Korea, Republic of

Research on Automatic Story Generation (ASG) relies heavily on human and automatic evaluation. However, there is no consensus on which human evaluation criteria to use, and no analysis of how well automatic criteria correlate with them. In this paper, we propose to re-evaluate ASG evaluation. We introduce a set of 6 orthogonal and comprehensive human criteria, carefully motivated by the social sciences literature. We also present HANNA, an annotated dataset of 1,056 stories produced by 10 different ASG systems. HANNA allows us to quantitatively evaluate the correlations of 72 automatic metrics with human criteria. Our analysis highlights the weaknesses of current metrics for ASG and allows us to formulate practical recommendations for ASG evaluation.

COLING 2022

Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation

meta-evaluation

human evaluation

story generation

automatic evaluation

transformer

# 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)

ACL 2022

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). 

technical paper

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

This paper introduces the problem of determining whether people are located in the places they mention in their tweets. In particular, we investigate the role of text and images to solve this challenging problem. We present a new corpus of tweets that contain both text and images. Our analyses show that this problem is multimodal at its core: human judgments depend on whether annotators have access to the text, the image, or both. Experimental results show that a neural architecture that combines both modalities yields better results. We also conduct an error analysis to provide insights into why and when each modality is beneficial.

Are People Located in the Places They Mention in Their Tweets? A Multimodal Approach

Data-to-Text Generation (D2T) problems can be considered as a stream of time-stamped events with a text summary being produced for each. The problem becomes more challenging when event summaries contain complex insights derived from multiple records either within an event, or across several events from the event stream. It is important to understand the different types of content present in the summary to help us better define the system requirements so that we can build better systems. In this paper, we propose a novel typology of content types, that we use to classify the contents of event summaries. Using the typology, a profile of a dataset is generated as the distribution of the aggregated content types which captures the specific characteristics of the dataset and gives a measure of the complexity present in the problem. Through extensive experiments on different D2T datasets we demonstrate that neural generative systems specifically struggle to generate contents of complex types, highlighting the need for improved D2T techniques. 


Content Type Profiling of Data-to-Text Generation Datasets

A well-formulated benchmark plays a critical role in spurring advancements in the natural language processing (NLP) field, as it allows objective and precise evaluation of diverse models. As modern language models (LMs) have become more elaborate and sophisticated, more difficult benchmarks that require linguistic knowledge and reasoning have been proposed. However, most of these benchmarks only support English, and great effort is necessary to construct benchmarks for other low-resource languages. To this end, we propose a new benchmark named Korean balanced evaluation of significant tasks (KoBEST), which consists of five Korean-language downstream tasks. Professional Korean linguists designed the tasks that require advanced Korean linguistic knowledge. Moreover, our data is purely annotated by humans and thoroughly reviewed to guarantee high data quality. We
also provide baseline models and human performance results. Our dataset is available on the Huggingface.

KoBEST: Korean Balanced Evaluation of Significant Tasks

Learning visual and textual representations in the shared space from web-scale image-text pairs improves the performance of diverse vision-and-language tasks, as well as modality-specific tasks. Many attempts in this framework have been made to connect English-only texts and images, and only a few works have been proposed to extend this framework in multilingual settings with the help of many translation pairs. In this multilingual approach, a typical setup is to use pairs of (image and English-text) and translation pairs. The major limitation of this approach is that the learning signal of aligning visual representation with under-resourced language representation is not strong, achieving a sub-optimal performance of vision-and-language tasks. In this work, we propose a simple yet effective enhancement scheme for previous multilingual multi-modal representation methods by using a limited number of pairs of images and non-English texts. In specific, our scheme fine-tunes a pre-trained multilingual model by minimizing a triple contrastive loss on triplets of image and two different language texts with the same meaning, improving the connection between images and non-English texts. Experiments confirm that our enhancement strategy achieves performance gains in image-text retrieval, zero-shot image classification, and sentence embedding tasks.

Efficient Multilingual Multi-modal Pre-training through Triple Contrastive Loss

Paraphrasing, i.e., restating the same meaning in different ways, is an important data augmentation approach for natural language processing (NLP). Zhang et al. propose to extract sentence-level paraphrases from multiple Chinese translations of the same source texts, and construct the PKU Paraphrase Bank of 0.5M sentence pairs. However, despite being the largest Chinese parabank to date, the size of PKU parabank is limited by the availability of one-to-many sentence translation data, and cannot well support the training of large Chinese paraphrasers. In this paper, we relieve the restriction with one-to-many sentence translation data, and construct ParaZh-22M, a larger Chinese parabank that is composed of 22M sentence pairs, based on one-to-one bilingual sentence translation data and machine translation (MT). In our data augmentation experiments, we show that paraphrasing based on ParaZh-22M can bring about consistent and significant improvements over several strong baselines on a wide range of Chinese NLP tasks, including a number of Chinese natural language understanding benchmarks (CLUE) and low-resource machine translation.

ParaZh-22M: a Large-Scale Chinese Parabank via Machine Translation

Successful Machine Learning based Named Entity Recognition models could fail on texts from some special domains, for instance, Chinese addresses and e-commerce titles, where requires adequate background knowledge. Such texts are also difficult for human annotators. In fact, we can obtain some potentially helpful information from correlated texts, which have some common entities, to help the text understanding. Then, one can easily reason out the correct answer by referencing correlated samples. In this paper, we suggest enhancing NER models with correlated samples. We draw correlated samples by the sparse BM25 retriever from large-scale in-domain unlabeled data. To explicitly simulate the human reasoning process, we perform a training-free entity type calibrating by majority voting. To capture correlation features in the training stage, we suggest to model correlated samples by the transformer-based multi-instance cross-encoder. Empirical results on datasets of the above two domains show the efficacy of our methods.

Domain-Specific NER via Retrieving Correlated Samples

Generating synthetic data for supervised learning from large-scale pre-trained language models has enhanced performances across several NLP tasks, especially in low-resource scenarios. In particular, many studies of data augmentation employ masked language models to replace words with other words in a sentence. However, most of them are evaluated on sentence classification tasks and cannot immediately be applied to tasks related to the sentence structure. In this paper, we propose a simple yet effective approach to generating sentences with a coordinate structure in which the boundaries of its conjuncts are explicitly specified. For a given span in a sentence, our method embeds a mask with a coordinating conjunction in two ways (“X and <mask>”, “<mask> and X”) and forces masked language models to fill the two blanks with an identical text. To achieve this, we introduce decoding methods for BERT and T5 models with the constraint that predictions for different masks are synchronized. Furthermore, we develop a training framework that effectively selects synthetic examples for the supervised coordination disambiguation task. We demonstrate that our method produces promising coordination instances that provide gains for the task in low-resource settings.

Coordination Generation via Synchronized Text-Infilling

This paper presents a language-independent approach for morphological
disambiguation which has been regarded as an extension of POS tagging, jointly
predicting complex morphological tags. In the proposed approach, all words, roots,
POS and morpheme tags are embedded into vectors, and context representations from
surface word and morphological contexts are calculated. Then the inner products
between analyses and the context’s representations are computed to perform the
disambiguation. The underlying hypothesis is that the correct morphological analysis
should be closer to the context in a vector space. Experimental results show that the
proposed approach out-performs the existing models on seven different language
datasets. Concretely, compared with the baselines of MarMot and a sophisticated
neural model (Seq2Seq), the proposed approach achieves around 6% improvement in
average accuracy for all languages while running about 6 and 33 times faster than
MarMot and Seq2Seq, respectively.

Language-Independent Approach for Morphological Disambiguation

Multi-label Text Classification (MLTC) is the task of categorizing documents into one or more topics. Considering the large volumes of data and varying domains of such tasks, fully-supervised learning requires manually fully annotated datasets which is costly and time-consuming. In this paper, we propose BERT-Flow-VAE (BFV), a Weakly-Supervised Multi-Label Text Classification (WSMLTC) model that reduces the need for full supervision. This new model: (1) produces BERT sentence embeddings and calibrates them using a flow model, (2) generates an initial topic-document matrix by averaging results of a seeded sparse topic model and a textual entailment model that only require surface name of topics and 4-6 seed words per topic, and (3) adopts a VAE framework to reconstruct the embeddings under the guidance of the topic-document matrix. Finally, (4) it uses the means produced by the encoder model in the VAE architecture as predictions for MLTC. Experimental results on 6 multi-label datasets show that BFV can substantially outperform other baseline WSMLTC models in key metrics and achieve approximately 84% performance of a fully-supervised model.

BERT-Flow-VAE: A Weakly-supervised Model for Multi-Label Text Classification

Essay exams have been attracting attention as a way of measuring the higher-order abilities of examinees, but they have two major drawbacks in that grading them is expensive and raises questions about fairness. As an approach to overcome these problems, automated essay scoring (AES) is in increasing need. Many AES models based on deep neural networks have been proposed in recent years and have achieved high accuracy, but most of these models are designed to predict only a single overall score. However, to provide detailed feedback in practical situations, we often require not only the overall score but also analytic scores corresponding to various aspects of the essay. Several neural AES models that can predict both the analytic scores and the overall score have also been proposed for this very purpose. However, conventional models are designed to have complex neural architectures for each analytic score, which makes interpreting the score prediction difficult. To improve the interpretability of the prediction while maintaining scoring accuracy, we propose a new neural model for automated analytic scoring that integrates a multidimensional item response theory model, which is a popular psychometric model.

Premium content

Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation

Downloads

Next from COLING 2022

Are People Located in the Places They Mention in Their Tweets? A Multimodal Approach

Similar lecture

Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfer