Ireland

We debias the Who&#39;s Waldo dataset (Cui, et al. 2021) for the Person-centric Visual Grounding (PCVG) task, by filtering out the unsolvable instances. We show our now sub-sampled dataset contains less heuristic biases and serves more practical baselines for reliable benchmarking in future.

ACL 2022

To Find Waldo You Need Contextual Cues: Debiasing Who’s Waldo

visual-linguistic reasoning

dataset debiasing

resources and evaluation

visual grounding

# 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)

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). 

We debias the Who's Waldo dataset (Cui, et al. 2021) for the Person-centric Visual Grounding (PCVG) task, by filtering out the unsolvable instances. We show our now sub-sampled dataset contains less heuristic biases and serves more practical baselines for reliable benchmarking in future.

poster

Targeted Sentiment Analysis aims to extract sentiment towards a particular target from a given text. It is a field that is attracting attention due to the increasing accessibility of the Internet, which leads people to generate an enormous amount of data. Sentiment analysis, which in general requires annotated data for training, is a well-researched area for widely studied languages such as English. For low-resource languages such as Turkish, there is a lack of such annotated data. We present an annotated Turkish dataset suitable for targeted sentiment analysis. We also propose BERT-based models with different architectures to accomplish the task of targeted sentiment analysis. The results demonstrate that the proposed models outperform the traditional sentiment analysis models for the targeted sentiment analysis task.

 A Dataset and BERT-based Models for Targeted Sentiment Analysis on Turkish Texts

In a fill-in-the-blank exercise, a student is presented with a carrier sentence with one word hidden, and a multiple-choice list that includes the correct answer and several inappropriate options, called distractors. We propose to automatically generate distractors using round-trip neural machine translation: the carrier sentence is translated from English into another (pivot) language and back, and distractors are produced by aligning the original sentence and its round-trip translation. We show that using hundreds of translations for a given sentence allows us to generate a rich set of challenging distractors. Further, using multiple pivot languages produces a diverse set of candidates. The distractors are evaluated against a real corpus of cloze exercises and checked manually for validity. We demonstrate that the proposed method significantly outperforms two strong baselines.

 Automatic Generation of Distractors for Fill-in-the-Blank Exercises with Round-Trip Neural Machine Translation

Effective methods for multiword expressions detection are important for many technologies related to Natural Language Processing. Most contemporary methods are based on the sequence labeling scheme applied to an annotated corpus, while traditional methods use statistical measures. In our approach, we want to integrate the concepts of those two approaches. We present a novel weakly supervised multiword expressions extraction method which focuses on their behaviour in various contexts. Our method uses a lexicon of English multiword lexical units acquired from The Oxford Dictionary of English as a reference knowledge base and leverages neural language modelling with deep learning architectures. In our approach, we do not need a corpus annotated specifically for the task. The only required components are: a lexicon of multiword units, a large corpus, and a general contextual embeddings model. We propose a method for building a silver dataset by spotting multiword expression occurrences and acquiring statistical collocations as negative samples. Sample representation has been inspired by representations used in Natural Language Inference and relation recognition. Very good results (F1=0.8) were obtained with CNN network applied to individual occurrences followed by weighted voting used to combine results from the whole corpus. The proposed method can be quite easily applied to other languages.

 Deep Neural Representations for Multiword Expressions Detection

This work presents two experiments with the goal of replicating the transferability of dependency parsers and POS taggers trained on closely related languages within the low-resource language family Tupían. The experiments include both zero-shot settings as well as multilingual models. Previous studies have found that even a comparably small treebank from a closely related language will improve sequence labelling considerably in such cases. Results from both POS tagging and dependency parsing confirm previous evidence that the closer the phylogenetic relation between two languages, the better the predictions for sequence labelling tasks get. In many cases, the results are improved if multiple languages from the same family are combined. This suggests that in addition to leveraging similarity between two related languages, the incorporation of multiple languages of the same family might lead to better results in transfer learning for NLP applications.

 Evaluating zero-shot transfers and multilingual models for dependency parsing and POS tagging within the low-resource language family Tupían

Knowledge Graphs (KGs) are symbolically structured storages of facts. The KG embedding contains concise data used in NLP tasks requiring implicit information about the real world. Furthermore, the size of KGs that may be useful in actual NLP assignments is enormous, and creating embedding over it has memory cost issues. We represent KG as a 3rd-order binary tensor and move beyond the standard CP decomposition~\cite{hitchcock-sum-1927} by using a data-specific generalized version of it~\cite{Hong_2020}. The generalization of the standard CP-ALS algorithm allows obtaining optimization gradients without a backpropagation mechanism. It reduces the memory needed in training while providing computational benefits. We propose a MEKER, a memory-efficient KG embedding model, which yields SOTA-comparable performance on link prediction tasks and KG-based Question Answering.

 MEKER: Memory Efficient Knowledge Embedding Representation for Link Prediction and Question Answering

The capability of holding social talk (or casual conversation) and making sense of conversational content requires context-sensitive natural language understanding and reasoning, which cannot be handled efficiently by the current popular open-domain dialog systems and chatbots. Heavily relying on corpus-based machine learning techniques to encode and decode context-sensitive meanings, these systems focus on fitting a particular training dataset, but not tracking what is actually happening in a conversation, and therefore easily derail in a new context. This work sketches out a more linguistically-informed architecture to handle social talk in English, in which corpus-based methods form the backbone of the relatively context-insensitive components (e.g. part-of-speech tagging, approximation of lexical meaning and constituent chunking), while symbolic modeling is used for reasoning out the context-sensitive components, which do not have any consistent mapping to linguistic forms. All components are fitted into a Bayesian game-theoretic model to address the interactive and rational aspects of conversation.

 Sketching a Linguistically-Driven Reasoning Dialog Model for Social Talk

In this work, we explore the novel idea of employing dependency parsing information in the
context of few-shot learning, the task of learning the meaning of a rare word based on a limited amount of context sentences. Firstly, we
use dependency-based word embedding models as background spaces for few-shot learning.
Secondly, we introduce two few-shot learning
methods which enhance the additive baseline
model by using dependencies.

 Using dependency parsing for few-shot learning in distributional semantics

We present an event structure classification empirically derived from inferential properties annotated on sentence- and document-level Universal Decompositional Semantics (UDS) graphs. We induce this classification jointly with semantic role, entity, and event-event relation classifications using a document-level generative model structured by these graphs. To support this induction, we augment existing annotations found in the UDS1.0 dataset, which covers the entirety of the English Web Treebank, with an array of inferential properties capturing fine-grained aspects of the temporal and aspectual structure of events. The resulting dataset (available at decomp.io) is the largest annotation of event structure and (partial) event coreference to date.

Decomposing and Recomposing Event Structure

Existing table question answering datasets contain abundant factual questions that primarily evaluate a QA system’s comprehension of query and tabular data. However, restricted by their short-form answers, these datasets fail to include question–answer interactions that represent more advanced and naturally occurring information needs: questions that ask for reasoning and integration of information pieces retrieved from a structured knowledge source. To complement the existing datasets and to reveal the challenging nature of the table-based question answering task, we introduce FeTaQA, a new dataset with 10K Wikipedia-based {table, question, free-form answer, supporting table cells} pairs. FeTaQA is collected from noteworthy descriptions of Wikipedia tables that contain information people tend to seek; generation of these descriptions requires advanced processing that humans perform on a daily basis: Understand the question and table, retrieve, integrate, infer, and conduct text planning and surface realization to generate an answer. We provide two benchmark methods for the proposed task: a pipeline method based on semantic parsing-based QA systems and an end-to-end method based on large pretrained text generation models, and show that FeTaQA poses a challenge for both methods.

FeTaQA: Free-form Table Question Answering

We introduce a neuro-symbolic natural logic framework based on reinforcement learning with introspective revision. The model samples and rewards specific reasoning paths through policy gradient, in which the introspective revision algorithm modifies intermediate symbolic reasoning steps to discover reward-earning operations as well as leverages external knowledge to alleviate spurious reasoning and training inefficiency. The framework is supported by properly designed local relation models to avoid input entangling, which helps ensure the interpretability of the proof paths. The proposed model has built-in interpretability and shows superior capability in monotonicity inference, systematic generalization, and interpretability, compared to previous models on the existing datasets.

To Find Waldo You Need Contextual Cues: Debiasing Who’s Waldo

Downloads

Next from ACL 2022

A Dataset and BERT-based Models for Targeted Sentiment Analysis on Turkish Texts

Similar lecture

Comprehensive Multi-Modal Interactions for Referring Image Segmentation