论文检索

Jingyuan Qi, Minqian Liu, Ying Shen, Zhiyang Xu, Lifu Huang

Automatically generating scripts (i.e. sequences of key steps described in text) from video demonstrations and reasoning about the subsequent steps are crucial to the modern AI virtual assistants to guide humans to complete everyday tasks, especially unfamiliar ones. However, current methods for generative script learning rely heavily on well-structured preceding steps described in text and/or images or are limited to a certain domain, resulting in a disparity with real-world user scenarios. To address these limitations, we present a new benchmark challenge – MULTISCRIPT, with two new tasks on task-oriented multimodal script learning: (1) multimodal script generation, and (2) subsequent step prediction. For both tasks, the input consists of a target task name and a video illustrating what has been done to complete the target task, and the expected output is (1) a sequence of structured step descriptions in text based on the demonstration video, and (2) a single text description for the subsequent step, respectively. Built from WikiHow, MULTISCRIPT covers multimodal scripts in videos and text descriptions for over 6,655 human everyday tasks across 19 diverse domains. To establish baseline performance on MULTISCRIPT, we propose two knowledge-guided multimodal generative frameworks that incorporate the task-related knowledge prompted from large language models such as Vicuna. Experimental results show that our proposed approaches significantly improve over the competitive baselines.

Ruili Pu, Yang Li, Jun Zhao, Suge Wang, Deyu Li, Jian Liao, Jianxing Zheng

Event Causality Extraction (ECE) aims to extract the cause-effect event pairs with their structured event information from plain texts. As far as we know, the existing ECE methods mainly focus on the correlation between arguments, without explicitly modeling the causal relationship between events, and usually design two independent frameworks to extract cause events and effect events, respectively, which cannot effectively capture the dependency between the subtasks. Therefore, we propose a joint multi-label extraction framework for ECE to alleviate the above limitations. In particular, 1) we design a heterogeneous-relation-aware graph module to learn the potential relationships between events and arguments, in which we construct the heterogeneous graph by taking the predefined event types and all the words in the sentence as nodes, and modeling three relationships of "event-event", "event-argument" and "argument-argument" as edges. 2) We also design a multi-channel label enhancing module to better learn the distributed representation of each label in the multi-label extraction framework, and further enhance the interaction between the subtasks by considering the preliminary results of cause-effect type identification and event argument extraction. The experimental results on the benchmark dataset ECE-CCKS show that our approach outperforms previous state-of-the-art methods, and that our model also performs well on the complex samples with multiple cause-effect event pairs.

Tianshuo Peng, Zuchao Li, Ping Wang, Lefei Zhang, Hai Zhao

Multi-modal aspect-based sentiment analysis (MABSA) has recently attracted increasing attention. The span-based extraction methods, such as FSUIE, demonstrate strong performance in sentiment analysis due to their joint modeling of input sequences and target labels. However, previous methods still have certain limitations: (i) They ignore the difference in the focus of visual information between different analysis targets (aspect or sentiment). (ii) Combining features from uni-modal encoders directly may not be sufficient to eliminate the modal gap and can cause difficulties in capturing the image-text pairwise relevance. (iii) Existing span-based methods for MABSA ignore the pairwise relevance of target span boundaries. To tackle these limitations, we propose a novel framework called DQPSA. Specifically, our model contains a Prompt as Dual Query (PDQ) module that uses the prompt as both a visual query and a language query to extract prompt-aware visual information and strengthen the pairwise relevance between visual information and the analysis target. Additionally, we introduce an Energy-based Pairwise Expert (EPE) module that models the boundaries pairing of the analysis target from the perspective of an Energy-based Model. This expert predicts aspect or sentiment span based on pairwise stability. Experiments on three widely used benchmarks demonstrate that DQPSA outperforms previous approaches and achieves a new state-of-the-art performance. The code will be released at https://github.com/pengts/DQPSA.

Yu Pan, Ye Yuan, Yichun Yin, Jiaxin Shi, Zenglin Xu, Ming Zhang, Lifeng Shang, Xin Jiang, Qun Liu

The rapid progress of Transformers in artificial intelligence has come at the cost of increased resource consumption and greenhouse gas emissions due to growing model sizes. Prior work suggests using pretrained small models to improve training efficiency, but this approach may not be suitable for new model structures. On the other hand, training from scratch can be slow, and progressively stacking layers often fails to achieve significant acceleration. To address these challenges, we propose a novel method called Apollo, which prepares lessons for expanding operations by learning high-layer functionality during training of low layers. Our approach involves low-value-prioritized sampling (LVPS) to train different depths and weight sharing to facilitate efficient expansion. We also introduce an interpolation method for stable model depth extension. Experiments demonstrate that Apollo achieves state-of-the-art acceleration ratios, even rivaling methods using pretrained models, making it a universal and efficient solution for training deep models while reducing time, financial, and environmental costs.

Siru Ouyang, Zhuosheng Zhang, Hai Zhao

Recent years have witnessed an increasing interest in training machines with reasoning ability, which deeply relies on accurately and clearly presented clue forms. The clues are usually modeled as entity-aware knowledge in existing studies. However, those entity-aware clues are primarily focused on commonsense, making them insufficient for tasks that require knowledge of temporary facts or events, particularly in logical reasoning for reading comprehension. To address this challenge, we are motivated to cover both commonsense and temporary knowledge clues hierarchically. Specifically, we propose a general formalism of knowledge units by extracting backbone constituents of the sentence, such as the subject-verb-object formed ``facts''. We then construct a supergraph on top of the fact units, allowing for the benefit of sentence-level (relations among fact groups) and entity-level interactions (concepts or actions inside a fact). Experimental results on logical reasoning benchmarks and dialogue modeling datasets show that our approach improves the baselines substantially, and it is general across backbone models. Code is available at https://github.com/ozyyshr/FocalReasoner.

Jihong Ouyang, Zhiyao Yang, Silong Liang, Bing Wang, Yimeng Wang, Ximing Li

Aspect-based sentiment analysis (ABSA), a fine-grained sentiment classification task, has received much attention recently. Many works investigate sentiment information through opinion words, such as "good'' and "bad''. However, implicit sentiment data widely exists in the ABSA dataset, whose sentiment polarity is hard to determine due to the lack of distinct opinion words. To deal with implicit sentiment, this paper proposes an ABSA method that integrates explicit sentiment augmentations (ABSA-ESA) to add more sentiment clues. We propose an ABSA-specific explicit sentiment generation method to create such augmentations. Specifically, we post-train T5 by rule-based data and employ three strategies to constrain the sentiment polarity and aspect term of the generated augmentations. We employ Syntax Distance Weighting and Unlikelihood Contrastive Regularization in the training procedure to guide the model to generate the explicit opinion words with the same polarity as the input sentence. Meanwhile, we utilize the Constrained Beam Search to ensure the augmentations are aspect-related. We test ABSA-ESA on two ABSA benchmarks. The results show that ABSA-ESA outperforms the SOTA baselines on implicit and explicit sentiment accuracy.

Zhijie Nie, Richong Zhang, Zhongyuan Wang, Xudong Liu

Current methods for Knowledge-Based Question Answering (KBQA) usually rely on complex training techniques and model frameworks, leading to many limitations in practical applications. Recently, the emergence of In-Context Learning (ICL) capabilities in Large Language Models (LLMs) provides a simple and training-free semantic parsing paradigm for KBQA: Given a small number of questions and their labeled logical forms as demo examples, LLMs can understand the task intent and generate the logic form for a new question. However, current powerful LLMs have little exposure to logic forms during pre-training, resulting in a high format error rate. To solve this problem, we propose a code-style in-context learning method for KBQA, which converts the generation process of unfamiliar logical form into the more familiar code generation process for LLMs. Experimental results on three mainstream datasets show that our method dramatically mitigated the formatting error problem in generating logic forms while realizing a new SOTA on WebQSP, GrailQA, and GraphQ under the few-shot setting. The code and supplementary files are released at https://github.com/Arthurizijar/KB-Coder.

Thong Nguyen, Xiaobao Wu, Xinshuai Dong, Khoi M. Le, Zhiyuan Hu, Cong-Duy Nguyen, See-Kiong Ng, Anh Tuan Luu

Fully fine-tuning pretrained large-scale transformer models has become a popular paradigm for video-language modeling tasks, such as temporal language grounding and video-language summarization. With a growing number of tasks and limited training data, such full fine-tuning approach leads to costly model storage and unstable training. To overcome these shortcomings, we introduce lightweight adapters to the pre-trained model and only update them at fine-tuning time. However, existing adapters fail to capture intrinsic temporal relations among video frames or textual words. Moreover, they neglect the preservation of critical task-related information that flows from the raw video-language input into the adapter’s low-dimensional space. To address these issues, we first propose a novel REcurrent ADapter (READ) that employs recurrent computation to enable temporal modeling capability. Second, we propose Partial Video-Language Alignment (PVLA) objective via the use of partial optimal transport to maintain task-related information flowing into our READ modules. We validate our READ-PVLA framework through extensive experiments where READ-PVLA significantly outperforms all existing fine-tuning strategies on multiple low-resource temporal language grounding and video-language summarization benchmarks.

Zhaoxi Mu, Xinyu Yang, Sining Sun, Qing Yang

Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certain elements of global and local semantic information in the reference speech, which are irrelevant to speaker identity, can lead to speaker confusion within the speech extraction network. To overcome this challenge, we propose a self-supervised disentangled representation learning method. Our approach tackles this issue through a two-phase process, utilizing a reference speech encoding network and a global information disentanglement network to gradually disentangle the speaker identity information from other irrelevant factors. We exclusively employ the disentangled speaker identity information to guide the speech extraction network. Moreover, we introduce the adaptive modulation Transformer to ensure that the acoustic representation of the mixed signal remains undisturbed by the speaker embeddings. This component incorporates speaker embeddings as conditional information, facilitating natural and efficient guidance for the speech extraction network. Experimental results substantiate the effectiveness of our meticulously crafted approach, showcasing a substantial reduction in the likelihood of speaker confusion.

Alon Mor, Yonatan Belinkov, Benny Kimelfeld

Local explanation methods highlight the input tokens that have a considerable impact on the outcome of classifying the document at hand. For example, the Anchor algorithm applies a statistical analysis of the sensitivity of the classifier to changes in the token. Aggregating local explanations over a dataset provides a global explanation of the model. Such aggregation aims to detect words with the most impact, giving valuable insights about the model, like what it has learned in training and which adversarial examples expose its weaknesses. However, standard aggregation methods bear a high computational cost: a naive implementation applies a costly algorithm to each token of each document, and hence, it is infeasible for a simple user running in the scope of a short analysis session. We devise techniques for accelerating the global aggregation of the Anchor algorithm. Specifically, our goal is to compute a set of top-k words with the highest global impact according to different aggregation functions. Some of our techniques are lossless and some are lossy. We show that for a very mild loss of quality, we are able to accelerate the computation by up to 30 times, reducing the computation from hours to minutes. We also devise and study a probabilistic model that accounts for noise in the Anchor algorithm and diminishes the bias toward words that are frequent yet low in impact.

Debjyoti Mondal, Suraj Modi, Subhadarshi Panda, Rituraj Singh, Godawari Sudhakar Rao

Large Language Models (LLMs) have demonstrated impressive performance in natural language processing tasks by leveraging chain of thought (CoT) that enables step-by-step thinking. Extending LLMs with multimodal capabilities is the recent interest, but incurs computational cost and requires substantial hardware resources. To address these challenges, we propose KAM-CoT a framework that integrates CoT reasoning, Knowledge Graphs (KGs), and multiple modalities for a comprehensive understanding of multimodal tasks. KAM-CoT adopts a two-stage training process with KG grounding to generate effective rationales and answers. By incorporating external knowledge from KGs during reasoning, the model gains a deeper contextual understanding reducing hallucinations and enhancing the quality of answers. This knowledge-augmented CoT reasoning empowers the model to handle questions requiring external context, providing more informed answers. Experimental findings show KAM-CoT outperforms the state-of-the-art methods. On the ScienceQA dataset, we achieve an average accuracy of 93.87%, surpassing GPT-3.5 (75.17%) by 18% and GPT-4 (83.99%) by 10%. Remarkably, KAM-CoT achieves these results with only 280M trainable parameters at a time, demonstrating its cost-efficiency and effectiveness.

Ying Mo, Jian Yang, Jiahao Liu, Qifan Wang, Ruoyu Chen, Jingang Wang, Zhoujun Li

Cross-lingual named entity recognition (CrossNER) faces challenges stemming from uneven performance due to the scarcity of multilingual corpora, especially for non-English data. While prior efforts mainly focus on data-driven transfer methods, a significant aspect that has not been fully explored is aligning both semantic and token-level representations across diverse languages. In this paper, we propose Multi-view Contrastive Learning for Cross-lingual Named Entity Recognition (MCL-NER). Specifically, we reframe the CrossNER task into a problem of recognizing relationships between pairs of tokens. This approach taps into the inherent contextual nuances of token-to-token connections within entities, allowing us to align representations across different languages. A multi-view contrastive learning framework is introduced to encompass semantic contrasts between source, codeswitched, and target sentences, as well as contrasts among token-to-token relations. By enforcing agreement within both semantic and relational spaces, we minimize the gap between source sentences and their counterparts of both codeswitched and target sentences. This alignment extends to the relationships between diverse tokens, enhancing the projection of entities across languages. We further augment CrossNER by combining self-training with labeled source data and unlabeled target data. Our experiments on the XTREME benchmark, spanning 40 languages, demonstrate the superiority of MCL-NER over prior data-driven and model-based approaches. It achieves a substantial increase of nearly +2.0 F1 scores across a broad spectrum and establishes itself as the new state-of-the-art performer.

Emily McMilin

Modern language modeling tasks are often underspecified: for a given token prediction, many words may satisfy the user’s intent of producing natural language at inference time, however only one word will minimize the task’s loss function at training time. We introduce a simple causal mechanism to describe the role underspecification plays in the generation of spurious correlations. Despite its simplicity, our causal model directly informs the development of two lightweight black-box evaluation methods, that we apply to gendered pronoun resolution tasks on a wide range of LLMs to 1) aid in the detection of inference-time task underspecification by exploiting 2) previously unreported gender vs. time and gender vs. location spurious correlations on LLMs with a range of A) sizes: from BERT-base to GPT-3.5, B) pre-training objectives: from masked & autoregressive language modeling to a mixture of these objectives, and C) training stages: from pre-training only to reinforcement learning from human feedback (RLHF). Code and open-source demos available at https://github.com/2dot71mily/uspec.

Hongli Mao, Xian-Ling Mao, Hanlin Tang, Yu-Ming Shang, Heyan Huang

Named Entity Recognition (NER), which aims to identify the span and category of entities within text, is a fundamental task in natural language processing. Recent NER approaches have featured pre-trained transformer-based models (e.g., BERT) as a crucial encoding component to achieve state-of-the-art performance. However, due to the length limit for input text, these models typically consider text at the sentence-level and cannot capture the long-range contextual dependency within a document. To address this issue, we propose a novel Span Graph Transformer (SGT) method for document-level NER, which constructs long-range contextual dependencies at both the token and span levels. Specifically, we first retrieve relevant contextual sentences in the document for each target sentence, and jointly encode them by BERT to capture token-level dependencies. Then, our proposed model extracts candidate spans from each sentence and integrates these spans into a document-level span graph, where nested spans within sentences and identical spans across sentences are connected. By leveraging the power of Graph Transformer and well-designed position encoding, our span graph can fully exploit span-level dependencies within the document. Extensive experiments on both resource-rich nested and flat NER datasets, as well as low-resource distantly supervised NER datasets, demonstrate that proposed SGT model achieves better performance than previous state-of-the-art models.

Hieu Man, Franck Dernoncourt, Thien Huu Nguyen

To understand event structures of documents, event causality identification (ECI) emerges as a crucial task, aiming to discern causal relationships among event mentions. The latest approach for ECI has introduced advanced deep learning models where transformer-based encoding models, complemented by enriching components, are typically leveraged to learn effective event context representations for causality prediction. As such, an important step for ECI models is to transform the event context representations into causal label representations to perform logits score computation for training and inference purposes. Within this framework, event context representations might encapsulate numerous complicated and noisy structures due to the potential long context between the input events while causal label representations are intended to capture pure information about the causal relations to facilitate score estimation. Nonetheless, a notable drawback of existing ECI models stems from their reliance on simple feed-forward networks to handle the complex context-to-label representation transformation process, which might require drastic changes in the representations to hinder the learning process. To overcome this issue, our work introduces a novel method for ECI where, instead abrupt transformations, event context representations are gradually updated to achieve effective label representations. This process will be done incrementally to allow filtering of irrelevant structures at varying levels of granularity for causal relations. To realize this, we present a diffusion model to learn gradual representation transition processes between context and causal labels. It operates through a forward pass for causal label representation noising and a reverse pass for reconstructing label representations from random noise. Our experiments on different datasets across multiple languages demonstrate the advantages of the diffusion model with state-of-the-art performance for ECI.

Mingyu Derek Ma, Xiaoxuan Wang, Po-Nien Kung, P. Jeffrey Brantingham, Nanyun Peng, Wei Wang

Information extraction tasks such as event extraction require an in-depth understanding of the output structure and sub-task dependencies. They heavily rely on task-specific training data in the form of (passage, target structure) pairs to obtain reasonable performance. However, obtaining such data through human annotation is costly, leading to a pressing need for low-resource information extraction approaches that require minimal human labeling for real-world applications. Fine-tuning supervised models with synthesized training data would be a generalizable method, but the existing data generation methods either still rely on large-scale ground-truth data or cannot be applied to complicated IE tasks due to their poor performance. To address these challenges, we propose STAR, a data generation method that leverages Large Language Models (LLMs) to synthesize data instances given limited seed demonstrations, thereby boosting low-resource information extraction performance. Our approach involves generating target structures (Y) followed by generating passages (X), all accomplished with the aid of LLMs. We design fine-grained step-by-step instructions to obtain the initial data instances. We further reduce errors and improve data quality through self-reflection error identification and self-refinement with iterative revision. Our experiments show that the data generated by STAR significantly improve the performance of low-resource event extraction and relation extraction tasks, even surpassing the effectiveness of human-curated data. Human assessment of the data quality shows STAR-generated data exhibit higher passage quality and better align with the task definitions compared with the human-curated data.

Da Luo, Yanglei Gan, Rui Hou, Run Lin, Qiao Liu, Yuxiang Cai, Wannian Gao

Few-shot Relation Extraction (FSRE) aims to extract relational facts from a sparse set of labeled corpora. Recent studies have shown promising results in FSRE by employing Pre-trained Language Models (PLMs) within the framework of supervised contrastive learning, which considers both instances and label facts. However, how to effectively harness massive instance-label pairs to encompass the learned representation with semantic richness in this learning paradigm is not fully explored. To address this gap, we introduce a novel synergistic anchored contrastive pre-training framework. This framework is motivated by the insight that the diverse viewpoints conveyed through instance-label pairs capture incomplete yet complementary intrinsic textual semantics. Specifically, our framework involves a symmetrical contrastive objective that encompasses both sentence-anchored and label-anchored contrastive losses. By combining these two losses, the model establishes a robust and uniform representation space. This space effectively captures the reciprocal alignment of feature distributions among instances and relational facts, simultaneously enhancing the maximization of mutual information across diverse perspectives within the same relation. Experimental results demonstrate that our framework achieves significant performance enhancements compared to baseline models in downstream FSRE tasks. Furthermore, our approach exhibits superior adaptability to handle the challenges of domain shift and zero-shot relation extraction. Our code is available online at https://github.com/AONE-NLP/FSRE-SaCon.

Xinwei Long, Jiali Zeng, Fandong Meng, Zhiyuan Ma, Kaiyan Zhang, Bowen Zhou, Jie Zhou

Knowledge retrieval with multi-modal queries plays a crucial role in supporting knowledge-intensive multi-modal applications. However, existing methods face challenges in terms of their effectiveness and training efficiency, especially when it comes to training and integrating multiple retrievers to handle multi-modal queries. In this paper, we propose an innovative end-to-end generative framework for multi-modal knowledge retrieval. Our framework takes advantage of the fact that large language models (LLMs) can effectively serve as virtual knowledge bases, even when trained with limited data. We retrieve knowledge via a two-step process: 1) generating knowledge clues related to the queries, and 2) obtaining the relevant document by searching databases using the knowledge clue. In particular, we first introduce an object-aware prefix-tuning technique to guide multi-grained visual learning. Then, we align multi-grained visual features into the textual feature space of the LLM, employing the LLM to capture cross-modal interactions. Subsequently, we construct instruction data with a unified format for model training. Finally, we propose the knowledge-guided generation strategy to impose prior constraints in the decoding steps, thereby promoting the generation of distinctive knowledge clues. Through experiments conducted on three benchmarks, we demonstrate significant improvements ranging from 3.0% to 14.6% across all evaluation metrics when compared to strong baselines.

Yushan Liu, Zili Wang, Ruifeng Yuan

Query-focused summarization (QFS) aims to summarize the source document(s) with regard to a specific aspect of information given in a query. It plays an important role in presenting users with a concise answer summary from a set of query-relevant documents retrieved by the information retrieval system. Nonetheless, the QFS research has long been hampered by the lack of adequate datasets in terms of both quality and quantity. In this paper, we introduce a large-scale multi-document query-focused summarization dataset, called QuerySum, which contains 27,041 data samples covering diverse topics and its quality is guaranteed through human verification. Unlike some previous QFS datasets constructed directly from the question answering datasets, 74% queries in our dataset are the challenging non-factoid What-, Why-, and How- questions. More importantly, we also provide a set of similar queries together with the corresponding summaries pairs for each query as the retrieved context, presenting a new feature of QuerySum. We aim to encourage research efforts in query intention understanding in the context of QFS. Leveraging QuerySum's depth, we propose a model for query-aware multi-document summarization and set a new QFS benchmark.

Yonghao Liu, Lan Huang, Fausto Giunchiglia, Xiaoyue Feng, Renchu Guan

Text classification occupies an important role in natural language processing and has many applications in real life. Short text classification, as one of its subtopics, has attracted increasing interest from researchers since it is more challenging due to its semantic sparsity and insufficient labeled data. Recent studies attempt to combine graph learning and contrastive learning to alleviate the above problems in short text classification. Despite their fruitful success, there are still several inherent limitations. First, the generation of augmented views may disrupt the semantic structure within the text and introduce negative effects due to noise permutation. Second, they ignore the clustering-friendly features in unlabeled data and fail to further utilize the prior information in few valuable labeled data. To this end, we propose a novel model that utilizes improved Graph contrastIve learning for short text classiFicaTion (GIFT). Specifically, we construct a heterogeneous graph containing several component graphs by mining from an internal corpus and introducing an external knowledge graph. Then, we use singular value decomposition to generate augmented views for graph contrastive learning. Moreover, we employ constrained kmeans on labeled texts to learn clustering-friendly features, which facilitate cluster-oriented contrastive learning and assist in obtaining better category boundaries. Extensive experimental results show that GIFT significantly outperforms previous state-of-the-art methods. Our code can be found in https://github.com/KEAML-JLU/GIFT.