being deployed for general problem solving across a wide range of tasks, but are still confined to token-level, left-to-right decision-making processes during inference. This means they can fall short in tasks that require exploration, strategic lookahead, or where initial decisions play a pivotal role. To surmount these challenges, we introduce a new framework for language model inference, Tree of Thoughts (ToT), which generalizes over the popular Chain of Thought approach to prompting language models, and enables exploration over coherent units of text (thoughts) that serve as intermediate steps toward problem solving. ToT allows LMs to perform deliberate decision making by considering multiple different reasoning paths and self-evaluating choices to decide the next course of action, as well as looking ahead or backtracking when necessary to make global choices.Our experiments show that ToT significantly enhances language models’ problem-solving abilities on three novel tasks requiring non-trivial planning or search: Game of 24, Creative Writing, and Mini Crosswords. For instance, in Game of 24, while GPT-4 with chain-of-thought prompting only solved 4\% of tasks, our method achieved a success rate of 74\%. Code repo with all prompts: https://github.com/princeton-nlp/tree-of-thought-llm.

Deep Learning/Generative Models and Autoencoders

Max W. Y. Lam, Qiao Tian, Tang Li, Zongyu Yin, Siyuan Feng, Ming Tu, Yuliang Ji, Rui Xia, Mingbo Ma, Xuchen Song 等

Recent progress in music generation has been remarkably advanced by the state-of-the-art MusicLM, which comprises a hierarchy of three LMs, respectively, for semantic, coarse acoustic, and fine acoustic modelings. Yet, sampling with the MusicLM requires processing through these LMs one by one to obtain the fine-grained acoustic tokens, making it computationally expensive and prohibitive for a real-time generation. Efficient music generation with a quality on par with MusicLM remains a significant challenge.In this paper, we present **M**e**L**o**D**y (**M** for music; **L** for LM; **D** for diffusion), an LM-guided diffusion model that generates music audios of state-of-the-art quality meanwhile reducing 95.7\% to 99.6\% forward passes in MusicLM, respectively, for sampling 10s to 30s music. MeLoDy inherits the highest-level LM from MusicLM for semantic modeling, and applies a novel dual-path diffusion (DPD) model and an audio VAE-GAN to efficiently decode the conditioning semantic tokens into waveform. DPD is proposed to simultaneously model the coarse and fine acoustics by incorporating the semantic information into segments of latents effectively via cross-attention at each denoising step. Our experimental results suggest the superiority of MeLoDy, not only in its practical advantages on sampling speed and infinitely continuable generation, but also in its state-of-the-art musicality, audio quality, and text correlation.Our samples are available at https://Efficient-MeLoDy.github.io/.

Data-centric AI/Data augmentation

Zhi Li, Yifan Liu, Yin Zhang

We introduce Back-Modality, a novel data augmentation schema predicated on modal transformation. Data from an initial modality undergoes transformation to an intermediate modality, followed by a reverse transformation. This framework serves dual roles. On one hand, it operates as a general data augmentation strategy. On the other hand, it allows for other augmentation techniques, suitable for the intermediate modality, to enhance the initial modality. For instance, data augmentation methods applicable to pure text can be employed to augment images, thereby facilitating the cross-modality of data augmentation techniques. To validate the viability and efficacy of our framework, we proffer three instantiations of Back-Modality: back-captioning, back-imagination, and back-speech. Comprehensive evaluations across tasks such as image classification, sentiment classification, and textual entailment demonstrate that our methods consistently enhance performance under data-scarce circumstances.

Deep Learning/Algorithms

Liliang Ren, Yang Liu, Shuohang Wang, Yichong Xu, Chenguang Zhu, Cheng Xiang Zhai

Recent hybrid models combining Linear State Space Models (SSMs) with self-attention mechanisms have demonstrated impressive results across a range of sequence modeling tasks. However, current approaches apply attention modules statically and uniformly to all elements in the input sequences, leading to sub-optimal quality-efficiency trade-offs. To address this limitation, we introduce Sparse Modular Activation (SMA), a general mechanism enabling neural networks to sparsely and dynamically activate sub-modules for sequence elements in a differentiable manner. Through allowing each element to skip non-activated sub-modules, SMA reduces computation and memory consumption of neural networks at both training and inference stages. To validate the effectiveness of SMA on sequence modeling, we design a novel neural architecture, SeqBoat, which employs SMA to sparsely activate a Gated Attention Unit (GAU) based on the state representations learned from an SSM. By constraining the GAU to only conduct local attention on the activated inputs, SeqBoat can achieve linear inference complexity with theoretically infinite attention span, and provide substantially better quality-efficiency trade-off than the chunking-based models. With experiments on a wide range of tasks, including long sequence modeling, speech classification and language modeling, SeqBoat brings new state-of-the-art results among hybrid models with linear complexity, and reveals the amount of attention needed for each task through the learned sparse activation patterns. Our code is publicly available at https://github.com/renll/SeqBoat.

Applications/Language, Speech and Dialog

Zhenhailong Wang, Ansel Blume, Sha Li, Genglin Liu, Jaemin Cho, Zineng Tang, Mohit Bansal, Heng Ji

Action knowledge involves the understanding of textual, visual, and temporal aspects of actions. We introduce the **Action Dynamics Benchmark (ActionBench)** containing two carefully designed probing tasks: Action Antonym and Video Reversal, which targets multimodal alignment capabilities and temporal understanding skills of the model, respectively. Despite recent video-language models’ (VidLM) impressive performance on various benchmark tasks, our diagnostic tasks reveal their surprising deficiency (near-random performance) in action knowledge, suggesting that current models rely on object recognition abilities as a shortcut for action understanding. To remedy this, we propose a novel framework, **Paxion**, along with a new **Discriminative Video Dynamics Modeling (DVDM)** objective. The Paxion framework utilizes a **Knowledge Patcher** network to encode new action knowledge and a **Knowledge Fuser** component to integrate the Patcher into frozen VidLMs without compromising their existing capabilities. Due to limitations of the widely-used Video-Text Contrastive (VTC) loss for learning action knowledge, we introduce the DVDM objective to train the Knowledge Patcher. DVDM forces the model to encode the correlation between the action text and the correct ordering of video frames. Our extensive analyses show that Paxion and DVDM together effectively fill the gap in action knowledge understanding (~50% → 80%), while maintaining or improving performance on a wide spectrum of both object- and action-centric downstream tasks.

Applications/Language, Speech and Dialog

Szymon Tworkowski, Konrad Staniszewski, Mikołaj Pacek, Yuhuai Wu, Henryk Michalewski, Piotr Miłoś

Large language models have an exceptional capability to incorporate new information in a contextual manner. However, the full potential of such an approach is often restrained due to a limitation in the effective context length. One solution to this issue is to endow an attention layer with access to an additional context, which comprises of (key, value) pairs. Yet, as the number of documents increases, the proportion of relevant keys to irrelevant ones decreases, leading the model to focus more on the irrelevant keys. We identify a significant challenge, dubbed the distraction issue, where keys linked to different semantic values might overlap, making them hard to distinguish. To tackle this problem, we introduce the Focused Transformer (FoT), a technique that employs a training process inspired by contrastive learning. This novel approach enhances the structure of the (key, value) space, enabling an extension of the context length. Our method allows for fine-tuning pre-existing, large-scale models to lengthen their effective context. This is demonstrated by our fine-tuning of $3 B$ and $7 B$ OpenLLaMA checkpoints. The resulting models, which we name LongLLaMA, exhibit advancements in tasks requiring a long context. We further illustrate that our LongLLaMA models adeptly manage a $256 k$ context length for passkey retrieval.

Applications/Language, Speech and Dialog

Ping Guo, Xiangpeng Wei, Yue Hu, Baosong Yang, Dayiheng Liu, Fei Huang, jun xie

Expressing universal semantics common to all languages is helpful to understand the meanings of complex and culture-specific sentences. The research theme underlying this scenario focuses on learning universal representations across languages with the usage of massive parallel corpora. However, due to the sparsity and scarcity of parallel data, there is still a big challenge in learning authentic ``universals'' for any two languages. In this paper, we propose Emma-X: an EM-like Multilingual pre-training Algorithm, to learn Cross-lingual universals with the aid of excessive multilingual non-parallel data. Emma-X unifies the cross-lingual representation learning task and an extra semantic relation prediction task within an EM framework. Both the extra semantic classifier and the cross-lingual sentence encoder approximate the semantic relation of two sentences, and supervise each other until convergence. To evaluate Emma-X, we conduct experiments on xrete, a newly introduced benchmark containing 12 widely studied cross-lingual tasks that fully depend on sentence-level representations. Results reveal that Emma-X achieves state-of-the-art performance. Further geometric analysis of the built representation space with three requirements demonstrates the superiority of Emma-X over advanced models.

Applications/Language, Speech and Dialog

Chenyang Le, Yao Qian, Long Zhou, Shujie LIU, Yanmin Qian, Michael Zeng, Xuedong Huang

Joint speech-language training is challenging due to the large demand for training data and GPU consumption, as well as the modality gap between speech and language. We present ComSL, a speech-language model built atop a composite architecture of public pre-trained speech-only and language-only models and optimized data-efficiently for spoken language tasks. Particularly, we propose to incorporate cross-modality learning into transfer learning and conduct them simultaneously for downstream tasks in a multi-task learning manner. Our approach has demonstrated effectiveness in end-to-end speech-to-text translation tasks, achieving a new state-of-the-art average BLEU score of 31.5 on the multilingual speech to English text translation task for 21 languages, as measured on the public CoVoST2 evaluation set.

Applications/Language, Speech and Dialog

Shangtong Gui, Chenze Shao, Zhengrui Ma, xishan zhang, Yunji Chen, Yang Feng

Non-autoregressive Transformer(NAT) significantly accelerates the inference of neural machine translation. However, conventional NAT models suffer from limited expression power and performance degradation compared to autoregressive (AT) models due to the assumption of conditional independence among target tokens. To address these limitations, we propose a novel approach called PCFG-NAT, which leverages a specially designed Probabilistic Context-Free Grammar (PCFG) to enhance the ability of NAT models to capture complex dependencies among output tokens. Experimental results on major machine translation benchmarks demonstrate that PCFG-NAT further narrows the gap in translation quality between NAT and AT models. Moreover, PCFG-NAT facilitates a deeper understanding of the generated sentences, addressing the lack of satisfactory explainability in neural machine translation. Code is publicly available at https://github.com/ictnlp/PCFG-NAT.

Applications/Language, Speech and Dialog

Heng Wang, Shangbin Feng, Tianxing He, Zhaoxuan Tan, Xiaochuang Han, Yulia Tsvetkov

Large language models (LLMs) are increasingly adopted for a variety of tasks with implicit graphical structures, such as planning in robotics, multi-hop question answering or knowledge probing, structured commonsense reasoning, and more. While LLMs have advanced the state-of-the-art on these tasks with structure implications, whether LLMs could explicitly process textual descriptions of graphs and structures, map them to grounded conceptual spaces, and perform structured operations remains underexplored. To this end, we propose NLGraph (Natural Language Graph), a comprehensive benchmark of graph-based problem solving designed in natural language. NLGraph contains 29,370 problems, covering eight graph reasoning tasks with varying complexity from simple tasks such as connectivity and shortest path up to complex problems such as maximum flow and simulating graph neural networks. We evaluate LLMs (GPT-3/4) with various prompting approaches on the NLGraph benchmark and find that 1) language models do demonstrate preliminary graph reasoning abilities, 2) the benefit of advanced prompting and in-context learning diminishes on more complex graph problems, while 3) LLMs are also (un)surprisingly brittle in the face of spurious correlations in graph and problem settings. We then propose Build-a-Graph Prompting and Algorithmic Prompting, two instruction-based approaches to enhance LLMs in solving natural language graph problems. Build-a-Graph and Algorithmic prompting improve the performance of LLMs on NLGraph by 3.07% to 16.85% across multiple tasks and settings, while how to solve the most complicated graph reasoning tasks in our setup with language models remains an open research question.

Applications/Language, Speech and Dialog

Wenxin Tai, Yue Lei, Fan Zhou, Goce Trajcevski, Ting Zhong

Speech enhancement (SE) aims to improve the intelligibility and quality of speech in the presence of non-stationary additive noise. Deterministic deep learning models have traditionally been used for SE, but recent studies have shown that generative approaches, such as denoising diffusion probabilistic models (DDPMs), can also be effective. However, incorporating condition information into DDPMs for SE remains a challenge. We propose a model-agnostic method called DOSE that employs two efficient condition-augmentation techniques to address this challenge, based on two key insights: (1) We force the model to prioritize the condition factor when generating samples by training it with dropout operation; (2) We inject the condition information into the sampling process by providing an informative adaptive prior. Experiments demonstrate that our approach yields substantial improvements in high-quality and stable speech generation, consistency with the condition factor, and inference efficiency. Codes are publicly available at https://github.com/ICDM-UESTC/DOSE.

Applications/Language, Speech and Dialog

Noah Hollmann, Samuel Müller, Frank Hutter

As the field of automated machine learning (AutoML) advances, it becomes increasingly important to incorporate domain knowledge into these systems.We present an approach for doing so by harnessing the power of large language models (LLMs). Specifically, we introduce Context-Aware Automated Feature Engineering (CAAFE), a feature engineering method for tabular datasets that utilizes an LLM to iteratively generate additional semantically meaningful features for tabular datasets based on the description of the dataset. The method produces both Python code for creating new features and explanations for the utility of the generated features.Despite being methodologically simple, CAAFE improves performance on 11 out of 14 datasets -- boosting mean ROC AUC performance from 0.798 to 0.822 across all dataset - similar to the improvement achieved by using a random forest instead of logistic regression on our datasets. Furthermore, CAAFE is interpretable by providing a textual explanation for each generated feature.CAAFE paves the way for more extensive semi-automation in data science tasks and emphasizes the significance of context-aware solutions that can extend the scope of AutoML systems to semantic AutoML. We release our [code](url{https://github.com/automl/CAAFE), a simple [demo](url{https://colab.research.google.com/drive/1mCA8xOAJZ4MaB_alZvyARTMjhl6RZf0a) and a [python package](url{https://pypi.org/project/caafe/).

Applications/Language, Speech and Dialog

Tao Lei, Junwen Bai, Siddhartha Brahma, Joshua Ainslie, Kenton Lee, Yanqi Zhou, Nan Du, Vincent Zhao, Yuexin Wu, Bo Li 等

We propose Conditional Adapter (CoDA), a parameter-efficient transfer learning method that also improves inference efficiency. CoDA generalizes beyond standard adapter approaches to enable a new way of balancing speed and accuracy using conditional computation.Starting with an existing dense pretrained model, CoDA adds sparse activation together with a small number of new parameters and a light-weight training phase.Our experiments demonstrate that the CoDA approach provides an unexpectedly efficient way to transfer knowledge.Across a variety of language, vision, and speech tasks, CoDA achieves a 2x to 8x inference speed-up compared to the state-of-the-art Adapter approaches with moderate to no accuracy loss and the same parameter efficiency.