论文检索

Fan Xu, Pinyun Fu, Qi Huang, Bowei Zou, AiTi Aw, Mingwen Wang

Rumors spread rapidly through online social microblogs at a relatively low cost, causing substantial economic losses and negative consequences in our daily lives. Existing rumor detection models often neglect the underlying semantic coherence between text and image components in multimodal posts, as well as the challenges posed by incomplete modalities in single modal posts, such as missing text or images. This paper presents CLKD-IMRD, a novel framework for Incomplete Modality Rumor Detection. CLKD-IMRD employs Contrastive Learning and Knowledge Distillation to capture the semantic consistency between text and image pairs, while also enhancing model generalization to incomplete modalities within individual posts. Extensive experimental results demonstrate that our CLKD-IMRD outperforms state-of-the-art methods on two English and two Chinese benchmark datasets for rumor detection in social media.

Tejpalsingh Siledar, Suman Banerjee, Amey Patil, Sudhanshu Singh, Muthusamy Chelliah, Nikesh Garera, Pushpak Bhattacharyya

In e-commerce, opinion summarization is the process of condensing the opinions presented in product reviews. However, the absence of large amounts of supervised datasets presents challenges in generating both aspect-specific and general opinion summaries. Existing approaches have attempted to address these challenges through synthetic dataset creation (SDC). However, general opinion summarization models struggle to generate summaries faithful to the input reviews whereas aspect-specific opinion summarization models are limited due to their reliance on human-specified aspects and seed words. To address this, we propose SDC strategies tailored for general and aspect-specific opinion summarization. We experimented on three e-commerce test sets: Oposum+, Amazon, and Flipkart. For general opinion summarization, pre-trained language model (PLM) fine-tuned on our general synthetic dataset surpass the SOTA on average by 2.3 R1 points. Faithfulness evaluation metrics and human evaluations indicate that our model-generated summaries are more faithful to the input compared to others. For aspect-specific opinion summarization, PLM fine-tuned on our aspect-specific synthetic dataset surpass SOTA by ~ 1 R1 point without the aid of any human-specified aspects or seed words.

Jaeyeon Bae, Seokhoon Jeong, Seokun Kang, Namgi Han, Jae-Yon Lee, Hyounghun Kim, Taehwan Kim

Storytelling is multi-modal in the real world. When one tells a story, one may use all of the visualizations and sounds along with the story itself. However, prior studies on storytelling datasets and tasks have paid little attention to sound even though sound also conveys meaningful semantics of the story. Therefore, we propose to extend story understanding and telling areas by establishing a new component called background sound which is story context-based audio without any linguistic information. For this purpose, we introduce a new dataset, called Sound of Story (SoS), which has paired image and text sequences with corresponding sound or background music for a story. To the best of our knowledge, this is the largest well-curated dataset for storytelling with sound. Our SoS dataset consists of 27,354 stories with 19.6 images per story and 984 hours of speech-decoupled audio such as background music and other sounds. As benchmark tasks for storytelling with sound and the dataset, we propose retrieval tasks between modalities, and audio generation tasks from image-text sequences, introducing strong baselines for them. We believe the proposed dataset and tasks may shed light on the multi-modal understanding of storytelling in terms of sound.

Kaikai An, Ce Zheng, Bofei Gao, Haozhe Zhao, Baobao Chang

Frame identification aims to find semantic frames associated with target words in a sentence. Recent researches measure the similarity or matching score between targets and candidate frames by modeling frame definitions. However, they either lack sufficient representation learning of the definitions or face challenges in efficiently selecting the most suitable frame from over 1000 candidate frames. Moreover, commonly used lexicon filtering (lf) to obtain candidate frames for the target may ignore out-of-vocabulary targets and cause inadequate frame modeling. In this paper, we propose CoFFTEA, a \underline{Co}arse-to-\underline{F}ine \underline{F}rame and \underline{T}arget \underline{E}ncoders \underline{A}rchitecture. With contrastive learning and dual encoders, CoFFTEA efficiently and effectively models the alignment between frames and targets. By employing a coarse-to-fine curriculum learning procedure, CoFFTEA gradually learns to differentiate frames with varying degrees of similarity. Experimental results demonstrate that CoFFTEA outperforms previous models by 0.93 overall scores and 1.53 R@1 without lf. Further analysis suggests that CoFFTEA can better model the relationships between frame and frame, as well as target and target. The code for our approach is available at https://github.com/pkunlp-icler/COFFTEA.

Karel D’Oosterlinck, François Remy, Johannes Deleu, Thomas Demeester, Chris Develder, Klim Zaporojets, Aneiss Ghodsi, Simon Ellershaw, Jack Collins, Christopher Potts

Timely and accurate extraction of Adverse Drug Events (ADE) from biomedical literature is paramount for public safety, but involves slow and costly manual labor. We set out to improve drug safety monitoring (pharmacovigilance, PV) through the use of Natural Language Processing (NLP). We introduce BioDEX, a large-scale resource for Biomedical adverse Drug Event eXtraction, rooted in the historical output of drug safety reporting in the U.S. BioDEX consists of 65k abstracts and 19k full-text biomedical papers with 256k associated document-level safety reports created by medical experts. The core features of these reports include the reported weight, age, and biological sex of a patient, a set of drugs taken by the patient, the drug dosages, the reactions experienced, and whether the reaction was life threatening. In this work, we consider the task of predicting the core information of the report given its originating paper. We estimate human performance to be 72.0% F1, whereas our best model achieves 59.1% F1 (62.3 validation), indicating significant headroom. We also begin to explore ways in which these models could help professional PV reviewers. Our code and data are available at https://github.com/KarelDO/BioDEX.

Chao Zhao, Anvesh Vijjini, Snigdha Chaturvedi

Narrative comprehension is a challenging task that requires a deep understanding of the foundational elements of narratives. Acquiring this skill requires extensive annotated data. To mitigate the burden of data annotation, we present Parrot, a zero-shot approach for narrative reading comprehension through parallel reading, which involves two parallel narratives that tell the same story. By leveraging one narrative as a source of supervision signal to guide the understanding of the other, Parrot abstracts the textual content and develops genuine narrative understanding. Evaluation conducted on two narrative comprehension benchmarks demonstrates that Parrot surpasses previous zero-shot approaches and achieves comparable performance to fully supervised models. The code will be available at https://github.com/zhaochaocs/Parrot.

You Li, Jinhui Yin, Yuming Lin

Pretrained language models are expected to effectively map input text to a set of vectors while preserving the inherent relationships within the text. Consequently, designing a white-box model to compute metrics that reflect the presence of specific internal relations in these vectors has become a common approach for post-hoc interpretability analysis of pretrained language models. However, achieving interpretability in white-box models and ensuring the rigor of metric computation becomes challenging when the source model lacks inherent interpretability. Therefore, in this paper, we discuss striking a balance in this trade-off and propose a novel line to constructing metrics for understanding the mechanisms of pretrained language models. We have specifically designed a family of metrics along this line of investigation, and the model used to compute these metrics is referred to as the tree topological probe. We conducted measurements on BERT-large by using these metrics. Based on the experimental results, we propose a speculation regarding the working mechanism of BERT-like pretrained language models, as well as a strategy for enhancing fine-tuning performance by leveraging the topological probe to improve specific submodules.

Haotian Luo, Yixin Liu, Peidong Liu, Xianggen Liu

Deep generative modeling of natural languages has achieved many successes, such as producing fluent sentences and translating from one language into another. However, the development of generative modeling techniques for paraphrase generation still lags behind largely due to the challenges in addressing the complex conflicts between expression diversity and semantic preservation. This paper proposes to generate diverse and high-quality paraphrases by exploiting the pre-trained models with instance-dependent prompts. To learn generalizable prompts, we assume that the number of abstract transforming patterns of paraphrase generation (governed by prompts) is finite and usually not large. Therefore, we present vector-quantized prompts as the cues to control the generation of pre-trained models. Extensive experiments demonstrate that the proposed method achieves new state-of-art results on three benchmark datasets, including Quora, Wikianswers, and MSCOCO. We will release all the code upon acceptance.

Abhinav Rao, Aditi Khandelwal, Kumar Tanmay, Utkarsh Agarwal, Monojit Choudhury

In this position paper, we argue that instead of morally aligning LLMs to specific set of ethical principles, we should infuse generic ethical reasoning capabilities into them so that they can handle value pluralism at a global scale. When provided with an ethical policy, an LLM should be capable of making decisions that are ethically consistent to the policy. We develop a framework that integrates moral dilemmas with moral principles pertaining to different foramlisms of normative ethics, and at different levels of abstractions. Initial experiments with GPT-x models shows that while GPT-4 is a nearly perfect ethical reasoner, the models still have bias towards the moral values of Western and English speaking societies.

Xiaoying Zhang, Baolin Peng, Kun Li, Jingyan Zhou, Helen Meng

Building and maintaining end-to-end task bots using minimal human effort is a long-standing challenge in dialog research. In this work, we introduce SGP-TOD, Schema-Guided Prompting for building Task-Oriented Dialog systems effortlessly based on large language models (LLMs). Utilizing the predefined task schema, i.e., belief instruction and dialog policy, we instruct fixed LLMs to generate appropriate responses on novel tasks, without the need for training data. Specifically, SGP-TOD comprises three components: an LLM for interacting with users, a Dialog State Tracking (DST) Prompter to aid the LLM in tracking dialog states with the given belief instruction, and a Policy Prompter to direct the LLM to generate proper responses adhering to the provided dialog policy. Experimental results on Multiwoz, RADDLE, and STAR datasets show that our training-free strategy, SGP-TOD, yields state-of-the-art (SOTA) zero-shot performance, significantly surpassing the few-shot approaches. In a domain-extension setting, SGP-TOD aptly adapts to new functionalities by merely adding supplementary schema rules. We make our code and data publicly available.

Yao Xiao, Lu Xu, Jiaxi Li, Wei Lu, Xiaoli Li

While prompt tuning approaches have achieved competitive performance with high efficiency, we observe that they invariably employ the same initialization process, wherein the soft prompt is either randomly initialized or derived from an existing embedding vocabulary. In contrast to these conventional methods, this study aims to investigate an alternative way to derive soft prompt. Our empirical studies show that the soft prompt typically exhibits a low “intrinsic rank” characteristic. With such observations, we propose decomposed prompt tuning, a novel approach that utilizes low-rank matrices to initialize the soft prompt. Through the low-rank reparameterization, our method significantly reduces the number of trainable parameters while maintaining effectiveness. Experimental results on the SuperGLUE benchmark in both high-resource and low-resource scenarios demonstrate the effectiveness of the proposed method.

Mutsumi Nakamura, Santosh Mashetty, Mihir Parmar, Neeraj Varshney, Chitta Baral

Recently Large Language Models (LLMs) such as GPT-3, ChatGPT, and FLAN have led to impressive progress in Natural Language Inference (NLI) tasks. However, these models may rely on simple heuristics or artifacts in the evaluation data to achieve their high performance, which suggests that they still suffer from logical inconsistency. To assess the logical consistency of these models, we propose a LogicAttack, a method to attack NLI models using diverse logical forms of premise and hypothesis, providing a more robust evaluation of their performance. Our approach leverages a range of inference rules from propositional logic, such as Modus Tollens and Bidirectional Dilemma, to generate effective adversarial attacks and identify common vulnerabilities across multiple NLI models. We achieve an average ~53% Attack Success Rate (ASR) across multiple logic-based attacks. Moreover, we demonstrate that incorporating generated attack samples into training enhances the logical reasoning ability of the target model and decreases its vulnerability to logic-based attacks. Data and source code are available at https://github.com/msantoshmadhav/LogicAttack.

Lei Gao, Xinnan Zhang, Xian Wu, Shen Ge, Yefeng Zheng

The multi-turn doctor-patient dialogue includes rich medical knowledge, like the symptoms of the patient, the diagnosis and medication suggested by the doctor. If mined and represented properly, such medical knowledge can benefit a large range of clinical applications, including diagnosis assistance and medication recommendation. To derive structured knowledge from free text dialogues, we target a critical task: the Dialogue Medical Information Extraction (DMIE). DMIE aims to detect pre-defined clinical meaningful medical items (symptoms, surgery, etc.) as well as their statuses (positive, negative, etc.) from the dialogue. Existing approaches mainly formulate DMIE as a multi-label classification problem and ignore the relationships among medical items and statuses. Different from previous approaches, we propose a heterogeneous graph to model the relationship between items. We further propose two consecutive attention based modules to enrich the item representation with the dialogue and status. In this manner, we are able to model the relationships among medical items and statuses in the DMIE task. Experimental results on the public benchmark data set show that the proposed model outperforms previous works and achieves the state-of-the-art performance.

Kaiser Sun, Peng Qi, Yuhao Zhang, Lan Liu, William Wang, Zhiheng Huang

Generative models have been widely applied to solve extractive tasks, where parts of the input is extracted to form the desired output, and achieved significant success. For example, in extractive question answering (QA), generative models have constantly yielded state-of-the-art results. In this work, we study the issue of tokenization inconsistency that is commonly neglected in training these models. This issue damages the extractive nature of these tasks after the input and output are tokenized inconsistently by the tokenizer, and thus leads to performance drop as well as hallucination. We propose a simple yet effective fix to this issue and conduct a case study on extractive QA. We show that, with consistent tokenization, the model performs better in both in-domain and out-of-domain datasets, with a notable average of +1.7 F1 gain when a BART model is trained on SQuAD and evaluated on 8 QA datasets. Further, the model converges faster, and becomes less likely to generate out-of-context answers. Our results demonstrate the need for increased scrutiny regarding how tokenization is done in extractive tasks and the benefits of consistent tokenization during training.

Kuicai Dong, Aixin Sun, Jung-jae Kim, Xiaoli Li

Speculation detection is an important NLP task to identify text factuality. However, the extracted speculative information (e.g., speculative polarity, cue, and scope) lacks structure and poses challenges for direct utilization in downstream tasks. Open Information Extraction (OIE), on the other hand, extracts structured tuples as facts, without examining the certainty of these tuples. Bridging this gap between speculation detection and information extraction becomes imperative to generate structured speculative information and trustworthy relational tuples. Existing studies on speculation detection are defined at sentence level; but even if a sentence is determined to be speculative, not all factual tuples extracted from it are speculative. In this paper, we propose to study speculations in OIE tuples and determine whether a tuple is speculative. We formally define the research problem of tuple-level speculation detection. We then conduct detailed analysis on the LSOIE dataset which provides labels for speculative tuples. Lastly, we propose a baseline model SpecTup for this new research task.

Linhao Luo, Trang Vu, Dinh Phung, Reza Haf

Previous studies have relied on existing question-answering benchmarks to evaluate the knowledge stored in large language models (LLMs). However, this approach has limitations regarding factual knowledge coverage, as it mostly focuses on generic domains which may overlap with the pretraining data. This paper proposes a framework to systematically assess the factual knowledge of LLMs by leveraging knowledge graphs (KGs). Our framework automatically generates a set of questions and expected answers from the facts stored in a given KG, and then evaluates the accuracy of LLMs in answering these questions. We systematically evaluate the state-of-the-art LLMs with KGs in generic and specific domains. The experiment shows that ChatGPT is consistently the top performer across all domains. We also find that LLMs performance depends on the instruction finetuning, domain and question complexity and is prone to adversarial context.

Renyi Qu, Lyle Ungar, João Sedoc

We explore the role of dialog acts in style transfer, specifically empathy style transfer – rewriting a sentence to make it more empathetic without changing its meaning. Specifically, we use two novel few-shot prompting strategies: target prompting, which only uses examples of the target style (unlike traditional prompting with source/target pairs), and dialog-act-conditioned prompting, which first estimates the dialog act of the source sentence and then makes it more empathetic using few-shot examples of the same dialog act. Our study yields two key findings: (1) Target prompting typically improves empathy more effectively while maintaining the same level of semantic similarity; (2) Dialog acts matter. Dialog-act-conditioned prompting enhances empathy while preserving both semantics and the dialog-act type. Different dialog acts benefit differently from different prompting methods, highlighting the need for further investigation of the role of dialog acts in style transfer.

Seungwhan Moon, Andrea Madotto, Zhaojiang Lin, Aparajita Saraf, Amy Bearman, Babak Damavandi

We present IMU2CLIP, a novel pre-training approach to align Inertial Measurement Unit (IMU) motion sensor recordings with text and video, by projecting them into the joint representation space of Contrastive Language-Image Pre-training (CLIP). The proposed approach allows IMU2CLIP to translate human motions (as measured by IMU sensors) into their corresponding textual descriptions and videos – while preserving the transitivity across these modalities. We introduce several new IMU-based Wearable AI applications such as motion-based media search, or an LM-based multimodal reasoning with motion sensor data – all using text as the grounding platform. In addition, we show that IMU2CLIP significantly improves downstream performances when fine-tuned for each application, demonstrating its universal usage as a new pre-trained resource. Our code and models will be released publicly.

Khouloud Saadi, Jelena Mitrović, Michael Granitzer

Knowledge distillation is known as an effective technique for compressing over-parameterized language models. In this work, we propose to break down the global feature distillation task into N local sub-tasks. In this new framework, we consider each neuron in the last hidden layer of the teacher network as a specialized sub-teacher. We also consider each neuron in the last hidden layer of the student network as a focused sub-student. We make each focused sub-student learn from one corresponding specialized sub-teacher and ignore the others. This will facilitate the task for the sub-student and keep it focused. Our proposed method is novel and can be combined with other distillation techniques. Empirical results show that our proposed approach outperforms the state-of-the-art methods by maintaining higher performance on most benchmark datasets. Furthermore, we propose a randomized variant of our approach, called Masked One-to-One Mapping. Rather than learning all the N sub-tasks simultaneously, we focus on learning a subset of these sub-tasks at each optimization step. This variant enables the student to digest the received flow of knowledge more effectively and yields superior results.

Alex Wilf, Syeda Akter, Leena Mathur, Paul Liang, Sheryl Mathew, Mengrou Shou, Eric Nyberg, Louis-Philippe Morency

The self-supervised objective of masked prediction has led to promising performance gains on a variety of downstream tasks. However, while most approaches randomly mask tokens, there is strong intuition that deciding what to mask can substantially improve learning outcomes. We investigate this in continued pretraining setting in which pretrained models continue to pretrain on domain-specific data before performing some downstream task. We introduce Difference-Masking, a masking strategy that automatically chooses what to mask during continued pretraining by considering what makes a task domain different from the pretraining domain. Empirically, we find that Difference-Masking outperforms baselines on continued pretraining settings across four diverse language-only and multimodal video tasks.