Taiwan

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

IJCNLP-AACL 2022

Double Trouble: How to not explain a text classifier&#39;s decisions using counterfactuals synthesized by masked language models?

bert-based mask language models.

biases between attribution methods and metrics

counterfactuals

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). 

Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?

technical paper

Grammatical error correction (GEC) systems are a useful tool for assessing a learner's writing ability. These systems allow the grammatical proficiency of a candidate’s text to be assessed without requiring an examiner or teacher to read the text. A simple summary of a candidate's ability can be measured by the total number of edits between the input text and the GEC system output: the fewer the edits the better the candidate. With advances in deep learning, GEC systems have become increasingly powerful and accurate. However, deep learning systems are susceptible to adversarial attacks, in which a small change at the input can cause large, undesired changes at the output. In the context of GEC for automated assessment, the aim of an attack can be to deceive the system into not correcting (concealing) grammatical errors to create the perception of higher language ability. An interesting aspect of adversarial attacks in this scenario is that the attack needs to be simple as it must be applied by, for example, a learner of English. The form of realistic attack examined in this work is appending the same phrase to each input sentence: a concatenative universal attack. The candidate only needs to learn a single attack phrase. State-of-the-art GEC systems are found to be susceptible to this form of simple attack, which transfers to different test sets as well as system architectures.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.13/)

Grammatical Error Correction Systems for Automated Assessment: Are They Susceptible to Universal Adversarial Attacks?

Related works used indexes like CKA and variants of CCA to measure the similarity of cross-lingual representations in multilingual language models. In this paper, we argue that assumptions of CKA/CCA align poorly with one of the motivating goals of cross-lingual learning analysis, i.e., explaining zero-shot cross-lingual transfer. We highlight what valu- able aspects of cross-lingual similarity these indexes fail to capture and provide a motivating case study demonstrating the problem empir- ically. Then, we introduce Average Neuron- Wise Correlation (ANC) as a straightforward al- ternative that is exempt from the difficulties of CKA/CCA and is good specifically in a cross- lingual context. Finally, we use ANC to con- struct evidence that the previously introduced “first align, then predict” pattern takes place not only in masked language models (MLMs) but also in multilingual models with causal lan- guage modeling objectives (CLMs). Moreover, we show that the pattern extends to the scaled versions of the MLMs and CLMs (up to 85x original mBERT).

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.15/)

Cross-lingual Similarity of Multilingual Representations Revisited

Human fixation patterns have been shown to correlate strongly with Transformer-based attention. Those correlation analyses are usually carried out without taking into account individual differences between participants and are mostly done on monolingual datasets making it difficult to generalise findings. In this paper, we analyse eye-tracking data from speakers of 13 different languages reading both in their native language (L1) and in English as language learners (L2). We find considerable differences between languages but also that individual reading behaviour such as skipping rate, total reading time and vocabulary knowledge (LexTALE) influence the alignment between humans and models to an extent that should be considered in future studies.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-short.10/)

Every word counts: A multilingual analysis of individual human alignment with model attention

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-short.54/)

Automatic Readability Assessment: Can Linguistic Features Promote Pre-trained Language Models

Cross-lingual transfer learning has proven useful in a variety of Natural Language Processing (NLP) tasks, but it is understudied in the context of legal NLP, and not at all in Legal Judgment Prediction (LJP). We explore transfer learning techniques on LJP using the trilingual Swiss-Judgment-Prediction dataset, including cases written in three languages. We find that cross-lingual transfer improves the overall results across languages, especially when we use adapter-based fine-tuning. Finally, we further improve the model's performance by augmenting the training dataset with machine-translated versions of the original documents, using a 3x larger training corpus. Further on, we perform an analysis exploring the effect of cross-domain and cross-regional transfer, i.e., train a model across domains (legal areas), or regions. We find that in both settings (legal areas, origin regions), models trained across all groups perform overall better, while they also have improved results in the worst-case scenarios. Finally, we report improved results when we ambitiously apply cross-jurisdiction transfer, where we further augment our dataset with Indian legal cases.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.3/)

An Empirical Study on Cross-X Transfer for Legal Judgment Prediction

The use of deep neural models for diagnosis prediction from clinical text has shown promising results. However, in clinical practice such models must not only be accurate, but provide doctors with interpretable and helpful results. We introduce ProtoPatient, a novel method based on prototypical networks and label-wise attention with both of these abilities. ProtoPatient makes predictions based on parts of the text that are similar to prototypical patients–providing justifications that doctors understand. We evaluate the model on two publicly available clinical datasets and show that it outperforms existing baselines. Quantitative and qualitative evaluations with medical doctors further demonstrate that the model provides valuable explanations for clinical decision support.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.14/)

This Patient Looks Like That Patient: Prototypical Networks for Interpretable Diagnosis Prediction from Clinical Text

While there has been substantial progress in developing systems to automate fact-checking, they still lack credibility in the eyes of the users. Thus, an interesting approach has emerged: to perform automatic fact-checking by verifying whether an input claim has been previously fact-checked by professional fact-checkers and to return back an article that explains their decision. This is a sensible approach as people trust manual fact-checking, and as many claims are repeated multiple times. Yet, a major issue when building such systems is the small number of known tweet--verifying article pairs available for training. Here, we aim to bridge this gap by making use of crowd fact-checking, i.e., mining claims in social media for which users have responded with a link to a fact-checking article. In particular, we mine a large-scale collection of 330,000 tweets paired with a corresponding fact-checking article. We further propose an end-to-end framework to learn from this noisy data based on modified self-adaptive training, in a distant supervision scenario. Our experiments on the CLEF'21 CheckThat! test set show improvements over the state of the art by two points absolute. Our code and datasets are available at https://github.com/mhardalov/
crowdchecked-claims.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.22/)

CrowdChecked: Detecting Previously Fact-Checked Claims in Social Media

Automated reporting has the potential to assist radiologists with the time-consuming procedure of generating text radiology reports. Most existing approaches generate the report directly from the radiology image, however we observe that the resulting reports exhibit a realistic style but lack clinical accuracy. Therefore, we propose a two-step pipeline that subdivides the problem into factual triple extraction followed by free-text report generation. The first step comprises supervised extraction of clinically relevant structured information from the image, expressed as triples of the form (entity1, relation, entity2). In the second step, these triples are input to condition the generation of the radiology report. In particular, we focus our work on Chest X-Ray (CXR) radiology report generation. The proposed framework shows state-of-the-art results on the MIMIC-CXR dataset according to most of the standard text generation metrics that we employ (BLEU, METEOR, ROUGE) and to clinical accuracy metrics (recall, precision and F1 assessed using the CheXpert labeller), also giving a 23% reduction in the total number of errors and a 29% reduction in critical clinical errors as assessed by expert human evaluation. In future, this solution can easily integrate more advanced model architectures – to both improve the triple extraction and the report generation – and can be applied to other complex image captioning tasks, such as those found in the medical domain.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.47/)

Multimodal Generation of Radiology Reports using Knowledge-Grounded Extraction of Entities and Relations

Universal Sentence Encoder (USE) has gained much popularity recently as a general-purpose sentence encoding technique. As the name suggests, USE is designed to be fairly general and has indeed been shown to achieve superior performances for many downstream NLP tasks. In this paper, we present an interesting "negative'' result on USE in the context of zero-shot text classification, a challenging task, which has recently gained much attraction. More specifically, we found some interesting cases of zero-shot classification, where topic based inference outperformed USE-based inference in terms of F1 score. Further investigation revealed that USE struggles to perform well on datasets with a large number of labels with high semantic overlaps, while topic-based classification works well for the same.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-short.18/)

Exploring Universal Sentence Encoders for Zero-shot Text Classification

In this talk, I will share my perspective on making conversational AI more inclusive and accessible through advances in natural language understanding, speech recognition, and by incorporating interaction affordances that make conversational AI more useful for everyone. I will start with a brief overview of accessibility considerations and some Alexa-powered user experiences that address those considerations. That overview will be followed by a description of some of our recent and ongoing AI/ML work in natural language understanding (Alexa Teacher Model) and in ASR with a focus on achieving fairness at scale. I will conclude with a brief mention of our engagements with academia, including through the Alexa Prize and through the release of publicly available datasets and associated research tasks.

Downloads

Next from IJCNLP-AACL 2022

Grammatical Error Correction Systems for Automated Assessment: Are They Susceptible to Universal Adversarial Attacks?

Similar lecture

Efficient and Robust Knowledge Graph Construction

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from IJCNLP-AACL 2022

Grammatical Error Correction Systems for Automated Assessment: Are They Susceptible to Universal Adversarial Attacks?

Similar lecture

Efficient and Robust Knowledge Graph Construction

Downloads