Korea, Republic of

Despite the recent success of pretrained lan-
guage models as on-the-fly knowledge sources
for various downstream tasks, they have been
shown to inadequately represent trivial com-
mon facts that vision typically captures. This
limits their application to natural language un-
derstanding tasks that require commonsense
knowledge. We seek to determine the capa-
bility of pretrained visual–linguistic models as
knowledge sources on demand. To this end,
we systematically compare language-only and
visual–linguistic models in a zero-shot com-
monsense question answering inference task.
We find that visual–linguistic models are highly
promising regarding their benefit for text-only
tasks on certain types of commonsense knowl-
edge associated with the visual world. Sur-
prisingly, this knowledge can be activated even
when no visual input is given during inference,
suggesting effective multimodal fusion during
pretraining. However, we also reveal that there
is still a huge scope for improvements towards
better cross-modal reasoning abilities and pre-
training strategies for event understanding.

COLING 2022

Are Visual-Linguistic Models Commonsense Knowledge Bases?

probing analysis

commonsense learning

vision and language

[![](https://assets.underline.io/uploads/markdown_image/1/image/81a3c0317d24f663b49b996875024d45.png)](https://aclanthology.org/volumes/2022.coling-1/)



### THE CONFERENCE WE KNOW AND WE WANT.
**COLING**, the International Conference on Computational Linguistics, is one of the premier conferences for the natural language processing and computational linguistics.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes but also in industrial research departments including tech-startups. COLING provides opportunities for all these communities to showcase their exciting discovery.

In fall of 2022, COLING will be held in Gyeongju in a hybrid format. All participants can either present at the venue site or join virtually. As more people get vaccinated, we are happy to provide safer environments for our colleagues. We believe that COLING 2022 will be one of the conferences, free from the pandemic. The hybrid format gives presenters and sponsors a valuable opportunity to promote their companies in both an online and in-person venue. For the first time in a long time, customers can interact with their sponsor's products first-hand. The online venue, too, gives sponsors the chance to network with those unable to attend the in-person session.

The hybrid format ultimately lends itself to greater exposure for our sponsors: COLING2022 will let you reach more potential partners and customers than ever before!<br><br><br>

To gain access to this event page you are required to register.<br> Find more information and pay the registration fee on event the organizer’s website **[https://coling2022.org/reg](https://coling2022.org/reg)**

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for the natural language processing and computational linguistics.

technical paper

Benchmarking Compositionality with Formal Languages

Building Joint Relationship Attention Network for Image-Text Generation

Pretrained Language Models (PLMs), though popular, have been diagnosed to encode bias against protected groups in the representations they learn, which may harm the prediction fairness of downstream models. Given that such bias is believed to be related to the amount of demographic information carried in the learned representations, this study aimed to quantify the awareness that a PLM (i.e., BERT) has regarding people’s protected attributes and augment BERT to improve prediction fairness of downstream models by inhibiting this awareness. Specifically, we developed a method to dynamically sample data to continue the pretraining of BERT and enable it to generate representations carrying minimal demographic information, which can be directly used as input to downstream models for fairer predictions. By experimenting on the task of classifying educational forum posts and measuring fairness between students of different gender or first-language backgrounds, we showed that, compared to a baseline without any additional pretraining, our method improved not only fairness (with a maximum improvement
of 52.33%) but also accuracy (with a maximum improvement of 2.53%). Our method can be generalized to any PLM and demographic attributes.

Bigger Data or Fairer Data? Augmenting BERT via Active Sampling for Educational Text Classification

Post-processing of static embedding has been shown to improve their performance on both lexical and sequence-level tasks. However, post-processing for contextualized embeddings is an under-studied problem. In this work, we question the usefulness of post-processing for contextualized embeddings obtained from different layers of pre-trained language models. More specifically, we standardize individual neuron activations using z-score, min-max normalization, and by removing top principal components using the all-but-the-top method. Additionally, we apply unit length normalization to word representations. On a diverse set of pre-trained models, we show that post-processing unwraps vital information present in the representations for both lexical tasks (such as word similarity and analogy) and sequence classification tasks. Our findings raise interesting points in relation to the research studies that use contextualized representations, and suggest z-score normalization as an essential step to consider when using them in an application.

Effect of Post-processing on Contextualized Word Representations

Few-shot Named Entity Recognition (NER) is imperative for entity tagging in limited resource domains and thus received proper attention in recent years. Existing approaches for few-shot NER are evaluated mainly under in-domain settings. In contrast, little is known about how these inherently faithful models perform in cross-domain NER using a few labeled in-domain examples. This paper proposes a two-step rationale-centric data augmentation method to improve the model's generalization ability. Results on several datasets show that our model-agnostic method significantly improves the performance of cross-domain NER tasks compared to previous state-of-the-art methods, including the counterfactual data augmentation and prompt-tuning methods. Our codes are available at https://github.com/lifan-yuan/FactMix.

FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognition

Fast screening and diagnosis are critical in COVID-19 patient treatment. In addition to the gold standard RT-PCR, radiological imaging like X-ray and CT also works as an important means in patient screening and follow-up. However, due to the excessive number of patients, writing reports becomes a heavy burden for radiologists. To reduce the workload of radiologists, we propose DeltaNet to generate medical reports automatically. Different from typical image captioning approaches that generate reports with an encoder and a decoder, DeltaNet applies a conditional generation process. In particular, given a medical image, DeltaNet employs three steps to generate a report: 1) first retrieving related medical reports, i.e., the historical reports from the same or similar patients; 2) then comparing retrieved images and current image to find the differences; 3) finally generating a new report to accommodate identified differences based on the conditional report. We evaluate DeltaNet on a COVID-19 dataset, where DeltaNet outperforms state-of-the-art approaches. Besides COVID-19, the proposed DeltaNet can be applied to other diseases as well. We validate its generalization capabilities on the public IU-Xray and MIMIC-CXR datasets for chest-related diseases.


DeltaNet: Conditional Medical Report Generation for COVID-19 Diagnosis

Several studies in the literature on the interpretation of Neural Language Models (NLM) focus on the linguistic generalization abilities of pre-trained models. However, little attention is paid to how the linguistic knowledge of the models changes during the fine-tuning steps. In this paper, we contribute to this line of research by showing to what extent a wide range of linguistic phenomena are forgotten across 50 epochs of fine-tuning, and how the preserved linguistic knowledge is correlated with the resolution of the fine-tuning task. To this end, we considered a quite understudied task where linguistic information plays the main role, i.e.\ the prediction of the evolution of written language competence of native language learners. In addition, we investigate whether it is possible to predict the fine-tuned NLM accuracy across the 50 epochs solely relying on the assessed linguistic competence. Our results are encouraging and show a high relationship between the model's linguistic competence and its ability to solve a linguistically-based downstream task.

On the Nature of BERT: Correlating Fine-Tuning and Linguistic Competence

Lifelong language learning aims to stream learning NLP tasks while retaining knowledge of previous tasks. Previous works based on the language model and following data-free constraint approaches have explored formatting all data as "begin token (B) + context (C) + question (Q) + answer (A)" for different tasks. However, they still suffer from catastrophic forgetting and are exacerbated when the previous task’s pseudo data is insufficient for the following reasons: (1) The model has difficulty generating task-corresponding pseudo data, and (2) A is prone to error when A and C are separated by Q because the information of the C is diminished before generating A. Therefore, we propose the Ask Question First and Replay Question (AQF-RQ), including a novel data format "BQCA" and a new training task to train pseudo questions of previous tasks. Experimental results demonstrate that AQF-RQ makes it easier for the model to generate more pseudo data that match corresponding tasks, and is more robust to both sufficient and insufficient pseudo-data when the task boundary is both clear and unclear. AQF-RQ can achieve only 0.36% lower performance than multi-task learning

Ask Question First for Enhancing Lifelong Language Learning

Knowledge-grounded dialog systems need to incorporate smooth transitions among knowledge selected for generating responses, to ensure that dialog flows naturally. For document-grounded dialog systems, the inter- and intra- document knowledge relations can be used to model such conversational flows. We develop a novel Multi-Document Co-Referential Graph (Coref-MDG) to effectively capture the inter-document relationships based on common- sense and similarity and the intra-document co-referential structures of knowledge segments within the grounding documents. We propose CorefDiffs, a Co-referential and Differential flow management method, to linearize the static Coref-MDG into conversational sequence logic. CorefDiffs performs knowledge selection by accounting for contextual graph structures and the knowledge difference sequences. CorefDiffs significantly outperforms the state-of-the-art by 9.5%, 7.4%, and 8.2% on three public benchmarks. This demonstrates that the effective modeling of co-reference and knowledge difference for dialog flows are critical for transitions in document-grounded conversation1.

CorefDiffs: Co-referential and Differential Knowledge Flow in Document Grounded Conversations

Framing is a communication strategy to bias discussion by selecting and emphasizing. Frame detection aims to automatically analyze framing strategy. Previous works on frame detection mainly focus on a single scenario or issue, ignoring the special characteristics of frame detection that new events emerge continuously and policy agenda changes dynamically. To better deal with various context and frame typologies across different issues, we propose a two-stage adaptation framework. In the framing domain adaptation from pre-training stage, we design two tasks based on pivots and prompts to learn a transferable encoder, verbalizer, and prompts. In the downstream scenario generalization stage, the transferable components are applied to new issues and label sets. Experiment results demonstrate the effectiveness of our framework in different scenarios. Also, it shows superiority both in full-resource and low-resource conditions.


Premium content

Are Visual-Linguistic Models Commonsense Knowledge Bases?

Downloads

Next from COLING 2022

Benchmarking Compositionality with Formal Languages

Similar lecture

Visual Recipe Flow: A Dataset for Learning Visual State Changes of Objects with Recipe Flows