Canada

People often imagine relevant scenes to aid in the writing process. In this work, we aim to utilize visual information for composition in the same manner as humans. We propose a method, LIVE, that makes pre-trained language models (PLMs) Learn to Imagine for Visually-augmented natural language gEneration. First, we imagine the scene based on the text: we use a diffusion model to synthesize high-quality images conditioned on the input texts. Second, we use CLIP to determine whether the text can evoke the imagination in a posterior way. Finally, our imagination is dynamic, and we conduct synthesis for each sentence rather than generate only one image for an entire paragraph. Technically, we propose a novel plug-and-play fusion layer to obtain visually-augmented representations for each text. Our vision-text fusion layer is compatible with Transformer-based architecture. We have conducted extensive experiments on four generation tasks using BART and T5, and the automatic results and human evaluation demonstrate the effectiveness of our proposed method. We will release the code, model, and data at the link: https://github.com/RUCAIBox/LIVE.

&lt;iframe src=&quot;https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/f5bc4994-0289-4aad-ae8e-b1de4c19063f&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

Learning to Imagine: Visually-Augmented Natural Language Generation

visually-augmented

pre-trained model

natural language generation

People often imagine relevant scenes to aid in the writing process. In this work, we aim to utilize visual information for composition in the same manner as humans. We propose a method, LIVE, that makes pre-trained language models (PLMs) Learn to Imagine for Visually-augmented natural language gEneration. First, we imagine the scene based on the text: we use a diffusion model to synthesize high-quality images conditioned on the input texts. Second, we use CLIP to determine whether the text can evoke the imagination in a posterior way. Finally, our imagination is dynamic, and we conduct synthesis for each sentence rather than generate only one image for an entire paragraph. Technically, we propose a novel plug-and-play fusion layer to obtain visually-augmented representations for each text. Our vision-text fusion layer is compatible with Transformer-based architecture. We have conducted extensive experiments on four generation tasks using BART and T5, and the automatic results and human evaluation demonstrate the effectiveness of our proposed method. We will release the code, model, and data at the link: https://github.com/RUCAIBox/LIVE.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/f5bc4994-0289-4aad-ae8e-b1de4c19063f" width="300" height="400"></iframe>

technical paper

### Welcome to ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics! 
<br>The conference will be held in Toronto, Canada, July 9-14, 2023.<br><br>
Following the succession of the recent conferences in our field, ACL 2023 will adopt a hybrid format.
While the impact of Covid has considerably diminished in terms of traveling, obtaining visas to Canada
entails a very long process. Moreover, the global economic conditions pose challenges for many individuals to travel to conferences. Recognizing these circumstances, we know many participants may not be
able to attend the conference in person. Therefore, we are committed to providing a great virtual platform
so everyone has the opportunity to interact with other participants and enjoy the conference. Based on the
current registered participants, approxiately 30% have chosen to attend the conference virtually. Whether
you join us in person or virtually, we sincerely hope everyone has a remarkable conference experience.<br>
This General Chair’s message is where I express my gratitude to the many individuals who have made
enormous contributions to the conference over the past year.

Read [**ACL 2023 General Chair's message**](https://docs.google.com/document/d/1WobYM7norbG4dI48s75HfJoD89qgX5a_F-6U8AteLSA/edit?usp=sharing/) in full.

##### **[Conference Handbook](https://2023.aclweb.org/downloads/acl2023-handbook.pdf)**
<br><br><br><br>

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing.

Multi-party dialogues are more difficult for models to understand than one-to-one two-party dialogues, since they involve multiple interlocutors, resulting in interweaving reply-to relations and information flows. To step over these obstacles, an effective way is to pre-train a model that understands the discourse structure of multi-party dialogues, namely, to whom each utterance is replying. However, due to the lack of explicitly annotated discourse labels in multi-party dialogue corpora, previous works fail to scale up the pre-training process by putting aside the unlabeled multi-party conversational data for nothing. To fully utilize the unlabeled data, we propose to treat the discourse structures as latent variables, then jointly infer them and pre-train the discourse-aware model by unsupervised latent variable inference methods. Experiments on multiple downstream tasks show that our pre-trained model outperforms strong baselines by large margins and achieves state-of-the-art (SOTA) results, justifying the effectiveness of our method. The official implementation of this paper is available at https://github.com/EricLee8/MPD_EMVI.

