Taiwan

Multi-document summarization (MDS) is a process of generating an informative and con- cise summary from multiple topic-related doc- uments. Many studies have analyzed the qual- ity of MDS dataset or models, however no work has been done from the perspective of topic preservation. In this work, we fill the gap by performing an empirical analysis on two MDS datasets and study topic preservation on generated summaries from 8 MDS mod- els. Our key findings include i) Multi-News dataset has better gold summaries compared to Multi-XScience in terms of its topic distribu- tion consistency and ii) Extractive approaches perform better than abstractive approaches in preserving topic information from source doc- uments. We hope our findings could help de- velop a summarization model that can generate topic-focused summary and also give inspira- tion to researchers in creating dataset for such challenging task.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-srw.9/)


IJCNLP-AACL 2022

An Empirical Study on Topic Preservation in Multi-Document Summarization

multi-document

topic

summarization

analysis

[![](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!

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

COLING 2022

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

workshop paper

The AACL, Asia-Pacific Chapter of the Association for Computational Linguistics, and the AFNLP, Asian Federation of Natural Language Processing, invite you to participate in the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL) and the 10th International Joint Conference on Natural Language Processing (IJCNLP).

A registration is required to access this event. Access to the event site will be granted to all registered attendees on **November 16th**. If you have not already done so, please register using the link below:
 
 https://conference.iis.sinica.edu.tw/servlet/Register?ConferenceID=411

Registration Is Required

The AACL, Asia-Pacific Chapter of the Association for Computational Linguistics, and the AFNLP, Asian Federation of Natural Language Processing, invite you to participate in the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL) and the 10th International Joint Conference on Natural Language Processing (IJCNLP). 

It has been shown that multilingual transformer models are able to predict human reading behavior when fine-tuned on small amounts of eye tracking data. As the cumulated prediction results do not provide insights into the linguistic cues that the model acquires to predict reading behavior, we conduct a deeper analysis of the predictions from the perspective of readability. We try to disentangle the three-fold relationship between human eye movements, the capability of language models to predict these eye movement patterns, and sentence-level readability measures for English. We compare a range of model configurations to multiple baselines. We show that the models exhibit difficulties with function words and that pre-training only provides limited advantages for linguistic generalization.

Patterns of Text Readability in Human and Predicted Eye Movements.

Inalienable possession differs from alienable possession in that, in the former – e.g., kinships and part-whole relations – there is an intrinsic semantic dependency between the possessor and possessum. This paper reports two studies that used acceptability-judgment tasks to investigate whether native Mandarin speakers experienced different levels of interpretational costs while resolving different types of possessive relations, i.e., inalienable possessions (kinship terms and body parts) and alienable ones, expressed within relative clauses. The results show that sentences received higher acceptability ratings when body parts were the possessum as compared to sentences with alienable possessum, indicating that the inherent semantic dependency facilitates the resolution. However, inalienable kinship terms received the lowest acceptability ratings. We argue that this was because the kinship terms, which had the [+human] feature and appeared at the beginning of the experimental sentences, tended to be interpreted as the subject in shallow processing; these features contradicted the semantic-syntactic requirements of the experimental sentences.

(In)Alienable Possession in Mandarin Relative Clauses

Evaluating the performance of Massively Multilingual Language Models (MMLMs) is difficult due to the shortage of evaluation datasets in low-resource languages. Due to computational limitations evaluating MMLMs trained on all possible pivot configurations is not feasible. This paper describes our contribution to the SumEval 2022 shared task, which handles the crucial task of Performance prediction of MMLMs. We build upon Microsoft Research's Project LITMUS and devise a method to further improve predictions. We develop various machine-learning approaches which outperform the baseline score provided by LITMUS. Our system ranked first with an RMSE score of 0.017 for the non-surprise and 0.109 for the surprise dataset.

To Train or Not to Train: Predicting the Performance of Massively Multilingual Models

The GMU System Submission for the SUMEval 2022 Shared Task

Access to mobile phones in many low- and middle-income countries has increased exponentially over the last 20 years, providing an opportunity to connect patients with healthcare interventions through mobile phones (known as mobile health). A barrier to large-scale implementation of interactive mobile health interventions is the human effort needed to manage participant messages. In this study, we explore the use of natural language processing to improve healthcare workers’ management of messages from pregnant and postpartum women in Kenya. Using multilingual, low-resource language text messages from the Mobile solutions for Women and Children’s health (Mobile WACh NEO) study, we developed models to assess urgency of incoming messages. We evaluated models using a novel approach that focuses on clinical usefulness in either triaging or prioritizing messages. Our best-performing models did not reach the threshold for clinical usefulness we set, but have the potential to improve nurse workflow and responsiveness to urgent messages.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-srw.10/)

Detecting Urgency in Multilingual Medical SMS in Kenya

The multi-modal foundation model CLIP computes representations from texts and images that achieved unprecedented performance on tasks such as zero-shot image classification. However, CLIP was pretrained on public internet data. Thus it lacks highly domain-specific knowledge.
We investigate the adaptation of CLIP-based models to the chest radiography domain using the MIMIC-CXR dataset. We show that the features of the pretrained CLIP models do not transfer to this domain. 
We adapt CLIP to the chest radiography domain using contrastive language supervision and show that this approach yields a model that outperforms supervised learning on labels on the MIMIC-CXR dataset while also generalizing to the CheXpert and RSNA Pneumonia datasets. Furthermore, we do a detailed ablation study of the batch and dataset size.
Finally, we show that language supervision allows for better explainability by using the multi-modal model to generate images from texts such that experts can inspect what the model has learned.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-srw.11/)

Language over Labels: Contrastive Language Supervision Exceeds Purely Label-Supervised Classification Performance on Chest X-Rays

A new trend in topic modeling research is to do Neural Topic Modeling by Clustering document Embeddings (NTM-CE) created with a pretrained language model. Studies have evaluated static NTM-CE models and found them performing comparably to, or even better than other topic models. An important extension of static topic modeling is making the models dynamic, allowing the study of topic evolution over time, as well as detecting emerging and disappearing topics. In this research proposal, we present two research questions to understand dynamic topic modeling with NTM-CE theoretically and practically. To answer these, we propose four phases with the aim of establishing evaluation methods for dynamic topic modeling, finding NTM-CE-specific properties, and creating a framework for dynamic NTM-CE. For evaluation, we propose to use both quantitative measurements of coherence and human evaluation supported by our recently developed tool.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-srw.12/)

Dynamic Topic Modeling by Clustering Embeddings from Pretrained Language Models: A Research Proposal

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-srw.13/)

Concreteness vs. Abstractness: A Selectional Preference Perspective

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-tutorials.2/)


Recent Advances in Pre-trained Language Models: Why Do They Work and How Do They Work

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-tutorials.6/)


Downloads

Next from IJCNLP-AACL 2022

Patterns of Text Readability in Human and Predicted Eye Movements.

Similar lecture

Analyzing the Dialect Diversity in Multi-document Summaries