Canada

Language Generation Models produce words based on the previous context. Although existing methods offer input attributions as explanations for a model&#39;s prediction, it is still unclear how prior words affect the model&#39;s decision throughout the layers. In this work, we leverage recent advances in explainability of the Transformer and present a procedure to analyze models for language generation. Using contrastive examples, we compare the alignment of our explanations with evidence of the linguistic phenomena, and show that our method consistently aligns better than gradient-based and perturbation-based baselines. Then, we investigate the role of MLPs inside the Transformer and show that they learn features that help the model predict words that are grammatically acceptable. Lastly, we apply our method to Neural Machine Translation models, and demonstrate that they generate human-like source-target alignments for building predictions.

&lt;iframe src=&quot;https://app.sli.do/event/t38CPUax2NoHBQcXN6okdA/embed/polls/a37d2061-1a80-4822-98cb-ba53feb66a83&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

Explaining How Transformers Use Context to Build Predictions

explainability

interpretability

transformers

### 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.

Language Generation Models produce words based on the previous context. Although existing methods offer input attributions as explanations for a model's prediction, it is still unclear how prior words affect the model's decision throughout the layers. In this work, we leverage recent advances in explainability of the Transformer and present a procedure to analyze models for language generation. Using contrastive examples, we compare the alignment of our explanations with evidence of the linguistic phenomena, and show that our method consistently aligns better than gradient-based and perturbation-based baselines. Then, we investigate the role of MLPs inside the Transformer and show that they learn features that help the model predict words that are grammatically acceptable. Lastly, we apply our method to Neural Machine Translation models, and demonstrate that they generate human-like source-target alignments for building predictions.

<iframe src="https://app.sli.do/event/t38CPUax2NoHBQcXN6okdA/embed/polls/a37d2061-1a80-4822-98cb-ba53feb66a83" width="300" height="400"></iframe>

poster

Unsupervised pre-training on millions of digital-born or scanned documents has shown promising advances in visual document understanding~(VDU). While various vision-language pre-training objectives are studied in existing solutions, the document textline, as an intrinsic granularity in VDU, has seldom been explored so far. A document textline usually contains words that are spatially and semantically correlated, which can be easily obtained from OCR engines. In this paper, we propose Wukong-Reader, trained with new pre-training objectives to leverage the structural knowledge nested in document textlines. We introduce textline-region contrastive learning to achieve fine-grained alignment between the visual regions and texts of document textlines. Furthermore, masked region modeling and textline-grid matching are also designed to enhance the visual and layout representations of textlines. Experiments show that Wukong-Reader brings superior performance on various VDU tasks in both English and Chinese. The fine-grained alignment over textlines also empowers Wukong-Reader with promising localization ability.

<iframe src="https://app.sli.do/event/t38CPUax2NoHBQcXN6okdA/embed/polls/ab821cbd-07b2-48bf-9886-d026469f7bbe" width="300" height="400"></iframe>

Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding

Graph neural networks (GNNs), which effectively use topological structures in the knowledge graphs (KG) to embed entities and relations in low-dimensional spaces, have shown great power in knowledge graph completion (KGC). KG has abundant global and local structural information, however, many GNN-based KGC models cannot capture these two types of information about the graph structure by designing complex aggregation schemes, and are not designed well to learn representations of seen entities with sparse neighborhoods in isolated subgraphs. In this paper, we find that a simple attention-based method can outperform a general GNN-based approach for KGC. We then propose a double-branch multi-attention based graph neural network (MA-GNN) to learn more expressive entity representations which contain rich global-local structural information. Specifically, we first explore the graph attention network-based local aggregator to learn entity representations. Furthermore, we propose a snowball local attention mechanism by leveraging the semantic similarity between two-hop neighbors to enrich the entity embedding. Finally, we use Transformer-based self-attention to learn long-range dependence between entities to obtain richer representations with the global graph structure and entity features. Experimental results on five benchmark datasets show that MA-GNN achieves significant improvements over strong baselines for inductive KGC.

<iframe src="https://app.sli.do/event/t38CPUax2NoHBQcXN6okdA/embed/polls/b77e6bfb-1367-422e-b668-c9928cb2bf16" width="300" height="400"></iframe>

Double-Branch Multi-Attention based Graph Neural Network for Knowledge Graph Completion

Pretrained Vision-Language Models (VLMs) have achieved remarkable performance in image retrieval from text. However, their performance drops drastically when confronted with linguistically complex texts that they struggle to comprehend. Inspired by the Divide-and-Conquer algorithm and dual-process theory, in this paper, we regard linguistically complex texts as compound proposition texts composed of multiple simple proposition sentences and propose an end-to-end Neural Divide-and-Conquer Reasoning framework, dubbed NDCR. It contains three main components: 1) Divide: a proposition generator divides the compound proposition text into simple proposition sentences and produces their corresponding representations, 2) Conquer: a pretrained VLMs-based visual-linguistic interactor achieves the interaction between decomposed proposition sentences and images, 3) Combine: a neural-symbolic reasoner combines the above reasoning states to obtain the final solution via a neural logic reasoning approach. According to the dual-process theory, the visual-linguistic interactor and neural-symbolic reasoner could be regarded as analogical reasoning System 1 and logical reasoning System 2. We conduct extensive experiments on a challenging image retrieval from contextual descriptions data set. Experimental results and analyses indicate NDCR significantly improves performance in the complex image-text reasoning problem.

<iframe src="https://app.sli.do/event/t38CPUax2NoHBQcXN6okdA/embed/polls/ef59a775-d6fb-4d06-931a-9afd1f5d7b29" width="300" height="400"></iframe>

A Neural Divide-and-Conquer Reasoning Framework for Image Retrieval from Linguistically Complex Text

Current pre-trained language models have enabled remarkable improvements in downstream tasks, but it remains difficult to distinguish effects of statistical correlation from more systematic logical reasoning grounded on the understanding of real world. We tease these factors apart by leveraging counterfactual conditionals, which force language models to predict unusual consequences based on hypothetical propositions. We introduce a set of tests from psycholinguistic experiments, as well as larger-scale controlled datasets, to probe counterfactual predictions from five pre-trained language models. We find that models are consistently able to override real-world knowledge in counterfactual scenarios, and that this effect is more robust in case of stronger baseline world knowledge---however, we also find that for most models this effect appears largely to be driven by simple lexical cues. When we mitigate effects of both world knowledge and lexical cues to test knowledge of linguistic nuances of counterfactuals, we find that only GPT-3 shows sensitivity to these nuances, though this sensitivity is also non-trivially impacted by lexical associative factors.

<iframe src="https://app.sli.do/event/t38CPUax2NoHBQcXN6okdA/embed/polls/589f8c4e-3825-4b74-a829-c86caef276a0" width="300" height="400"></iframe>

Counterfactual reasoning: Testing language models' understanding of hypothetical scenarios

In this paper, we present LLM-Blender, an innovative ensembling framework designed to attain consistently superior performance by leveraging the diverse strengths and weaknesses of multiple open-source large language models (LLMs). Our framework consists of two complementary modules: PairRanker and GenFuser, addressing the observation that optimal LLMs for different examples can significantly vary. PairRanker employs a specialized pairwise comparison method to distinguish subtle differences between candidate outputs. It jointly encodes the input text and a pair of candidate outputs, utilizing cross-attention encoders to determine the superior candidate. Our results demonstrate that PairRanker exhibits the highest correlation with ChatGPT-based ranking. By aggregating these pairwise comparisons from PairRanker, we can generate a ranking of LLMs for each example. GenFuser then aims to merge the top-ranked candidates, generating an improved output by capitalizing on their strengths and mitigating their weaknesses. To facilitate large scale evaluation, we introduce a benchmark dataset, MixInstruct, which is a mixture of multiple instruction datasets featuring oracle pairwise comparisons for testing purposes. Our LLM-BLENDER significantly surpasses the best LLMs and baseline ensembling methods across various metrics, establishing a substantial performance gap.

<iframe src="https://app.sli.do/event/t38CPUax2NoHBQcXN6okdA/embed/polls/98e3bb1c-7e64-4e09-93af-49fcc90e4e97" width="300" height="400"></iframe>

LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion

Despite the growing success of diffusion models in continuous-valued domains (e.g., images), similar efforts for discrete domains such as text have yet to match the performance of autoregressive language models. In this work, we present SSD-LM---a diffusion-based language model with two key design choices. First, SSD-LM is semi-autoregressive, iteratively generating blocks of text, allowing for flexible output length at decoding time while enabling local bidirectional context updates. Second, it is simplex-based, performing diffusion on the natural vocabulary space rather than a learned latent space, allowing us to incorporate classifier guidance and modular control using off-the-shelf classifiers without any adaptation. We evaluate SSD-LM on unconstrained text generation benchmarks, and show that it matches or outperforms strong autoregressive GPT-2 models across standard quality and diversity metrics, while vastly outperforming diffusion-based baselines. On controlled text generation, SSD-LM also outperforms competitive baselines, with an extra advantage in modularity.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/0baeb2a1-26b6-4096-8186-ade6c21d1668" width="300" height="400"></iframe>

SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control

The retrieval model is an indispensable component for real-world knowledge-intensive tasks, e.g., open-domain question answering (ODQA). As separate retrieval skills are annotated for different datasets, recent work focuses on customized methods, limiting the model transfer- ability and scalability. In this work, we propose a modular retriever where individual modules correspond to key skills that can be reused across datasets. Our approach supports flexible skill configurations based on the target domain to boost performance. To mitigate task interference, we design a novel modularization parameterization inspired by sparse Transformer. We demonstrate that our model can benefit from self-supervised pretraining on Wikipedia and fine-tuning using multiple ODQA datasets, both in a multi-task fashion. Our approach outperforms recent self-supervised retrievers in zero-shot evaluations and achieves state-of-the-art fine-tuned retrieval performance on NQ, HotpotQA and OTT-QA.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/d8a26312-66e5-47ce-8966-b47898cbcc4e" width="300" height="400"></iframe>

Chain-of-Skills: A Configurable Model for Open-Domain Question Answering

Tables are widely used in research and business, which are suitable for human consumption, but not easily machine-processable, particularly when tables are present in images.One of the main challenges to extracting data from images of tables is accurately recognizing table structures, especially for complex tables with cross rows and columns.In this study, we propose a novel multi-modal pre-training model for table structure recognition, named TableVLM.With a two-stream multi-modal transformer-based encoder-decoder architecture, TableVLM learns to capture rich table structure-related features by multiple carefully-designed unsupervised objectives inspired by the notion of masked visual-language modeling.To pre-train this model, we also created a dataset, called ComplexTable, which consists of 1,000K samples to be released publicly. Experiment results show that the model built on pre-trained TableVLM can improve the performance up to 1.97% in tree-editing-distance-score on ComplexTable.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/65b75329-48fd-4881-988b-9355c6cf9c8b" width="300" height="400"></iframe>

TableVLM: Multi-modal Pre-training for Table Structure Recognition

The inevitable private information in legal data necessitates legal artificial intelligence to study privacy-preserving and decentralized learning methods. Federated learning (FL) has merged as a promising technique for multiple participants to collaboratively train a shared model while efficiently protecting the sensitive data of participants. However, to the best of our knowledge, there is no work on applying FL to legal NLP. To fill this gap, this paper presents the first real-world FL benchmark for legal NLP, coined FEDLEGAL, which comprises five legal NLP tasks and one privacy task based on the data from Chinese courts. Based on the extensive experiments on these datasets, our results show that FL faces new challenges in terms of real-world non-IID data. The benchmark also encourages researchers to investigate privacy protection using real-world data in the FL setting, as well as deploying models in resource-constrained scenarios. The code and datasets of FEDLEGAL are available here.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/5e454aa7-3b79-4ed0-95e9-76a35a1ae5dd" width="300" height="400"></iframe>

FEDLEGAL: The First Real-World Federated Learning Benchmark for Legal NLP

Named entity recognition in real-world applications suffers from the diversity of entity types, the emergence of new entity types, and the lack of high-quality annotations. To address the above problems, this paper proposes an in-context learning-based NER approach, which can effectively inject in-context NER ability into PLMs and recognize entities of novel types on-the-fly using only a few demonstrative instances. Specifically, we model PLMs as a meta-function Lambda_{instruction, demonstrations, text}.M, and a new entity extractor can be implicitly constructed by applying new instruction and demonstrations to PLMs, i.e., (Lambda . M) }(instruction, demonstrations) ->F where F will be a new entity extractor F: text -> entities. To inject the above in-context NER ability into PLMs, we propose a meta-function pre-training algorithm, which pre-trains PLMs by comparing the (instruction, demonstration)-initialized extractor with a surrogate golden extractor. Experimental results on 4 few-shot NER datasets show that our method can effectively inject in-context NER ability into PLMs and significantly outperforms the PLMs+fine-tuning counterparts.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/c80063e8-cb65-428f-8aee-3de518f91411" width="300" height="400"></iframe>

Downloads

Next from ACL 2023

Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding

Similar lecture

Model Interpretability and Rationale Extraction by Input Mask Optimization