<iframe src="https://app.sli.do/event/uyG7EHDP5trs2LHubv2Gj8/embed/polls/d4e7c8db-2f36-43cd-8388-6c8c02668d5c" width="300" height="400"></iframe>

Pre-training Multi-party Dialogue Models with Latent Discourse Inference

The task of web information extraction is to extract target fields of an object from web pages, such as extracting the name, genre and actor from a movie page. Recent sequential modeling approaches have achieved state-of-the-art results on web information extraction. However, most of these methods only focus on extracting information from textual sources while ignoring the rich information from other modalities such as image and web layout. In this work, we propose a novel MUltimodal Structural Transformer (MUST) that incorporates multiple modalities for web information extraction. Concretely, we develop a structural encoder that jointly encodes the multimodal information based on the HTML structure of the web layout, where high-level DOM nodes, and low-level text and image tokens are introduced to represent the entire page. Structural attention patterns are designed to learn effective cross-modal embeddings for all DOM nodes and low-level tokens. An extensive set of experiments are conducted on WebSRC and Common Crawl benchmarks. Experimental results demonstrate the superior performance of MUST over several state-of-the-art baselines.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/a3458d22-3c7e-44cf-b64a-fabec727f1a8" width="300" height="400"></iframe>

MUSTIE: Multimodal Structural Transformer for Web Information Extraction

Document-level relation extraction (DocRE) attracts more research interest recently. While models achieve consistent performance gains in DocRE, their underlying decision rules are still understudied: Do they make the right predictions according to rationales? In this paper, we take the first step toward answering this question and then introduce a new perspective on comprehensively evaluating a model.Specifically, we first conduct annotations to provide the rationales considered by humans in DocRE. Then, we conduct investigations and discover the fact that: In contrast to humans, the representative state-of-the-art (SOTA) models in DocRE exhibit different reasoning processes. Through our proposed RE-specific attacks, we next demonstrate that the significant discrepancy in decision rules between models and humans severely damages the robustness of models. After that, we introduce mean average precision (MAP) to evaluate the understanding and reasoning capabilities of models. According to the extensive experimental results, we finally appeal to future work to consider evaluating the understanding ability of models because the improved ability renders models more trustworthy and robust to be deployed in real-world scenarios. We make our annotations and code publicly available.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/a4d4b038-ec19-4d87-a52e-00722dbdec92" width="300" height="400"></iframe>

Did the Models Understand Documents? Benchmarking Models for Language Understanding in Document-Level Relation Extraction

The high annotation costs and diverse demands of various summarization tasks motivate the development of few-shot summarization.However, despite the emergence of many summarization tasks and datasets, the current training paradigm for few-shot summarization systems ignores potentially shareable knowledge in heterogeneous datasets.To this end, we propose \textsc{UniSumm}, a unified few-shot summarization model pre-trained with multiple summarization tasks and can be prefix-tuned to excel at any few-shot summarization task.Meanwhile, to better evaluate few-shot summarizers, under the principles of diversity and robustness, we assemble and release a new benchmark \textsc{SummZoo}. It consists of $8$ summarization tasks with multiple sets of few-shot samples for each task, covering diverse domains.Experimental results and analysis show that \textsc{UniSumm} outperforms strong baselines by a large margin across all sub-tasks in \textsc{SummZoo} under both automatic and human evaluations and achieves comparable results in human evaluation compared with a GPT-3.5 model.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/d11b5822-e061-41d2-8dd5-10545654d4d9" width="300" height="400"></iframe>

UniSumm and SummZoo: Unified Model and Diverse Benchmark for Few-Shot Summarization

Most existing cross-lingual summarization (CLS) work constructs CLS corpora by simply and directly translating pre-annotated summaries from one language to another, which can contain errors from both summarization and translation processes.To address this issue, we propose ConvSumX, a cross-lingual conversation summarization benchmark, through a new annotation schema that explicitly considers source input context.ConvSumX consists of 2 sub-tasks under different real-world scenarios, with each covering 3 language directions.We conduct thorough analysis on ConvSumX and 3 widely-used manually annotated CLS corpora and empirically find that ConvSumX is more faithful towards input text.Additionally, based on the same intuition, we propose a 2-Step method, which takes both conversation and summary as input to simulate human annotation process.Experimental results show that 2-Step method surpasses strong baselines on ConvSumX under both automatic and human evaluation.Analysis shows that both source input text and summary are crucial for modeling cross-lingual summaries.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/a1eef280-969b-4ef7-8167-638824ab2456" width="300" height="400"></iframe>

Revisiting Cross-Lingual Summarization: A Corpus-based Study and A New Benchmark with Improved Annotation

Thanks to the recent success of Pre-trained Language Models (PLMs), it has become a promising research direction to develop a universal model (UIE) that can solve all typical information extraction tasks within one generative framework. Nonetheless, in real-world scenarios of UIE applications, new data of different IE tasks and domains usually come in a stream over time. A desirable UIE system should be capable of continually learning new tasks without forgetting old ones, thereby allowing knowledge and functionalities expansion without re-training the whole system. In this paper, we study the UIE system under a more challenging yet practical scenario, i.e., "lifelong learning settings, to evaluate its abilities in three aspects, including knowledge sharing and expansion, catastrophic forgetting prevention, and rapid generalization on few-shot and unseen tasks.To achieve these three goals, we present a novel parameter- and deployment-efficient prompt tuning method namely Lottery Prompt Tuning (LPT).LPT freezes the PLM's parameters and sequentially learns compact pruned prompt vectors for each task leveraging a binary prompt mask, while keeping the prompt parameters selected by the previous tasks insusceptible.Furthermore, we use a simple yet effective method to perform mask selection and show the powerful transferability of Lottery Prompts to novel tasks.Extensive experiments demonstrate that LPT consistently sets state-of-the-art performance on multiple lifelong learning settings of UIE, including task-incremental setting on seen tasks, few-shot adaptation, and zero-shot generalization on novel tasks.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/c4780440-2a31-4431-91ef-7210fea85f53" width="300" height="400"></iframe>

Prompts Can Play Lottery Tickets Well: Achieving Lifelong Information Extraction via Lottery Prompt Tuning

Influence functions (IFs) are a powerful tool for detecting anomalous examples in large scale datasets.However, they are unstable when applied to deep networks.In this paper, we provide an explanation for the instability of IFs and develop a solution to this problem.We show that IFs are unreliable when the two data points belong to two different classes.Our solution leverages class information to improve the stability of IFs.Extensive experiments show that our modification significantly improves the performance and stability of IFs while incurring no additional computational cost.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/de3b3c1b-d26c-4d37-bc87-f97d6c316ffd" width="300" height="400"></iframe>

Class based Influence Functions for Error Detection

Generative methods greatly promote aspect-based sentiment analysis via generating a sequence of sentiment elements in a specified format. However, existing studies usually predict sentiment elements in a fixed order, which ignores the effect of the interdependence of the elements in a sentiment tuple and the diversity of language expression on the results. In this work, we propose Multi-view Prompting (MVP) that aggregates sentiment elements generated in different orders, leveraging the intuition of human-like problem-solving processes from different views. Specifically, MVP introduces element order prompts to guide the language model to generate multiple sentiment tuples, each with a different element order, and then selects the most reasonable tuples by voting. MVP can naturally model multi-view and multi-task as permutations and combinations of elements, respectively, outperforming previous task-specific designed methods on multiple ABSA tasks with a single model. Extensive experiments show that MVP significantly advances the state-of-the-art performance on 10 datasets of 4 benchmark tasks, and performs quite effectively in low-resource settings. Detailed evaluation verified the effectiveness, flexibility, and cross-task transferability of MVP.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/ed4a7592-d047-4008-8c6f-ad9f0ea06104" width="300" height="400"></iframe>

MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction

Supervised visual captioning models typically require a large scale of images or videos paired with descriptions in a specific language (i.e., the vision-caption pairs) for training. However, collecting and labeling large-scale datasets is time-consuming and expensive for many scenarios and languages. Therefore, sufficient labeled pairs are usually not available. To deal with the label shortage problem, we present a simple yet effective zero-shot approach MultiCapCLIP that can generate visual captions for different scenarios and languages without any labeled vision-caption pairs of downstream datasets. In the training stage, MultiCapCLIP only requires text data for input. Then it conducts two main steps: 1) retrieving concept prompts that preserve the corresponding domain knowledge of new scenarios; 2) auto-encoding the prompts to learn writing styles to output captions in a desired language. In the testing stage, MultiCapCLIP instead takes visual data as input directly to retrieve the concept prompts to generate the final visual descriptions. The extensive experiments on image and video captioning across four benchmarks and four languages (i.e., English, Chinese, German, and French) confirm the effectiveness of our approach. Compared with state-of-the-art zero-shot and weakly-supervised methods, our method achieves 4.8% and 21.5% absolute improvements in terms of BLEU@4 and CIDEr metrics. Our code is available at https://github.com/yangbang18/MultiCapCLIP.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/7bf5c338-a3b3-4488-a04e-cb1b7a39ff66" width="300" height="400"></iframe>

MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning

In this paper, we address the Event Detection task under a zero-shot cross-lingual setting where a model is trained on a source language but evaluated on a distinct target language for which there is no labeled data available. Most recent efforts in this field follow a direct transfer approach in which the model is trained using language-invariant features and then directly applied to the target language. However, we argue that these methods fail to take advantage of the benefits of the data transfer approach where a cross-lingual model is trained on target-language data and is able to learn task-specific information from syntactical features or word-label relations in the target language. As such, we propose a hybrid knowledge-transfer approach that leverages a teacher-student framework where the teacher and student networks are trained following the direct and data transfer approaches, respectively. Our method is complemented by a hierarchical training-sample selection scheme designed to address the issue of noisy labels being generated by the teacher model. Our model achieves state-of-the-art results on 9 morphologically-diverse target languages across 3 distinct datasets, highlighting the importance of exploiting the benefits of hybrid transfer.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/d8205518-7b33-41cf-a002-f2f1b34c68a0" width="300" height="400"></iframe>

Premium content

Learning to Imagine: Visually-Augmented Natural Language Generation

Downloads

Next from ACL 2023

Pre-training Multi-party Dialogue Models with Latent Discourse Inference

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES