Taiwan

Several multi-hop reading comprehension datasets have been proposed to resolve the issue of reasoning shortcuts by which questions can be answered without performing multi-hop reasoning. However, the ability of multi-hop models to perform step-by-step reasoning when finding an answer to a comparison question remains unclear. It is also unclear how questions about the internal reasoning process are useful for training and evaluating question-answering (QA) systems. To evaluate the model precisely in a hierarchical manner, we first propose a dataset, \textit{HieraDate}, with three probing tasks in addition to the main question: extraction, reasoning, and robustness. Our dataset is created by enhancing two previous multi-hop datasets, HotpotQA and 2WikiMultiHopQA, focusing on multi-hop questions on date information that involve both comparison and numerical reasoning. We then evaluate the ability of existing models to understand date information. Our experimental results reveal that the multi-hop models do not have the ability to subtract two dates even when they perform well in date comparison and number subtraction tasks. Other results reveal that our probing questions can help to improve the performance of the models (e.g., by +10.3 F1) on the main QA task and our dataset can be used for data augmentation to improve the robustness of the models.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-short.58/)

IJCNLP-AACL 2022

How Well Do Multi-hop Reading Comprehension Models Understand Date Information?

reasoning ability

multi-hop dataset

question answering

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

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 and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING 2020

poster

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). 
<br>
<br>

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:
<br>
<br>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). 

Word associations are among the most common paradigms for studying the human mental lexicon. While their structure and types of associations have been well studied, surprisingly little attention has been given to the question of why participants produce the observed associations. Answering this question would not only advance understanding of human cognition, but could also aid machines in learning and representing basic commonsense knowledge. This paper introduces a large, crowd-sourced dataset of English word associations with explanations, labeled with high-level relation types. We present an analysis of the provided explanations, and design several tasks to probe to what extent current pre-trained language models capture the underlying relations. Our experiments show that models struggle to capture the diversity of human associations, suggesting WAX is a rich benchmark for commonsense modeling and generation.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.9/)

WAX: A New Dataset for Word Association eXplanations

Social media often serves as a breeding ground for various hateful and offensive content. Identifying such content on social media is crucial due to its impact on the race, gender, or religion in an unprejudiced society. However, while there is extensive research in hate speech detection in English, there is a gap in hateful content detection in low-resource languages like Bengali. Besides, a current trend on social media is the use of Romanized Bengali for regular interactions. To overcome the existing research's limitations, in this study, we develop an annotated dataset of 10K Bengali posts consisting of 5K actual and 5K Romanized Bengali tweets. We implement several baseline models for the classification of such hateful posts. We further explore the interlingual transfer mechanism to boost classification performance. Finally, we perform an in-depth error analysis by looking into the misclassified posts by the models. While training actual and Romanized datasets separately, we observe that XLM-Roberta performs the best. Further, we witness that on joint training and few-shot training, MuRIL outperforms other models by interpreting the semantic expressions better. We make our code and dataset public for others.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.23/)

Hate Speech and Offensive Language Detection in Bengali

We use Chinese ba/bei construction to explore if pre-trained transformer-based language models are capable of integrating syntax and semantics like humans. Our experiment results show a similar performance between humans and models for agency, but not for telicity and individuation. This suggests that models and humans respond diversely to features affecting argument hierarchy construction.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.21/)

Who did what to Whom? Language models and humans respond diversely to features affecting argument hierarchy construction

Recent methods based on pre-trained language models have exhibited superior performance over tabular tasks (e.g., tabular NLI), despite showing inherent problems such as not using the right evidence and inconsistent predictions across inputs while reasoning over the tabular data (Gupta et al., 2021). In this work, we utilize Pattern-Exploiting Training (PET) (i.e., strategic MLM) on pre-trained language models to strengthen these tabular reasoning models' pre-existing knowledge and reasoning abilities. Our upgraded model exhibits a superior understanding of knowledge facts and tabular reasoning compared to current baselines. Additionally, we demonstrate that such models are more effective for underlying downstream tasks of tabular inference on INFOTABS. Furthermore, we show our model's robustness against adversarial sets generated through various character and word level perturbations.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.54/)

Enhancing Tabular Reasoning with Pattern Exploiting Training

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.10/)

Missing Modality meets Meta Sampling (M3S): An Efficient Universal Approach for Multimodal Sentiment Analysis with Missing Modality

Emotion recognition in conversation (ERC) has attracted much attention in recent years for its necessity in widespread applications. With the development of graph neural network (GNN), recent state-of-the-art ERC models mostly use GNN to embed the intrinsic structure informa- tion of a conversation into the utterance fea- tures. In this paper, we propose a novel GNN- based model for ERC, namely S+PAGE, to bet- ter capture the speaker and position-aware con- versation structure information. Specifically, we add the relative positional encoding and speaker dependency encoding in the represen- tations of edge weights and edge types respec- tively to acquire a more reasonable aggregation algorithm for ERC. Besides, a two-stream con- versational Transformer is presented to extract both the self and inter-speaker contextual fea- tures for each utterance. Extensive experiments are conducted on four ERC benchmarks with state-of-the-art models employed as baselines for comparison, whose results demonstrate the superiority of our model.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.12/)

S+PAGE: A Speaker and Position-Aware Graph Neural Network Model for Emotion Recognition in Conversation

Knowledge graphs are increasingly used in a plethora of downstream tasks or in the augmentation of statistical models to improve factuality. However, social biases are engraved in these representations and propagate downstream. We conducted a critical analysis of literature concerning biases at different steps of a knowledge graph lifecycle. We investigated factors introducing bias, as well as the biases that are rendered by knowledge graphs and their embedded versions afterward. Limitations of existing measurement and mitigation strategies are discussed and paths forward are proposed.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.49/)

The Lifecycle of "Facts": On Social Biases in Knowledge Graphs

Recent research has revealed undesirable biases in NLP data and models. However, these efforts focus of social disparities in West, and are not directly portable to other geo-cultural contexts. In this paper, we focus on NLP fairness in the context of India. We start with a brief account of the prominent axes of social disparities in India. We build resources for fairness evaluation in the Indian context and use them to demonstrate prediction biases along some of the axes. We then delve deeper into social stereotypes for Region and Religion, demonstrating its prevalence in corpora and models. Finally, we outline a holistic research agenda to re-contextualize NLP fairness research for the Indian context, accounting for Indian societal context, bridging technological gaps in NLP capabilities and resources, and adapting to Indian cultural values. While we focus on India, this framework can be generalized to other geo-cultural contexts.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.55/)

Re-contextualizing Fairness in NLP: The Case of India

VScript is a controllable script generation system including dialogues and scene descriptions, as well as presents visually using video retrieval. We adopt a hierarchical structure for our framework by implementing high-level planning and following the guidelines of video-making processes.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-demo.1/)

VScript: Controllable Script Generation with Visual Presentation

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


How Well Do Multi-hop Reading Comprehension Models Understand Date Information?

Downloads

Next from IJCNLP-AACL 2022

WAX: A New Dataset for Word Association eXplanations

Similar lecture

Exploring the Zero Shot Limit of FewRel

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES