Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

An Empirical Study on Cross-X Transfer for Legal Judgment Prediction (2022.aacl-main)

Challenge:	Input Marginalization (IM) is a method that takes the prediction difference between before-and-after an input feature (here, a token) is removed as its attribution.
Approach:	They propose to use a BERT-based method to replace a token with a feature to give more plausible counterfactuals.
Outcome:	The proposed method is effective, but the Deletion-BERT metric is biased towards IM, and the results are not convincing.

Copied to clipboard

Joel Niklaus, Matthias Stürmer, Ilias Chalkidis

CNN for Modeling Sanskrit Originated Bengali and Hindi Language (2022.aacl-main)

Challenge:	Cross-lingual transfer learning is understudied in legal NLP but not in legal Judgment Prediction (LJP).
Approach:	They explore cross-lingual transfer learning techniques on legal JP using a trilingual Swiss-Judgment-Prediction dataset and adapter-based fine-tuning.
Outcome:	The proposed methods improve the model’s performance by augmenting the training dataset with machine-translated versions of the original documents, using a 3 larger training corpus.

Copied to clipboard

Chowdhury Rahman, MD. Hasibur Rahman, Mohammad Rafsan, Mohammed Eunus Ali, Samiha Zakir, Rafsanjani Muhammod

Leveraging Key Information Modeling to Improve Less-Data Constrained News Headline Generation via Duality Fine-Tuning (2022.aacl-main)

Challenge:	Existing studies on the effectiveness of different architectures for modeling low resource languages are limited.
Approach:	They propose a trainable memory efficient CNN architecture for Bengali and Hindi . they propose two learnable convolutional sub-models that are end to end trainable .
Outcome:	The proposed model outperforms pretrained BERT models on Bengali and Hindi with 16X less parameters and achieves much better performance than SOTA LSTMs on multiple real-world datasets.

Copied to clipboard

Zhuoxuan Jiang, Lingfeng Qiao, Di Yin, Shanshan Feng, Bo Ren

Text Generation

Challenge:	Recent language generative models are mostly trained on large-scale datasets, while in some real scenarios, the training datasets are often expensive and would be small-scale.
Approach:	They propose a novel duality fine-tuning method to capture more information from limited data and build connections between tasks.
Outcome:	The proposed method can capture more information from limited data, build connections between separate tasks, and is suitable for less-data constrained generation tasks.

Systematic Evaluation of Predictive Fairness (2022.aacl-main)

Copied to clipboard

Xudong Han, Aili Shen, Trevor Cohn, Timothy Baldwin, Lea Frermann

Graph-augmented Learning to Rank for Querying Large-scale Knowledge Graph (2022.aacl-main)

Challenge:	Several methods have been proposed to mitigate bias in training on biased datasets.
Approach:	They propose to examine the effect of target class imbalance and stereotyping on model performance by analyzing binary classification, profession prediction and regression tasks.
Outcome:	The proposed methods show that data conditions have a strong influence on relative model performance.

Copied to clipboard

Hanning Gao, Lingfei Wu, Po Hu, Zhihua Wei, Fangli Xu, Bo Long

An Embarrassingly Simple Approach for Intellectual Property Rights Protection on Recurrent Neural Networks (2022.aacl-main)

Challenge:	Existing knowledge graph question answering methods only search for the answer in a large knowledge graph.
Approach:	They propose to partition retrieved knowledge subgraphs into smaller sub-KSGs and then use a graph-augmented learning to rank method to select the top-ranked sub-kSGs.
Outcome:	The proposed method can capture global interactions in question and subgraphs and local interactions on the full KSG and top-ranked sub-KSGs respectively.

Copied to clipboard

Zhi Qin Tan, Hao Shan Wong, Chee Seng Chan

WAX: A New Dataset for Word Association eXplanations (2022.aacl-main)

Challenge:	Existing protection schemes for deep neural network models protect intellectual property rights from being abused, stolen and plagiarized.
Approach:	They propose a practical approach for the IPR protection on recurrent neural networks without all the bells and whistles of existing IPR solutions.
Outcome:	The proposed approach is robust and effective against ambiguity and removal attacks on different RNN variants.

Copied to clipboard

Chunhua Liu, Trevor Cohn, Simon De Deyne, Lea Frermann

Explainability & Interpretability in NLP

Challenge:	Word associations are among the most common paradigms to study the human mental lexicon.
Approach:	They present a large dataset of word associations with explanations and relation labels . they show that current language models struggle to capture the diversity of human associations .
Outcome:	The proposed model fails to capture the diversity of human associations, the authors show . they show that the model is a rich benchmark for commonsense modeling and generation.

Missing Modality meets Meta Sampling (M3S): An Efficient Universal Approach for Multimodal Sentiment Analysis with Missing Modality (2022.aacl-main)

Copied to clipboard

Haozhe Chi, Minghua Yang, Junhao Zhu, Guanhong Wang, Gaoang Wang

Sentiment Analysis

Challenge:	Existing methods to address missing modalities often assume a particular modality is completely missing due to recording or transmission error.
Approach:	They propose a missing modality-based meta-sampling approach for multimodal sentiment analysis with missing modalities . they conduct experiments on IEMOCAP, SIMS and CMU-MOSI datasets .
Outcome:	The proposed method significantly improves on existing models with a mixture of missing modalities.

SPARQL-to-Text Question Generation for Knowledge-Based Conversational Applications (2022.aacl-main)

Copied to clipboard

Gwénolé Lecorvé, Morgan Veyret, Quentin Brabant, Lina M. Rojas Barahona

S+PAGE: A Speaker and Position-Aware Graph Neural Network Model for Emotion Recognition in Conversation (2022.aacl-main)

Challenge:	a paper focuses on the generation of natural language questions based on SPARQL queries . knowledge-based approaches have become popular in the field of question answering and dialogue .
Approach:	This paper focuses on the generation of natural language questions based on SPARQL queries . it uses 4 knowledge-based QA corpora homogenized for the task and a new challenge set is introduced .
Outcome:	The proposed task is based on the generation of questions in a conversational context.

Copied to clipboard

Chen Liang, Jing Xu, Yangkun Lin, Chong Yang, Yongliang Wang

Grammatical Error Correction Systems for Automated Assessment: Are They Susceptible to Universal Adversarial Attacks? (2022.aacl-main)

Challenge:	Emotion recognition in conversation (ERC) is a task arousing increasing interest in many fields.
Approach:	They propose a novel GNN-based ERC model that captures speaker and position information.
Outcome:	The proposed model captures speaker and position-aware conversation structure information.

Copied to clipboard

Vyas Raina, Yiting Lu, Mark Gales

Robustness in NLP

Challenge:	With advances in deep learning, GEC systems are susceptible to adversarial attacks, in which a small change at the input can cause large undesired changes at the output.
Approach:	They propose to use a concatenative universal attack to deceive the system into not correcting grammatical errors to create the perception of higher language ability.
Outcome:	The proposed attack can deceive the system into not correcting (concealing) grammatical errors to create the perception of higher language ability.

This Patient Looks Like That Patient: Prototypical Networks for Interpretable Diagnosis Prediction from Clinical Text (2022.aacl-main)

Copied to clipboard

Betty van Aken, Jens-Michalis Papaioannou, Marcel Naik, Georgios Eleftheriadis, Wolfgang Nejdl, Felix Gers, Alexander Loeser

Explainability & Interpretability in NLP

Challenge:	a novel method for diagnosis prediction from clinical text is needed in clinical practice . prototypical part networks and label-wise attention are used to make models interpretable and helpful .
Approach:	They propose a deep neural model that makes predictions based on parts of the text that are similar to prototypical patients.
Outcome:	The proposed method outperforms baseline models on two clinical datasets and provides valuable explanations for clinical decision support.

Cross-lingual Similarity of Multilingual Representations Revisited (2022.aacl-main)

Copied to clipboard

Maksym Del, Mark Fishel

Arabic Dialect Identification with a Few Labeled Examples Using Generative Adversarial Networks (2022.aacl-main)

Challenge:	Similarity indexes like CKA and CCA are not suitable for cross-lingual learning analysis.
Approach:	They propose an alternative that is exempt from the difficulties of CKA/CCA and is good specifically in a cross-lingual context.
Outcome:	The proposed method is exempt from the difficulties of CKA/CCA and is good specifically in a cross-lingual context.

Copied to clipboard

Mahmoud Yusuf, Marwan Torki, Nagwa El-Makky

Robustness in NLP

Challenge:	Experimental results show that transformer-based models can handle Dialect Arabic (DA) classification tasks with a large corpus of labeled examples.
Approach:	They extend transformer-based models with unlabeled data in a generative adversarial setting using semi-supervised Generative Adversarial Networks (SS-GAN) they show that the model can produce high-quality embeddings for the Dialect Arabic examples and generalize for the downstream classification task given few labeled examples.
Outcome:	The proposed model outperforms models with unlabeled data in a generative adversarial setting with unlabelled examples and faster convergence when only a few labeled examples are available.

Semantic Shift Stability: Efficient Way to Detect Performance Degradation of Word Embeddings and Pre-trained Language Models (2022.aacl-main)

Copied to clipboard

Shotaro Ishihara, Hiromu Takahashi, Hono Shirai

Neural Text Sanitization with Explicit Measures of Privacy Risk (2022.aacl-main)

Challenge:	Existing methods to detect time-series performance degradation of word embeddings and pre-trained language models are not efficient.
Approach:	They propose a way to detect time-series performance degradation by calculating the degree of semantic shift.
Outcome:	The proposed method detects time-series performance degradation in Japanese and English datasets.

Copied to clipboard

Anthi Papadopoulou, Yunhao Yu, Pierre Lison, Lilja Øvrelid

AGRank: Augmented Graph-based Unsupervised Keyphrase Extraction (2022.aacl-main)

Challenge:	Personal data, also known as Personally Identifiable Information (PII), often abound in text documents.
Approach:	They propose a method for text sanitization that uses a neural entity recognizer to detect and classify potential personal identifiers and a classifier trained on labelled data to determine which entities to mask .
Outcome:	The proposed approach masks all personal identifiers and thereby conceals the identity of the individuals mentioned in the document.

Copied to clipboard

Haoran Ding, Xiao Luo

Towards Unified Representations of Knowledge Graph and Expert Rules for Machine Learning and Reasoning (2022.aacl-main)

Challenge:	Unsupervised keyphrase extraction (UKE) is highly anticipated because no labeled data is needed to train a model.
Approach:	They propose an augmented graph-based unsupervised model to identify keyphrases from a document by integrating graph and deep learning methods.
Outcome:	The proposed model is effective and robust for long and short documents.

Copied to clipboard

Zhepei Wei, Yue Wang, Jinnan Li, Zhining Liu, Erxin Yu, Yuan Tian, Xin Wang, Yi Chang

Who did what to Whom? Language models and humans respond diversely to features affecting argument hierarchy construction (2022.aacl-main)

Challenge:	Empirical study shows superiority of proposed method over time-tested knowledge-driven and data-driven methods.
Approach:	They propose a cognitive knowledge graph that unifies expert rules and relational facts as the substrate of machine learning and reasoning models.
Outcome:	Empirical results show the proposed method superior to time-tested methods . the proposed model can perform both learning and reasoning with labeled data .

Copied to clipboard

Xiaonan Xu, Haoshuo Chen

CrowdChecked: Detecting Previously Fact-Checked Claims in Social Media (2022.aacl-main)

Challenge:	Pre-trained transformer-based language models have achieved state-of-the-art performance in many areas of NLP.
Approach:	They propose to construct argument hierarchy similar to humans' constructs of telicity, agency, and individuation . authors propose to use a Chinese structure to analyze human and transformer-based models' preference for telic context and atelic feature .
Outcome:	The proposed model and humans respond to non-)agentive features in telic context and atelic feature very similarly.

Copied to clipboard

Momchil Hardalov, Anton Chernyavskiy, Ivan Koychev, Dmitry Ilvovsky, Preslav Nakov

Hate Speech and Offensive Language Detection in Bengali (2022.aacl-main)

Challenge:	Existing systems to automate fact-checking lack credibility in the eyes of the users.
Approach:	They propose to perform automatic fact-checking by verifying whether an input claim has been fact- checked by professional fact- checkers and to return back an article that explains their decision.
Outcome:	The proposed method improves on the CLEF’21 CheckThat! test set by two points absolute.

Copied to clipboard

Mithun Das, Somnath Banerjee, Punyajoy Saha, Animesh Mukherjee

Information Retrieval

Challenge:	Existing research on hate speech detection in English does not cover low-resource languages like Bengali.
Approach:	They develop an annotated dataset of 10K Bengali posts consisting of 5K actual and 5K Romanized Bengali tweets.
Outcome:	The proposed model outperforms other models on training actual and romanized datasets by interpreting the semantic expressions better.

Learning Interpretable Latent Dialogue Actions With Less Supervision (2022.aacl-main)

Copied to clipboard

Vojtěch Hudeček, Ondřej Dušek

Named Entity Recognition in Twitter: A Dataset and Analysis on Short-Term Temporal Shifts (2022.aacl-main)

Challenge:	supervised neural dialogue modeling requires a significant amount of work to obtain turn-level labels, usually with dialogue state annotation.
Approach:	They propose a novel architecture for explainable modeling of task-oriented dialogues with discrete latent variables to represent dialogue actions.
Outcome:	The proposed model outperforms previous approaches with less supervision in terms of perplexity and BLEU on three datasets.

Copied to clipboard

Asahi Ushio, Francesco Barbieri, Vitor Sousa, Leonardo Neves, Jose Camacho-Collados

PInKS: Preconditioned Commonsense Inference with Minimal Supervision (2022.aacl-main)

Challenge:	Named Entity Recognition (NER) is a longstanding NLP task that consists of identifying an entity in a sentence or document.
Approach:	They construct a dataset of seven entity types annotated over 11,382 tweets . they provide a set of language model baselines and analyze the performance of the model .
Outcome:	The proposed dataset contains seven entity types annotated over 11,382 tweets . the authors focus on short-term degradation of NER models over time and strategies to fine-tune a language model over different periods .

Copied to clipboard

Ehsan Qasemi, Piyush Khanna, Qiang Ning, Muhao Chen

Reasoning

Challenge:	Existing models for reasoning with preconditions lack data on the problem and lack of support for such reasoning.
Approach:	They propose to improve the model for reasoning with preconditions through minimum supervision by PAC-Bayesian informativeness analysis and precision measures.
Outcome:	The proposed model improves on benchmarks focused on reasoning with the preconditions of commonsense knowledge (up to 40% Macro-F1 scores) it also improves inferences on PAC-Bayesian informativeness analysis, precision measures, and ablation studies.

Cross-Lingual Open-Domain Question Answering with Answer Sentence Generation (2022.aacl-main)

Copied to clipboard

Benjamin Muller, Luca Soldaini, Rik Koncel-Kedziorski, Eric Lind, Alessandro Moschitti

Discourse Parsing Enhanced by Discourse Dependence Perception (2022.aacl-main)

Challenge:	Open-Domain Generative Question Answering has achieved impressive performance in English . combining document-level retrieval with answer generation can generate complete sentences .
Approach:	They propose an open-domain approach that combines document retrieval with answer generation to generate complete sentences in English . they propose a cross-lingual generative model that exploits passages written in multiple languages .
Outcome:	The proposed model outperforms answer sentence selection baselines for all 5 languages and monolingual pipelines for three out of five languages.

Copied to clipboard

Yuqing Xing, Longyin Zhang, Fang Kong, Guodong Zhou

Prediction of People’s Emotional Response towards Multi-modal News (2022.aacl-main)

Challenge:	Top-down neural models still suffer from the top-down error propagation issue . previous studies gradually switch from feature-based machine learning methods to deep neural models .
Approach:	They propose a top-down framework that learns from discourse dependency and constituency parsing through one shared encoder and two independent decoders.
Outcome:	The proposed framework learns from discourse dependency and constituency parsing through one shared encoder and two independent decoders on a Chinese discourse corpus.

Copied to clipboard

Ge Gao, Sejin Paik, Carley Reardon, Yanling Zhao, Lei Guo, Prakash Ishwar, Margrit Betke, Derry Tanti Wijaya

AugCSE: Contrastive Sentence Embedding with Diverse Augmentations (2022.aacl-main)

Challenge:	BU-NEmo dataset extends from 320 to 1,297 news headline and lead image pairings and collects 38,910 annotations in a crowdsourcing experiment.
Approach:	They extend the U.S. gun violence news-to-emotions dataset from 320 to 1,297 news headline and lead image pairings and collect annotations in a crowdsourcing experiment.
Outcome:	The proposed models outperform baseline models on the NEmo+ dataset by large margins across several metrics.

Copied to clipboard

Zilu Tang, Muhammed Yusuf Kocyigit, Derry Tanti Wijaya

Seamlessly Integrating Factual Information and Social Content with Persuasive Dialogue (2022.aacl-main)

Challenge:	Similar work has shown that a single augmentation can be used to learn a robust generalpurpose representation with contrastive learning.
Approach:	They propose a unified framework to utilize diverse sets of data augmentations to achieve a better, general-purpose sentence embedding model.
Outcome:	The proposed framework achieves state-of-the-art results on downstream transfer tasks and performs competitively on semantic textual similarity tasks, using only unsupervised data.

Copied to clipboard

Maximillian Chen, Weiyan Shi, Feifan Yan, Ryan Hou, Jingwen Zhang, Saurav Sahay, Zhou Yu

Dual-Encoder Transformers with Cross-modal Alignment for Multimodal Aspect-based Sentiment Analysis (2022.aacl-main)

Challenge:	Persuasive dialogue systems are designed for chatbots to communicate with and influence users with specific goals.
Approach:	They propose a modular dialogue system framework that integrates factual information and social content into persuasive dialogues.
Outcome:	The proposed framework is generalizable to any dialogue tasks that have mixed social and task contents.

Copied to clipboard

Zhewen Yu, Jin Wang, Liang-Chih Yu, Xuejie Zhang

Sentiment Analysis

Challenge:	Multimodal aspect-based sentiment analysis (MABSA) aims to extract aspect terms from text and image pairs, and then analyze their corresponding sentiment.
Approach:	They propose a dual-encoder transformer with cross-modal alignment to extract aspect terms from text and image pairs and then analyze their corresponding sentiments.
Outcome:	The proposed approach outperforms existing methods on two benchmarks.

AVAST: Attentive Variational State Tracker in a Reinforced Navigator (2022.aacl-main)

Copied to clipboard

Je-Wei Jang, Mahdin Rohmatillah, Jen-Tzung Chien

Phylogeny-Inspired Adaptation of Multilingual Models to New Languages (2022.aacl-main)

Challenge:	Recent advances in reinforcement learning have been proposed to deal with robotic navigation problems, especially vision-and-language navigation task.
Approach:	They propose a method to approximate belief state distribution for the construction of a reinforced navigator by using a variational approach to approximate the unseen environment.
Outcome:	The proposed method improves generalization to the unseen environment which is barely achieved by traditional deterministic state tracker.

Copied to clipboard

Fahim Faisal, Antonios Anastasopoulos

Multilinguality

Challenge:	Large pretrained multilingual models have delivered promising results due to cross-lingual learning capabilities on a variety of language tasks.
Approach:	They propose to use language phylogenetic information to improve cross-lingual transfer by leveraging closely related languages in a structured, linguistically-informed manner.
Outcome:	The proposed model significantly improves on the baseline model on languages unseen during training.

Transferring Knowledge via Neighborhood-Aware Optimal Transport for Low-Resource Hate Speech Detection (2022.aacl-main)

Copied to clipboard

Tulika Bose, Irina Illina, Dominique Fohr

Bag-of-Vectors Autoencoders for Unsupervised Conditional Text Generation (2022.aacl-main)

Challenge:	Existing approaches to detect hate speech are expensive and time-consuming . a new approach allows for flexible learning of neighborhood information .
Approach:	They propose a method that allows flexible modeling of neighbors retrieved from a resource-rich corpus to learn the amount of transfer.
Outcome:	The proposed training strategy improves on low-resource hate speech corpora over baselines.

Copied to clipboard

Florian Mai, James Henderson

RecInDial: A Unified Framework for Conversational Recommendation with Pretrained Language Models (2022.aacl-main)

Challenge:	Existing methods to learn mappings in the embedding space of text autoencoders are limited to a single-vector embeddment, which limits how much information can be retained.
Approach:	They propose a method to learn mappings in the embedding space of an autoencoder by extending it to Bag-of-Vectors Autoencodeurs (BoV-AEs) this allows to encode and reconstruct much longer texts than standard autoencodings .
Outcome:	The proposed method performs better than a standard autoencoder on unsupervised sentiment transfer.

Copied to clipboard

Lingzhi Wang, Huang Hu, Lei Sha, Can Xu, Daxin Jiang, Kam-Fai Wong

Dialogue Systems & Conversational Agents

Challenge:	Existing generative methods to recommend items are shallowly integrated into the model training and have poor chit-chat ability.
Approach:	They propose a framework that integrates recommendation into the dialog generation by introducing a vocabulary pointer.
Outcome:	The proposed framework outperforms the state-of-the-art models on a benchmark dataset.

SummVD : An efficient approach for unsupervised topic-based text summarization (2022.aacl-main)

Copied to clipboard

Gabriel Shenouda, Aurélien Bossard, Oussama Ayoub, Christophe Rodrigues

Director: Generator-Classifiers For Supervised Language Modeling (2022.aacl-main)

Challenge:	SummVD is an unsupervised extractive summarization method that uses word clustering to reduce word embeddings.
Approach:	They propose a method for automatic unsupervised extractive summarization using word clustering and singular value decomposition.
Outcome:	The proposed method outperforms other extractive methods using several corpora of different nature.

Copied to clipboard

Kushal Arora, Kurt Shuster, Sainbayar Sukhbaatar, Jason Weston

VLStereoSet: A Study of Stereotypical Bias in Pre-trained Vision-Language Models (2022.aacl-main)

Challenge:	Current language models achieve low perplexity but their resulting generations still suffer from toxic responses, repetitiveness, and contradictions.
Approach:	They propose a new language model architecture that uses a language modeling and a classification head for each output token.
Outcome:	The proposed model outperforms existing model guiding approaches in terms of accuracy and efficiency.

Copied to clipboard

Kankan Zhou, Eason Lai, Jing Jiang

Dynamic Context Extraction for Citation Classification (2022.aacl-main)

Challenge:	Existing studies on pre-trained vision-language models have focused on measuring biases and stereotypes in a single modality.
Approach:	They extend a recently released stereotypical bias dataset into a vision-language probing dataset called VLStereoSet to measure stereotypical biased vision-linguistic models.
Outcome:	The proposed probing task measures stereotypical bias in vision-language models and its intra-modal and inter-modal biases.

Copied to clipboard

Suchetha Nambanoor Kunnath, David Pride, Petr Knoth

Affective Retrofitted Word Embeddings (2022.aacl-main)

Challenge:	Prior studies have focused on the application of fixed-size contiguous citation contexts or manually curated citation contextual contexts.
Approach:	They propose an automated unsupervised approach for the selection of a dynamic-size and potentially non-contiguous citation context based on transformer-based document representations and embedding similarities.
Outcome:	The proposed model improves on the domain-specific and multi-disciplinary datasets, irrespective of the dataset's domain.

Copied to clipboard

Sapan Shah, Sreedhar Reddy, Pushpak Bhattacharyya

Is Encoder-Decoder Redundant for Neural Machine Translation? (2022.aacl-main)

Challenge:	Word embeddings do not capture affective dimensions of valence, arousal, and dominance . valency, valance, and adolescence are present in words, but are not represented in text .
Approach:	They propose a method for updating word embeddings for affective meaning . they use a non-linear transformation function that maps pre-trained embedders to an affective vector space .
Outcome:	The proposed method improves inter-cluster and intra-c cluster distances for emotion-bearing words.

Copied to clipboard

Yingbo Gao, Christian Herold, Zijian Yang, Hermann Ney

SAPGraph: Structure-aware Extractive Summarization for Scientific Papers with Heterogeneous Graph (2022.aacl-main)

Challenge:	Encoder-decoder architecture is widely adopted for sequence-to-sequence modeling tasks.
Approach:	They propose to combine bilingual and multilingual translations to train a language model to do translation.
Outcome:	The proposed approach performs on par with the baseline encoder-decoder Transformer . the proposed approach is compared with the translation model in the target language .

Copied to clipboard

Siya Qi, Lei Li, Yiyang Li, Jin Jiang, Dingxin Hu, Yuze Li, Yingqi Zhu, Yanquan Zhou, Marina Litvak, Natalia Vanetik

Toward Implicit Reference in Dialog: A Survey of Methods and Data (2022.aacl-main)

Challenge:	Abstractive and extractive methods are used to condense long text into concise summaries while retaining essential information.
Approach:	They propose to use paper structure to extract paper summaries from long text . they provide a large-scale dataset of COVID-19-related papers .
Outcome:	The proposed framework generates more comprehensive and valuable summaries compared to previous work on COVID-19-related papers.

Copied to clipboard

Lindsey Vanderlyn, Talita Anthonio, Daniel Ortega, Michael Roth, Ngoc Thang Vu

A Decade of Knowledge Graphs in Natural Language Processing: A Survey (2022.aacl-main)

Challenge:	In natural language, speakers often leave out information that is understood by the other party through the shared context.
Approach:	They propose to use omitted entities as implicit references in dialogs to improve language processing.
Outcome:	The proposed method is based on a set of experiments which show that the proposed method has a high level of accuracy and is a success.

Copied to clipboard

Phillip Schneider, Tim Schopf, Juraj Vladika, Mikhail Galkin, Elena Simperl, Florian Matthes

Structured Data in NLP

Challenge:	Knowledge graphs (KGs) are a representation of semantic relations between entities . despite their popularity, there is still no general understanding of what exactly a KG is or for what tasks it is applicable.
Approach:	They analyze 507 papers on knowledge graphs in natural language processing (NLP) they provide a taxonomy of tasks and review the maturity of individual research streams .
Outcome:	The findings summarize the literature and highlight directions for future work.

Multimodal Generation of Radiology Reports using Knowledge-Grounded Extraction of Entities and Relations (2022.aacl-main)

Copied to clipboard

Francesco Dalla Serra, William Clackett, Hamish MacKinnon, Chaoyang Wang, Fani Deligianni, Jeff Dalton, Alison Q. O’Neil

SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features (2022.aacl-main)

Challenge:	Existing approaches to generate text radiology reports are prone to errors and poor clinical accuracy.
Approach:	They propose a two-step pipeline that subdivides the problem into factual triple extraction followed by free-text report generation.
Outcome:	The proposed pipeline shows that the generated reports exhibit realistic style but lack clinical accuracy.

Copied to clipboard

Juri Opitz, Anette Frank

The Lifecycle of “Facts”: A Survey of Social Bias in Knowledge Graphs (2022.aacl-main)

Challenge:	Abstract Meaning Representation (S3BERT) embeddings are composed of explainable sub-embeddings that emphasize various sentence meaning features.
Approach:	They propose to induce Semantically Structured Sentence BERT embeddings (S3BERT) that emphasize various sentence meaning features.
Outcome:	The proposed model shows high correlation to human similarity ratings, but lacks interpretability.

Copied to clipboard

Angelie Kraft, Ricardo Usbeck

Knowledge Representation

Challenge:	Knowledge graphs are used in a variety of downstream tasks and in hybrid AI systems.
Approach:	They propose to examine the lifecycle of knowledge graphs with respect to bias influences.
Outcome:	The proposed models are based on the lifecycle of knowledge graphs and their embedded versions . they show that the KGs manifest biases and propagate harmful prejudices .

Food Knowledge Representation Learning with Adversarial Substitution (2022.aacl-main)

Copied to clipboard

Diya Li, Mohammed J Zaki

Construction Repetition Reduces Information Rate in Dialogue (2022.aacl-main)

Challenge:	Knowledge graph embedding (KGE) has been well-studied in general domains, but has not been examined for food computing.
Approach:	They propose to use a pre-trained language model to encode entities and relations, emphasizing contextual information in food KGs.
Outcome:	The proposed method is able to generate high quality substitutions over a food knowledge graph and provide generalized substitutions to meet different user needs.

Copied to clipboard

Mario Giulianelli, Arabella Sinclair, Raquel Fernández

Dialogue Systems & Conversational Agents

Challenge:	We observe that construction usage lowers the information content of utterances.
Approach:	They propose to use construction repetition to mitigate information rate in English open-domain spoken dialogues.
Outcome:	The proposed method lowers the information content of utterances, while increasing the frequency and density of repetition.

Analogy-Guided Evolutionary Pretraining of Binary Word Embeddings (2022.aacl-main)

Copied to clipboard

R. Alexander Knipper, Md. Mahadi Hassan, Mehdi Sadi, Shubhra Kanti Karmaker Santu

Contrastive Video-Language Learning with Fine-grained Frame Sampling (2022.aacl-main)

Challenge:	Existing binary word embeddings are derived from pretrained real-valued embeddables through different simple transformations, which often break the semantic consistency and the “arithmetic” properties of the embedded words.
Approach:	They propose a genetic algorithm to learn binary word embeddings from scratch by preserving the semantic relationships between words and the arithmetic properties of the embeddables themselves.
Outcome:	Evaluating 16, 32, and 64-bit word embeddings on Mikolov’s word analogy task shows that 95% of the time, the best fit is ranked in the top 5 most similar words in terms of cosine similarity.

Copied to clipboard

Zixu Wang, Yujie Zhong, Yishu Miao, Lin Ma, Lucia Specia

Enhancing Tabular Reasoning with Pattern Exploiting Training (2022.aacl-main)

Challenge:	despite recent progress in video and language representation learning, the weak or sparse correspondence between the two modalities remains a bottleneck.
Approach:	They propose a fine-grained contrastive objective for video frame sampling to improve cross-modal correspondence.
Outcome:	The proposed approach achieves state-of-the-art performance on YouCookII with long videos.

Copied to clipboard

Abhilash Shankarampeta, Vivek Gupta, Shuo Zhang

Re-contextualizing Fairness in NLP: The Case of India (2022.aacl-main)

Challenge:	Existing methods based on pre-trained language models have shown superior performance over tabular tasks despite showing inherent problems such as not using the right evidence and inconsistent predictions across inputs.
Approach:	They utilize Pattern-Exploiting Training (PET) on pre-trained language models to strengthen tabular reasoning models’ pre-existing knowledge and reasoning abilities.
Outcome:	The proposed model exhibits superior understanding of knowledge facts and tabular reasoning compared to baseline models.

Copied to clipboard

Shaily Bhatt, Sunipa Dev, Partha Talukdar, Shachi Dave, Vinodkumar Prabhakaran

Low-Resource Multilingual and Zero-Shot Multispeaker TTS (2022.aacl-main)

Challenge:	Recent research has revealed undesirable biases in NLP data and models . however, these efforts focus of social disparities in the West and are not directly portable to other geo-cultural contexts.
Approach:	They propose a framework to re-contextualize NLP fairness research for the Indian context . they build resources for fairness evaluation in the Indian and delve deeper into social stereotypes for Region and Religion .
Outcome:	The proposed framework can be generalized to other geo-cultural contexts.

Copied to clipboard

Florian Lux, Julia Koch, Ngoc Thang Vu

Unsupervised Domain Adaptation for Sparse Retrieval by Filling Vocabulary and Word Frequency Gaps (2022.aacl-main)

Challenge:	Currently, the amount of data needed for TTS is limited to the vast majority of the spoken languages.
Approach:	They propose to use language agnostic meta learning procedure to learn speaking a new language with just 5 minutes of training data while retaining the ability to infer the voice of even unseen speakers.
Outcome:	The proposed approach is able to learn speaking a new language using just 5 minutes of training data while retaining the ability to infer the voice of even unseen speakers in the newly learned language.

Copied to clipboard

Hiroki Iida, Naoaki Okazaki

KESA: A Knowledge Enhanced Approach To Sentiment Analysis (2022.aacl-main)

Challenge:	IR models with a pretrained language model outperform lexical approaches like BM25 for vocabulary mismatch.
Approach:	They propose an unsupervised domain adaptation method by filling vocabulary gaps by expanding queries and documents through an MLM.
Outcome:	The proposed method outperforms the current state-of-the-art domain adaptation method on datasets with a large vocabulary gap from a source domain.

Copied to clipboard

Qinghua Zhao, Shuai Ma, Shuo Ren

Cross-lingual Few-Shot Learning on Unseen Languages (2022.aacl-main)

Challenge:	Recent work on injecting sentiment knowledge into pre-trained language models, but it is difficult to integrate external knowledge into PLMs.
Approach:	They propose two sentiment-aware auxiliary tasks to integrate sentiment knowledge into the objective of the downstream task.
Outcome:	The proposed tasks outperform baselines and complement existing sentiment-enhanced models.

Copied to clipboard

Genta Winata, Shijie Wu, Mayank Kulkarni, Thamar Solorio, Daniel Preotiuc-Pietro

Low-Resource NLP

Challenge:	Large pre-trained language models have demonstrated the ability to obtain good performance on downstream tasks with limited examples in resource-rich languages.
Approach:	They propose to use a downstream sentiment analysis task to analyze the effectiveness of several few-shot learning strategies across 12 languages, including 8 unseen languages, to compare results.
Outcome:	The proposed model, XLM-R, gives the best performance on a task with few examples in resource-rich languages.

Domain-aware Self-supervised Pre-training for Label-Efficient Meme Analysis (2022.aacl-main)

Copied to clipboard

Shivam Sharma, Mohd Khizir Siddiqui, Md. Shad Akhtar, Tanmoy Chakraborty

A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning (2022.aacl-main)

Challenge:	Existing self-supervised learning strategies focus on uni-modal applications . a recent study shows that multimodality is a major challenge for multi-modal systems .
Approach:	They propose two self-supervised pre-training methods that employ off-the-shelf multi-modal hate-speech data . they also incorporate multiple specialized pretext tasks to cater to complex multi-modity representation learning .
Outcome:	The proposed methods outperform the baseline self-supervised learning strategies on the Memotion challenge and the HarMeme task.

Copied to clipboard

Hugo Berg, Siobhan Hall, Yash Bhalgat, Hannah Kirk, Aleksandar Shtedritski, Max Bain

Some Languages are More Equal than Others: Probing Deeper into the Linguistic Disparity in the NLP World (2022.aacl-main)

Challenge:	Large-scale, pretrained vision-language models are growing in popularity due to impressive performance on downstream tasks with minimal finetuning.
Approach:	They propose to apply ranking metrics to image-text representations to investigate bias measures and debiasing methods to reduce various bias measures.
Outcome:	The proposed model reduces bias measures with minimal degradation to image-text representations.

Copied to clipboard

Surangika Ranathunga, Nisansa de Silva

Multilinguality

Challenge:	Linguistic disparity in the NLP world is widely acknowledged, but the reasons behind it are rarely discussed within the field.
Approach:	They propose to categorise languages based on speaker population and vitality . they also analyse the distribution of language data resources and amount of NLP/CL research .
Outcome:	The proposed model identifies the reasons for the disparity and suggests ways to overcome it.

Neural Readability Pairwise Ranking for Sentences in Italian Administrative Language (2022.aacl-main)

Copied to clipboard

Martina Miliani, Serena Auriemma, Fernando Alva-Manchego, Alessandro Lenci

Paraphrasing

Challenge:	Automatic Readability Assessment (ARA) aims at assigning a complexity level to a text, which could help improve the accessibility to information in specific domains, such as the administrative one.
Approach:	They propose to use a Neural Pairwise Ranking Model (NPRM) to assess Italian administrative texts by rewriting sentences using three different rewrite strategies.
Outcome:	The proposed model is effective in zero-shot scenarios (0.78) and the best results are obtained by adding in-domain data (achieving perfect performance for such sentence pairs).

Delivering Fairness in Human Resources AI: Mutual Information to the Rescue (2022.aacl-main)

Copied to clipboard

Leo Hemamou, William Coleman

Not another Negation Benchmark: The NaN-NLI Test Suite for Sub-clausal Negation (2022.aacl-main)

Challenge:	Automated language processing is used in the Human Resources sector for automated candidate sourcing and evaluation of resumes.
Approach:	They propose to minimize the MI between a candidate’s name and a latent representation of their CV or short biography by first projecting the name representation into a smaller space to prevent potential MI minimization problems in high dimensions.
Outcome:	The proposed method minimizes the MI between a candidate’s name and a latent representation of their CV or short biography.

Copied to clipboard

Thinh Hung Truong, Yulia Otmakhova, Timothy Baldwin, Trevor Cohn, Jey Han Lau, Karin Verspoor

HaRiM+: Evaluating Summary Quality with Hallucination Risk (2022.aacl-main)

Challenge:	Negation is an important linguistic phenomenon which denotes non-existence, denial, or contradiction.
Approach:	They propose a natural language inference test suite to test models for negation . they use a linguistic framework to analyze negation types and constructions .
Outcome:	The proposed test suite is more challenging than existing benchmarks on negation . it includes annotation of negation types and constructions grounded in linguistic theory .

Copied to clipboard

Seonil (Simon) Son, Junsoo Park, Jeong-in Hwang, Junghwa Lee, Hyungjong Noh, Yeonsoo Lee

Text Generation

Challenge:	Existing summarization models are limited in measuring the factual inconsistency of generated summaries.
Approach:	They propose a decoder overconfidence-regularizing objective as a hallucination risk measurement to better estimate the quality of generated summaries.
Outcome:	The proposed metric is reference-free and requires no training or modules . it records state-of-the-art correlation to human judgment on three sets of summary-quality annotations.

The lack of theory is painful: Modeling Harshness in Peer Review Comments (2022.aacl-main)

Copied to clipboard

Rajeev Verma, Rajarshi Roychoudhury, Tirthankar Ghosal

Linguistic Theories

Challenge:	a new study shows that peer-review has a power imbalance, making it fraught for authors . authors argue that a little more effort to remain critical but be constructive would help foster a positive outcome .
Approach:	They propose to use a dataset to show peer-review comments' harshness scores . they argue that this moderation could help authors to be more constructive .
Outcome:	The proposed dataset shows that it can be used to make peer reviews less hurtful and more welcoming.

Dual Mechanism Priming Effects in Hindi Word Order (2022.aacl-main)

Copied to clipboard

Sidharth Ranjan, Marten van Schijndel, Sumeet Agarwal, Rajakrishnan Rajkumar

Syntactic Text Processing

Challenge:	Existing studies have shown that word order choices can be primed by preceding sentences.
Approach:	They propose to model lexical priming and lexically-independent syntactic priming using a logistic regression model.
Outcome:	The proposed hypothesis supports multiple cognitive mechanisms . the experimental record shows that lexical priming and lexically-independent priming affect complementary sets of verb classes.

Unsupervised Single Document Abstractive Summarization using Semantic Units (2022.aacl-main)

Copied to clipboard

Jhen-Yi Wu, Ying-Jia Lin, Hung-Yu Kao

Detecting Incongruent News Articles Using Multi-head Attention Dual Summarization (2022.aacl-main)

Challenge:	a lack of sufficient training pairs is a common issue in real-world applications.
Approach:	They propose a framework that lets a model learn the frequency of each semantic unit in the source text.
Outcome:	The proposed model outperforms other unsupervised methods under CNN/Daily Mail task.

Copied to clipboard

Sujit Kumar, Gaurav Kumar, Sanasam Ranbir Singh

Summarization

Challenge:	Recent studies on incongruity detection focus on estimating the similarity between the headline and the encoding of the body or its summary but most of these methods fail to handle inconvenient news articles created with embedded noise.
Approach:	They propose a method which generates two types of summaries that capture the congruent and incongruent parts in the body separately.
Outcome:	The proposed method outperforms the state-of-the-art methods over three publicly available datasets.

Meta-Learning based Deferred Optimisation for Sentiment and Emotion aware Multi-modal Dialogue Act Classification (2022.aacl-main)

Copied to clipboard

Tulika Saha, Aditya Prakash Patra, Sriparna Saha, Pushpak Bhattacharyya

Information Retrieval

Challenge:	Empirically, we show that the optimisation of multi-modal DAC, SA and ER tasks produces better results compared to its different counterparts.
Approach:	They propose a dual attention mechanism that integrates sentiment tags into a multi-modal conversational framework that integrate modal attentions and multiple loss optimization.
Outcome:	The proposed framework integrates sentiment tags for each utterance and learns generalized features across multiple tasks.

Enhancing Financial Table and Text Question Answering with Tabular Graph and Numerical Reasoning (2022.aacl-main)

Copied to clipboard

Rungsiman Nararatwong, Natthawut Kertkeidkachorn, Ryutaro Ichise

Reasoning

Challenge:	Existing models that learn tabular structures in financial documents do not understand tables and numbers.
Approach:	They propose to infuse explicit tabular structures through a graph neural network to improve model's performance in question answering.
Outcome:	The proposed model outperforms the baseline model in low-resource settings while outperforming the graph module.

Fine-grained Contrastive Learning for Definition Generation (2022.aacl-main)

Copied to clipboard

Hengyuan Zhang, Dawei Li, Shiping Yang, Yanran Li

Hengam: An Adversarially Trained Transformer for Persian Temporal Tagging (2022.aacl-main)

Challenge:	Recent pre-trained transformer-based definition generation models lack effective representation learning to contain full semantic components of the given word, leading to under-specific definitions.
Approach:	They propose a novel contrastive learning method that encourages the model to capture more detailed semantic representations from the definition sequence encoding.
Outcome:	The proposed method could generate more specific definitions compared with state-of-the-art models.

Copied to clipboard

Sajad Mirzababaei, Amir Hossein Kargaran, Hinrich Schütze, Ehsaneddin Asgari

What’s Different between Visual Question Answering for Machine “Understanding” Versus for Accessibility? (2022.aacl-main)

Challenge:	A wide array of natural language processing (NLP) applications relies on accurately identifying events and their respective occurrence times.
Approach:	They propose an adversarially trained transformer for Persian temporal tagging that can generalize over the HengamTagger’s rules.
Outcome:	The proposed tool outperforms state-of-the-art methods on a diverse and manually created dataset.

Copied to clipboard

Yang Trista Cao, Kyle Seelman, Kyungjun Lee, Hal Daumé III

Persona or Context? Towards Building Context adaptive Personalized Persuasive Virtual Sales Assistant (2022.aacl-main)

Challenge:	Existing benchmarking datasets for visual question answering focus on machine "understanding" but it remains unclear how progress on those datasets corresponds to improvements in this real-world use case.
Approach:	They evaluate the visual question answering task by evaluating a variety of VQA models.
Outcome:	The proposed model can achieve high scores on tasks thought to require human-like comprehension, including image tagging and captioning.

Copied to clipboard

Abhisek Tiwari, Sriparna Saha, Shubhashis Sengupta, Anutosh Maitra, Roshni Ramnani, Pushpak Bhattacharyya

Dialogue Systems & Conversational Agents

Challenge:	Existing task-oriented conversational agents assume that end-users will always have a pre-determined and servable task goal, which results in dialogue failure in hostile scenarios, such as goal unavailability.
Approach:	They propose to build an end-to-end multi-modal persuasive dialogue system incorporating a personalized persuasive module aided goal controller and goal persuader.
Outcome:	The proposed system achieves user tasks even in goal unavailability scenarios by persuading them towards a similar and servable goal.

Legal Case Document Summarization: Extractive and Abstractive Methods and their Evaluation (2022.aacl-main)

Copied to clipboard

Abhay Shukla, Paheli Bhattacharya, Soham Poddar, Rajdeep Mukherjee, Kripabandhu Ghosh, Pawan Goyal, Saptarshi Ghosh

Summarization

Challenge:	Summarization of legal case judgement documents is a challenging problem in Legal NLP.
Approach:	They propose to use extractive and abstractive summarization methods to evaluate legal document summarizing systems.
Outcome:	The proposed methods have been evaluated on three legal summarization datasets.

FPC: Fine-tuning with Prompt Curriculum for Relation Extraction (2022.aacl-main)

Copied to clipboard

Sicheng Yang, Dandan Song

Dead or Murdered? Predicting Responsibility Perception in Femicide News Reports (2022.aacl-main)

Challenge:	Existing methods for relation extraction ignore semantics of relation labels . prompt-based fine-tuning has been proposed for RE .
Approach:	They propose a method for relation extraction using prompt-based fine-tuning . they use auxiliary prompt-tuned learning task to make the model capture semantics of relation labels .
Outcome:	The proposed method outperforms existing methods on four widely used RE benchmarks under fully supervised and low-resource settings.

Copied to clipboard

Gosse Minnema, Sara Gemelli, Chiara Zanchi, Tommaso Caselli, Malvina Nissim

PESE: Event Structure Extraction using Pointer Network based Encoder-Decoder Architecture (2022.aacl-main)

Challenge:	linguistic expressions of gender-based violence can conceptualize the same event from different perspectives by emphasizing certain participants over others.
Approach:	They conduct a large-scale perception survey of GBV descriptions from italian newspapers and train regression models that predict the salience of GV participants with respect to different dimensions of perceived responsibility.
Outcome:	The proposed model shows that salient focus is more predictable than salient blame, and perpetrators’ salience is more predictable than victims’ salient.

Copied to clipboard

Alapan Kuila, Sudeshna Sarkar

How do we get there? Evaluating transformer neural networks as cognitive models for English past tense inflection (2022.aacl-main)

Challenge:	Event extraction (EE) aims to find the events and event-related argument information from the text and represent them in a structured format.
Approach:	They propose to represent each event record in a unique tuple format that contains trigger phrase, trigger type, argument phrase, and corresponding role information.
Outcome:	The proposed model achieves competitive performance compared to the state-of-the-art methods.

Copied to clipboard

Xiaomeng Ma, Lingyu Gao

Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modeling (2022.aacl-main)

Challenge:	English past tense inflections is a typical quasi-regularity task, but it is criticized that it learns only to generalize the most frequent pattern, but not the regular pattern.
Approach:	They train a set of transformer models with different settings to examine their behavior on a typical English quasi-regularity task.
Outcome:	The models achieved high accuracy on unseen regular verbs and some accuracy on unseen irregular verbs.

Copied to clipboard

Ilia Kulikov, Maksim Eremeev, Kyunghyun Cho

Machine Translation

Challenge:	Neural autoregressive sequence models assign high probability to unreasonably short sequences . authors propose to minimize oversmoothing rate during training .
Approach:	They propose to minimize the oversmoothing rate during training by tuning the regularization strength.
Outcome:	The proposed regularization can control the oversmoothing rate and improve decoding performance.

Identifying Weaknesses in Machine Translation Metrics Through Minimum Bayes Risk Decoding: A Case Study for COMET (2022.aacl-main)

Copied to clipboard

Chantal Amrhein, Rico Sennrich

Machine Translation

Challenge:	Neural metrics have a high correlation with human judgements but they are hard to eliminate due to their "black box" nature.
Approach:	They propose to use minimum bayes risk decoding to explore and quantify weaknesses in COMET models.
Outcome:	The proposed model is not sensitive enough to discrepancies in numbers and named entities, and is hard to remove by training on additional synthetic data.

Whodunit? Learning to Contrast for Authorship Attribution (2022.aacl-main)

Copied to clipboard

Bo Ai, Yuchen Wang, Yugin Tan, Samson Tan

Higher-Order Dependency Parsing for Arc-Polynomial Score Functions via Gradient-Based Methods and Genetic Algorithm (2022.aacl-main)

Challenge:	Existing approaches to authorship attribution are dataset-dependent and yield inconsistent performance across corpora.
Approach:	They propose to fine-tune pre-trained generic language representations with a contrastive objective to learn author-specific representations by identifying clusters of authors.
Outcome:	The proposed approach improves on multiple human and machine authorship attribution benchmarks, but at the cost of sacrificing performance for some authors.

Copied to clipboard

Xudong Zhang, Joseph Le Roux, Thierry Charnois

Underspecification in Scene Description-to-Depiction Tasks (2022.aacl-main)

Challenge:	Existing methods for higher-order dependency parsing are based on arc-polynomials . a score function is linear in arc variables, while for second-order models it is linear .
Approach:	They propose a method which takes advantage of arc-polynomials score functions . they use coordinate ascent and genetic search to iteratively update a candidate parse .
Outcome:	The proposed method matches state-of-the-art second order parsers on three standard datasets.

Copied to clipboard

Ben Hutchinson, Jason Baldridge, Vinodkumar Prabhakaran