Ireland

Medical images are widely used in clinical decision-making, where writing radiology reports is a potential application that can be enhanced by automatic solutions to alleviate physicians&#39; workload. In general, radiology report generation is an image-text task, where cross-modal mappings between images and texts play an important role in generating high-quality reports. Although previous studies attempt to facilitate the alignment via the co-attention mechanism under supervised settings, they suffer from lacking valid and accurate correspondences due to no annotation of such alignment. In this paper, we propose an approach with reinforcement learning (RL) over a cross-modal memory (CMM) to better align visual and textual features for radiology report generation. In detail, a shared memory is used to record the mappings between visual and textual information, and the proposed reinforced algorithm is performed to learn the signal from the reports to guide the cross-modal alignment even though such reports are not directly related to how images and texts are mapped. Experimental results on two English radiology report datasets, i.e., IU X-Ray and MIMIC-CXR, show the effectiveness of our approach, where the state-of-the-art results are achieved. We further conduct human evaluation and case study which confirm the validity of the reinforced algorithm in our approach.

ACL 2022

Reinforced Cross-modal Alignment for Radiology Report Generation

alignment

radiology report generation

reinforcement learning

# Welcome everyone to ACL 2022!

The 60th Annual Meeting of the Association for Computational Linguistics is taking place May 22-27, 2022 as a hybrid event, in Dublin and online. We are happy to welcome all of you to this anniversary edition with an almost 50-50 in-person and virtual participation. 
The main conference program features oral presentations, in-person and virtual posters and demo sessions, a plenary session for our best paper presentations and awards, three amazing keynote events and two new initiatives of invited talks: Spotlight Talks for Young Rising Stars (STIRS) and The Next Big Idea Talks. Posters (including Findings of ACL 2022) and demos are grouped by areas for both the in-person and the virtual sessions. For the virtual component, the talks will be on Zoom and the posters and the demos will be in GatherTown. The Student Research Workshop will have an oral session and a poster session as part of Poster Session 1. The program also features eight Tutorials and 28 Workshops. 

 
We wish you a wonderful conference! 
[**The ACL 2022 Organizing Committee**](https://www.2022.aclweb.org/organisers)
 
[**Conference Handbook**](https://drive.google.com/file/d/1_BUCMfhMVrjG9E2e71aHdHeE28KSje0l/view?usp=sharing) 
[**Mini Handbook**](https://drive.google.com/file/d/1qlBKl0wzmlVF1oCeMQl3BahLd9nLP5Ce/view?usp=sharing) 
[**Posters and Demo guides**](https://drive.google.com/file/d/1UucMAoCNncIOaH1rMMDa0owuG9qgvJTG/view?usp=sharing)

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 (NLP). 

Medical images are widely used in clinical decision-making, where writing radiology reports is a potential application that can be enhanced by automatic solutions to alleviate physicians' workload. In general, radiology report generation is an image-text task, where cross-modal mappings between images and texts play an important role in generating high-quality reports. Although previous studies attempt to facilitate the alignment via the co-attention mechanism under supervised settings, they suffer from lacking valid and accurate correspondences due to no annotation of such alignment. In this paper, we propose an approach with reinforcement learning (RL) over a cross-modal memory (CMM) to better align visual and textual features for radiology report generation. In detail, a shared memory is used to record the mappings between visual and textual information, and the proposed reinforced algorithm is performed to learn the signal from the reports to guide the cross-modal alignment even though such reports are not directly related to how images and texts are mapped. Experimental results on two English radiology report datasets, i.e., IU X-Ray and MIMIC-CXR, show the effectiveness of our approach, where the state-of-the-art results are achieved. We further conduct human evaluation and case study which confirm the validity of the reinforced algorithm in our approach.

poster

Offensive intention can be implicitly hidden in ambiguous text. Previous work on offensive text detection (Explicit OTD) predicts a label based on contextual representations of the surface ambiguous text. We propose the Implicit OTD task to classify text by its offensive intention and show that it is more difficult than Explicit OTD. We provide a possible approach of applying reasoning to reach the offensive intention with the chain of reasoning. We construct a dataset annotated with chains of reasoning for the research to find offensive intention in ambiguous text. We also provide analysis on the necessary knowledge to build the chain of reasoning.

Rethinking Offensive Text Detection as a Multi-Hop Reasoning Problem

Recent work points existing MWP solving models rely on shallow heuristics to generate equations. We look at this issue and hypothesize it is because existing methods overlook the outlining and distinction of MWP patterns. We first investigate how a neural network understands MWP patterns only from semantics, and then propose a contrastive learning approach based on our observation, which helps the neural network perceive the divergence of patterns. Experiments on Math23k and MathQA verify the effectiveness of our method.

Seeking Patterns, Not just Memorizing Procedures: Contrastive Learning for Solving Math Word Problems

Code mixing is the linguistic phenomenon where bilingual speakers tend to switch between two or more languages in conversations. Recent work on code-mixing in computational settings has leveraged social media code mixed texts to train NLP models. For capturing the variety of code mixing in, and across corpus, Language ID (LID) tags based measures (CMI) have been proposed. Syntactical variety/patterns of code-mixing and their relationship vis-a-vis computational model’s performance is under explored. In this work, we investigate a collection of English(en)-Hindi(hi) code-mixed datasets from a syntactic lens to propose, SyM CoM , an indicator of syntactic variety in code-mixed text, with intuitive theoretical bounds. We train SoTA en-hi PoS tagger, accuracy of 93.4%, to reliably compute PoS tags on a corpus, and demonstrate the utility of SyM CoM by applying it on various syntactical categories on a collection of datasets, and compare datasets using the measure.

SyMCoM - Syntactic Measure of Code Mixing A Study Of English-Hindi Code-Mixing

Syntactic information has been proved to be useful for transformer-based pre-trained language models. Previous studies often rely on additional syntax-guided attention components to enhance the transformer, which require more parameters and additional syntactic parsing in downstream tasks. This increase in complexity severely limits the application of syntax-enhanced language model in a wide range of scenarios. In order to inject syntactic knowledge effectively and efficiently into pre-trained language models, we propose a novel syntax-guided contrastive learning method which does not change the transformer architecture. Based on constituency and dependency structures of syntax trees, we design phrase-guided and tree-guided contrastive objectives, and optimize them in the pre-training stage, so as to help the pre-trained language model to capture rich syntactic knowledge in its representations. Experimental results show that our contrastive method achieves consistent improvements in a variety of tasks, including grammatical error detection, entity tasks, structural probing and GLUE. Detailed analysis further verifies that the improvements come from the utilization of syntactic information, and the learned attention weights are more explainable in terms of linguistics.

Syntax-guided Contrastive Learning for Pre-trained Language Model

The table-based fact verification task has recently gained widespread attention and yet remains to be a very challenging problem. It inherently requires informative reasoning over natural language together with different numerical and logical reasoning on tables (e.g., count, superlative, comparative). Considering that, we exploit mixture-of-experts and present in this paper a new method: Self-adaptive Mixture-of-Experts Network (SaMoE). Specifically, we have developed a mixture-of-experts neural network to recognize and execute different types of reasoning---the network is composed of multiple experts, each handling a specific part of the semantics for reasoning, whereas a management module is applied to decide the contribution of each expert network to the verification result. A self-adaptive method is developed to teach the management module combining results of different experts more efficiently without external knowledge. The experimental results illustrate that our framework achieves 85.1% accuracy on the benchmark dataset TabFact, comparable with the previous state-of-the-art models. We hope our framework can serve as a new baseline for table-based verification.

Table-based Fact Verification with Self-adaptive Mixture of Experts

Generating natural and informative texts has been a long-standing problem in NLP. Much effort has been dedicated into incorporating pre-trained language models (PLMs) with various open-world knowledge, such as knowledge graphs or wiki pages. However, their ability to access and manipulate the task-specific knowledge is still limited on downstream tasks, as this type of knowledge is usually not well covered in PLMs and is hard to acquire. To address the problem, we propose augmenting TExt Generation via Task-specific and Open-world Knowledge (TegTok) in a unified framework. Our model selects knowledge entries from two types of knowledge sources through dense retrieval and then injects them into the input encoding and output decoding stages respectively on the basis of PLMs. With the help of these two types of knowledge, our model can learn what and how to generate. Experiments on two text generation tasks of dialogue generation and question generation, and on two datasets show that our method achieves better performance than various baseline models.

TegTok: Augmenting Text Generation via Task-specific and Open-world Knowledge

Vision-Language Pre-training (VLP) has achieved impressive performance on various
cross-modal downstream tasks. However, most existing methods can only learn from
aligned image-caption data and rely heavily on expensive regional features, which greatly limits their scalability and performance. In this paper, we propose an end-to-end unifiedmodal pre-training framework, namely UNIMO-2, for joint learning on both aligned image-caption data and unaligned image-only and text-only corpus. We build a unified Transformer model to jointly learn visual representations, textual representations and semantic alignment between images and texts. In particular, we propose to conduct grounded learning on both images and texts via a sharing grounded space, which helps bridge unaligned images and texts, and align the visual and textual semantic spaces on different types of corpora. The experiments show that our grounded learning method can improve textual and visual semantic alignment for improving performance on various cross-modal tasks. Moreover, benefiting from effective joint modeling of different types of corpora, our model also achieves impressive performance on single-modal visual and textual tasks

UNIMO-2: End-to-End Unified Vision-Language Grounded Learning

Recognizing the language of ambiguous texts has become a main challenge in language identification (LID). When using multilingual applications, users have their own language preferences, which can be regarded as external knowledge for LID. Nevertheless, current studies do not consider the inter-personal variations due to the lack of user annotated training data. To fill this gap, we introduce preference-aware LID and propose a novel unsupervised learning strategy. Concretely, we construct pseudo training set for each user by extracting training samples from a standard LID corpus according to his/her historical language distribution. Besides, we contribute the first user labeled LID test set called "U-LID". Experimental results reveal that our model can incarnate user traits and significantly outperforms existing LID systems on handling ambiguous texts. Our code and benchmark have been released.

Unsupervised Preference-Aware Language Identification

We present two simple modifications for word-level perturbation: Word Replacement considering Length (WR-L) and Compositional Word Replacement (CWR).
In conventional word replacement, a word in an input is replaced with a word sampled from the entire vocabulary, regardless of the length and context of the target word.
WR-L considers the length of a target word by sampling words from the Poisson distribution.
CWR considers the compositional candidates by restricting the source of sampling to related words that appear in subword regularization.
Experimental results showed that the combination of WR-L and CWR improved the performance of text classification and machine translation.

Word-level Perturbation Considering Word Length and Compositional Subwords

Large pretrained generative models like GPT-3 often suffer from hallucinating
non-existent or incorrect content, which undermines their potential merits in
real applications. Existing work usually attempts to detect these
hallucinations based on a corresponding oracle reference at a sentence or
document level. However ground-truth references may not be readily available
for many free-form text generation applications, and sentence- or
document-level detection may fail to provide the fine-grained signals that
would prevent fallacious content in real time. As a first step to addressing
these issues, we propose a novel token-level, reference-free hallucination
detection task and an associated annotated dataset named HaDes (HAllucination
DEtection dataSet). To create this dataset, we first perturb a large number of
text segments extracted from English language Wikipedia, and then verify these
with crowd-sourced annotations. To mitigate label imbalance during annotation,
we utilize an iterative model-in-loop strategy. We conduct comprehensive data
analyses and create multiple baseline models.

Reinforced Cross-modal Alignment for Radiology Report Generation

Downloads

Next from ACL 2022

Rethinking Offensive Text Detection as a Multi-Hop Reasoning Problem

Similar lecture

Situated Dialogue Learning through Procedural Environment Generation