United States

The power and the potential of deep learning models attract many researchers to design advanced and sophisticated architectures. Nevertheless, the progress is sometimes unreal due to various possible reasons. In this work, through an astonishing example we argue that more efforts should be paid to ensure the progress in developing a new deep learning method. For a highly influential multi-label text classification method XML-CNN, we show that the superior performance claimed in the original paper was mainly due to some unbelievable coincidences. We re-examine XML-CNN and make a re-implementation which reveals some contradictory findings to the claims in the original paper. Our study suggests suitable baselines for multi-label text classification tasks and confirms that the progress on a new architecture cannot be confidently justified without a cautious investigation.

NAACL 2022

Even the Simplest Baseline Needs Careful Re-investigation: A Case Study on XML-CNN

## Welcome to NAACL 2022!
The Annual Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL) is taking place July 10-15, 2022 as a hybrid event, in Seattle, WA and online. We are happy to welcome all of you to conference! 
 
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, keynote presentations, a plenary panel on the place of linguistics and symbolic structures in NLP, and an Industrial Track panel on Careers in NLP.
 
Posters (including Findings of NAACL 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 and will have an oral session and a poster session.
 
The program also features 6 Tutorials and 26 Workshops.
 
 We wish you a wonderful conference!
 
[The NAACL 2022 Organizing Committee](https://2022.naacl.org/committees/organization/)

2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics

technical paper

At the foundation of scientific evaluation is the labor-intensive process of peer review. This critical task requires participants to consume vast amounts of highly technical text. Prior work has annotated different aspects of review argumentation, but discourse relations between reviews and rebuttals have yet to be examined.

We present DISAPERE, a labeled dataset of 20k sentences contained in 506 review-rebuttal pairs in English, annotated by experts. DISAPERE synthesizes label sets from prior work and extends them to include fine-grained annotation of the rebuttal sentences, characterizing their context in the review and the authors' stance towards review arguments. Further, we annotate \textitevery review and rebuttal sentence.

We show that discourse cues from rebuttals can shed light on the quality and interpretation of reviews. Further, an understanding of the argumentative strategies employed by the reviewers and authors provides useful signal for area chairs and other decision makers.

DISAPERE: A Dataset for Discourse Structure in Peer Review Discussions

Political perspective detection has become an increasingly important task that can help com- bat echo chambers and political polarization. Previous approaches generally focus on lever- aging textual content to identify stances, while they fail to reason with background knowledge or leverage the rich semantic and syntactic tex- tual labels in news articles. In light of these limitations, we propose KCD, a political per- spective detection approach to enable multi- hop knowledge reasoning and incorporate tex- tual cues as paragraph-level labels. Specif- ically, we firstly generate random walks on external knowledge graphs and infuse them with news text representations. We then con- struct a heterogeneous information network to jointly model news content as well as se- mantic, syntactic and entity cues in news arti- cles. Finally, we adopt relational graph neural networks for graph-level representation learn- ing and conduct political perspective detection. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods on two benchmark datasets. We further exam- ine the effect of knowledge walks and textual cues and how they contribute to our approach’s data efficiency.

KCD: Knowledge Walks and Textual Cues Enhanced Political Perspective Detection in News Media

Existing research on Tabular Natural Language Inference (TNLI) exclusively examines the task in a monolingual setting where the tabular premise and hypothesis are in the same language. However, due to the uneven distribution of text resources on the web across languages, it is common to have the tabular premise in a high resource language and the hypothesis in a low resource language. As a result, we present the challenging task of bilingual Tabular Natural Language Inference (bTNLI), in which the tabular premise and a hypothesis over it are in two separate languages. We construct EI-InfoTabS: an English-Indic bTNLI dataset by translating the textual hypotheses of the English TNLI dataset InfoTabS into eleven major Indian languages. We thoroughly investigate how pre-trained multilingual models learn and perform on EI-InfoTabS. Our study shows that the performance on bTNLI can be close to its monolingual counterpart, with translate-train, translate-test and unified-train being strongly competitive baselines.

Bilingual Tabular Inference: A Case Study on Indic Languages

In Neural Machine Translation, it is typically assumed that the sentence with the highest estimated probability should also be the translation with the highest quality as measured by humans. In this work, we question this assumption and show that model estimates and translation quality only vaguely correlate. We apply Minimum Bayes Risk (MBR) decoding on unbiased samples to optimize diverse automated metrics of translation quality as an alternative inference strategy to beam search.
Instead of targeting the hypotheses with the highest model probability, MBR decoding extracts the hypotheses with the highest estimated quality. Our experiments show that the combination of a neural translation model with a neural reference-based metric, \bleurt{}, results in significant improvement in human evaluations. This improvement is obtained with translations different from classical 
beam-search output: these translations have much lower model likelihood and are less favored by surface metrics like BLEU.

Minimum Bayes Risk Decoding with Neural Metrics of Translation Quality

Product Listing Ads (PLAs) are primary online advertisements merchants pay to attract more customers. However, merchants prefer to stack various attributes to the title and neglect the fluency and information priority. These seller-created titles are not suitable for PLAs as they fail to highlight the core information in the visible part in PLAs titles. In this work, we present a title rewrite solution. Specifically, we train a self-supervised language model to generate high-quality titles in terms of fluency and information priority. Extensive offline test and real-world online test have demonstrated that our solution is effective in reducing the cost and gaining more profit as it lowers our CPC, CPB while improving CTR in the online test by a large amount.

Self-supervised Product Title Rewrite for Product Listing Ads

In production SLU systems, new training data becomes available with time so that ML models need to be updated on a regular basis. Specifically, releasing new features adds new classes of data while the old data remains constant. However, retraining the full model each time from scratch is computationally expensive. To address this problem, we propose to consider production releases from the curriculum learning perspective and to adapt the local-to-global learning (LGL) schedule (Cheng et al., 2019) for a neural model that starts with fewer output classes and adds more classes with each iteration.
We report experiments for the tasks of intent classification and slot filling in the context of a production voice-assistant. First, we apply the original LGL schedule on our data and then adapt LGL to the production setting where the full data is not available at initial training it- erations. We demonstrate that our method improves model error rates by -7.3% and saves up to 25% training time for individual iterations.

Local-to-global learning for iterative training of production SLU models on new features

Medical coding (MC) is an essential pre-requisite for reliable data retrieval and reporting. Given a free-text reported term (RT) such as "pain of right thigh to the knee", the task is to identify the matching lowest-level term (LLT) - in this case "unilateral leg pain" - from a very large and continuously growing repository of standardized medical terms. However, automating this task is challenging due to a large number of LLT codes (as of writing over 80,000), limited availability of training data for long tail/emerging classes, and the general high accuracy demands of the medical domain. With this paper, we introduce the MC task, discuss its challenges, and present a novel approach called xTARS that combines traditional BERT-based classification with a recent zero/few-shot learning approach (TARS). We present extensive experiments that show that our combined approach outperforms strong baselines, especially in the few-shot regime. The approach is developed and deployed at Bayer, live since November 2021. As we believe our approach potentially promising beyond MC, and to ensure reproducibility, we release the code to the research community.

Medical Coding with Biomedical Transformer Ensembles and Zero/Few-shot Learning

Automatically associating social media posts with topics is an important prerequisite for effective search and recommendation on many social media platforms. However, topic classification of such posts is quite challenging because of (a) a large topic space (b) short text with weak topical cues and (c) multiple topic associations per post. In contrast to most prior work which only focuses on post classification into a small number of topics (10-20), we consider the task of large-scale topic classification in the context of Twitter where the topic space is 10 times larger with potentially multiple topic associations per Tweet. We address the challenges above by proposing a novel neural model, CTM that (a) supports a large topic space of 300 topics and (b) takes a holistic approach to tweet content modeling – leveraging multi-modal content, author context, and deeper semantic cues in the Tweet. Our method offers an effective way to classify Tweets into topics at scale by yielding superior performance to other approaches (a relative lift of 20% in median average precision score) and has been successfully deployed in production at Twitter.

CTM - A Model for Large-Scale Multi-View Tweet Topic Classification

Self-learning paradigms in large-scale conver- sational AI agents tend to leverage user feed- back in bridging between what they say and what they mean. However, such learning, par- ticularly in Markov-based query rewriting sys- tems have far from addressed the impact of these models on future training where succes- sive feedback is inevitably contingent on the rewrite itself, especially in a continually up- dating environment. In this paper, we explore the consequences of this inherent lack of self- awareness towards impairing the model perfor- mance, ultimately resulting in both Type I and II errors over time. To that end, we propose aug- menting the Markov Graph construction with a superposition-based adjacency matrix. Here, our method leverages an induced stochastic- ity to reactively learn a locally-adaptive deci- sion boundary based on the performance of the individual rewrites in a bi-variate beta set- ting. We also surface a data augmentation strat- egy that leverages template-based generation in abridging complex conversation hierarchies of dialogs so as to simplify the learning pro- cess. All in all, we demonstrate that our self- aware model improves the overall PR-AUC by 27.45%, achieves a relative defect reduction of up to 31.22%, and is able to adapt quicker to changes in global preferences across a large number of customers.

Self-Aware Feedback-Based Self-Learning in Large-Scale Conversational AI

A growing body of work uses Natural Language Processing (NLP) methods to automatically generate medical notes from audio recordings of doctor-patient consultations. However, there are very few studies on how such systems could be used in clinical practice, how clinicians would adjust to using them, or how system design should be influenced by such considerations. In this paper, we present three rounds of user studies, carried out in the context of developing a medical note generation system. We present, analyse and discuss the participating clinicians' impressions and views of how the system ought to be adapted to be of value to them. Next, we describe a three-week test run of the system in a live telehealth clinical practice. Major findings include (i) the emergence of five different note-taking behaviours; (ii) the importance of the system generating notes in real time during the consultation; and (iii) the identification of a number of clinical use cases that could prove challenging for automatic note generation systems.

Even the Simplest Baseline Needs Careful Re-investigation: A Case Study on XML-CNN

Downloads

Next from NAACL 2022

DISAPERE: A Dataset for Discourse Structure in Peer Review Discussions

Similar lecture

ExSum: From Local Explanations to Model Understanding

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES