United Arab Emirates

Multi-hop Question Answering (QA) is a challenging task since it requires an accurate aggregation of information from multiple context paragraphs and a thorough understanding of the underlying reasoning chains. Recent work in multi-hop QA has shown that performance can be boosted by first decomposing the questions into simpler, single-hop questions. In this paper, we explore one additional utility of the multi-hop decomposition from the perspective of explainable NLP: to create explanation by probing a neural QA model with them. We hypothesize that in doing so, users will be better able to predict when the underlying QA system will give the correct answer. Through human participant studies, we verify that exposing the decomposition probes and answers to the probes to users can increase their ability to predict system performance on a question instance basis. We show that decomposition is an effective form of probing QA systems as well as a promising approach to explanation generation. In-depth analyses show the need for improvements in decomposition systems.

EMNLP 2022

Calibrating Trust of Multi-Hop Question Answering Systems with Decompositional Probes

trust calibration

explainable ai

multi-hop question answering

## Welcome to EMNLP 2022!
I am delighted to welcome you to EMNLP 2022! I believe this conference has been complicated beyond any precedent. Over the past year, it’s been thrilling to see the organization team approach each new puzzle with creativity and enthusiasm. We hope that those participating in Abu Dhabi as well as those joining remotely will leave the conference feeling newly inspired by the program and newly connected to our ever-growing community. Following EMNLP 2021 and major NLP conferences since, EMNLP 2022 is “hybrid,” serving both virtual and in-person participants.

Our key innovations for EMNLP 2022 include:

* EMNLP 2022 is “hybrid” in a second sense, as well: we allowed both direct and rolling review paper submissions, building on the pilot experiment of EMNLP 2021, which considered a small number of ARR submissions. 
* Familiar from NAACL but new to EMNLP, we’ve added an industry track.
* During the conference, “portals” will link virtual poster sessions to in-person conference participants during poster sessions each day.
* The first ACL-family conference in the United Arab Emirates.

 *Message from Noah A. Smith, University of Washington and Allen Institute for AI, Seattle, Washington, USA* 
***EMNLP 2022 General Chair***
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/9eec7d4a287ee18c278b08229290aa83.png)](https://drive.google.com/file/d/1OlPv6QBeo62VVTughj2jkiLeyHd1WnUt/view)
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/a3db7a768409f05192210d98601edb25.png)](https://emnlp2022.rocket.chat/)

To access this site you need to register. Please register [here](https://2022.emnlp.org/registration/).

Register here

Welcome!
EMNLP 2022 will take place in Abu Dhabi from December 7th to December 11th, 2022. And it will be held in hybrid mode, both online and offline.

workshop paper

Many standard tasks in NLP (e.g., Named Entity Recognition, Part-of-Speech tagging, and Semantic Role Labeling) are naturally framed as sequence tagging problems. However, there has been comparatively little work on interpretability methods for sequence tagging models. In this paper, we extend influence functions --- which aim to trace predictions back to the training points that informed them --- to sequence tagging tasks. We define the influence of a training instance segment as the effect that perturbing the labels within this segment has on a test segment level prediction. We provide an efficient approximation to compute this, and show that it tracks with the "true" segment influence (measured empirically). We show the practical utility of segment influence by using the method to identify noisy annotations in NER corpora.

Influence Functions for Sequence Tagging Models

Counterfactual data augmentation (CDA) -- i.e., adding minimally perturbed inputs during training -- helps reduce model reliance on spurious correlations and improves generalization to out-of-distribution (OOD) data. Prior work on generating counterfactuals only considered restricted classes of perturbations, limiting their effectiveness. We present Counterfactual Generation via Retrieval and Editing (CORE), a retrieval-augmented generation framework for creating diverse counterfactual perturbations for CDA. For each training example, CORE first performs a dense retrieval over a task-related unlabeled text corpus using a learned bi-encoder and extracts relevant counterfactual excerpts. CORE then incorporates these into prompts to a large language model with few-shot learning capabilities, for counterfactual editing. Conditioning language model edits on naturally occurring data results in more diverse perturbations. Experiments on natural language inference and sentiment analysis benchmarks show that CORE counterfactuals are more effective at improving generalization to OOD data compared to other DA approaches. We also show that the CORE retrieval framework can be used to encourage diversity in manually authored perturbations.

CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation

Weak Supervised Learning (WSL) is a popular technique to develop machine learning models in absence of labeled training data. WSL involves training over noisy labels which are traditionally obtained from hand-engineered semantic rules and task-specific pre-trained models. Such rules offer limited coverage and generalization over tasks. On the other hand, pre-trained models are available only for limited tasks. Thus, obtaining weak labels is a bottleneck in weak supervised learning. In this work, we propose to utilize the prompting paradigm to generate weak labels for the underlying tasks. We show that task-agnostic prompts are generalizable and can be used to obtain noisy labels for different Spoken Language Understanding (SLU) tasks such as sentiment classification, disfluency detection and emotion classification. These prompts can additionally be updated with human-in-the-loop to add task-specific contexts, thus providing flexibility to design task-specific prompts. Our proposed WSL pipeline outperforms other competitive low-resource benchmarks on zero and few-shot learning by more than 4\% on Macro-F1 and a conventional rule-based WSL baseline by more than 5\% across all the benchmark datasets. We demonstrate that prompt-based methods save nearly 75\% of time in a weak-supervised framework and generate more reliable labels for the above SLU tasks and thus can be used as a universal strategy to obtain weak labels.

Partially Humanizing Weak Supervision: Towards a Better Low Resource Pipeline for Spoken Language Understanding

Identifying and exploring emerging trends in news is becoming more essential than ever with many changes occurring around the world due to the global health crises. However, most of the recent research has focused mainly on detecting trends in social media, thus, benefiting from social features (e.g. likes and retweets on Twitter) which helped the task as they can be used to measure the engagement and diffusion rate of content. Yet, formal text data, unlike short social media posts, comes with a longer, less restricted writing format, and thus, more challenging. In this paper, we focus our study on emerging trends detection in financial news articles about Microsoft, collected before and during the start of the COVID-19 pandemic (July 2019 to July 2020). We make the dataset freely available and we also propose a strong baseline (Contextual Leap2Trend) for exploring the dynamics of similarities between pairs of keywords based on topic modeling and term frequency. Finally, we evaluate against a gold standard (Google Trends)  and present noteworthy real-world scenarios regarding the influence of the pandemic on Microsoft.

Contextualizing Emerging Trends in Financial News Articles

Using the pre-trained language models to understand source codes has attracted increasing attention from financial institutions owing to the great potential to uncover financial risks. However, there are several challenges in applying these language models to solve programming language related problems directly. For instance, the shift of domain knowledge between natural language (NL) and programming language (PL) requires understanding the semantic and syntactic information from the data from different perspectives. To this end, we propose the AstBERT model, a pre-trained PL model aiming to better understand the financial codes using the abstract syntax tree (AST). Specifically, we collect a sheer number of source codes (both Java and Python) from the Alipay code repository and incorporate both syntactic and semantic code knowledge into our model through the help of code parsers, in which AST information of the source codes can be interpreted and integrated. We evaluate the performance of the proposed model on three tasks, including code question answering, code clone detection and code refinement. Experiment results show that our AstBERT achieves promising performance on three different downstream tasks.

AstBERT: Enabling Language Model for Financial Code Understanding with Abstract Syntax Trees

Automatic generating financial report from a set of news is important but challenging. The financial reports is composed of key points of the news and corresponding inferring and reasoning from specialists in financial domain with professional knowledge. The challenges lie in the effective learning of the extra knowledge that is not well presented in the news, and the misalignment between topic of input news and output knowledge in target reports. In this work, we introduce a disentangled variational topic inference approach to learn two latent variables for news and report, respectively. We use a publicly available dataset to evaluate the proposed approach. The results demonstrate its effectiveness of enhancing the language informativeness and the topic accuracy of the generated financial reports.

Disentangled Variational Topic Inference for Topic-Accurate Financial Report Generation

Text embedding is an essential component to build efficient natural language applications based on text similarities such as search engines and chatbots. Certain industries like finance and healthcare demand strict privacy-preserving conditions that user's data should not be exposed to any potential malicious users even including service providers. From a privacy standpoint, text embeddings seem impossible to be interpreted but there is still a privacy risk that they can be recovered to original texts through inversion attacks. To satisfy such privacy requirements, in this paper, we study a Homomorphic Encryption (HE) based text similarity inference. To validate our method, we perform extensive experiments on two vital text similarity tasks. Through text embedding inversion tests, we prove that the benchmark datasets are vulnerable to inversion attacks and another privacy preserving approach, dχ-privacy, a relaxed version of Local Differential Privacy method fails to prevent them. We show that our approach preserves the performance of models compared to that the baseline has degradation up to 10% of scores for the minimum security.

Toward Privacy-preserving Text Embedding Similarity with Homomorphic Encryption

Stock sentiment has strong correlations with the stock market but traditional sentiment analysis task classifies sentiment according to having feelings and emotions of good or bad. This definition of sentiment is not an accurate indicator of public opinion about specific stocks. To bridge this gap, we introduce a new task of stock sentiment analysis and present a new dataset for this task named TweetFinSent. In TweetFinSent, tweets are annotated based on if one gained or expected to gain positive or negative return from a stock. Experiments on TweetFinSent with several sentiment analysis models from lexicon-based to transformer-based have been conducted. Experimental results show that TweetFinSent dataset constitutes a challenging problem and there is ample room for improvement on the stock sentiment analysis task. TweetFinSent is available at \url{https://github.com/jpmcair/tweetfinsent}.

TweetFinSent: A Dataset of Stock Sentiments on Twitter

Accurate prediction of the stock price volatility, the rate at which the price of a stock increases or decreases over a particular period, is an important problem in finance. Inaccurate prediction of stock price volatility might lead to investment risk and financial loss, while accurate prediction might generate significant returns for investors. Several studies investigated stock price volatility prediction in a regression task by using the transcripts of earning calls (quarterly conference calls held by public companies) with Natural Language Processing (NLP) techniques. Existing studies use the entire transcript and this degrades the performance due to noise caused by irrelevant information that might not have a significant impact on stock price volatility. In order to overcome these limitations, by considering stock price volatility prediction as a classification task, we explore several denoising approaches, ranging from general-purpose approaches to techniques specific to finance to remove the noise, and leverage AutoML systems that enable auto-exploration of a wide variety of models. Our preliminary findings indicate that domain-specific denoising approaches provide better results than general-purpose approaches, moreover AutoML systems provide promising results.

Stock Price Volatility Prediction: A Case Study with AutoML

Digital transformation reinvents companies, their vision and strategy, organizational structure, processes, capabilities, and culture, and enables the development of new or enhanced products and services delivered to customers more efficiently. Organizations, by formalizing their digital strategy attempt to plan for their digital transformations and accelerate their company growth. Understanding how successful a company is in its digital transformation starts with accurate measurement of its digital maturity levels. However, existing approaches to measuring organizations' digital strategy have low accuracy levels and this leads to inconsistent results, and also does not provide resources (data) for future research to improve. In order to measure the digital strategy maturity of companies, we leverage the state-of-the-art NLP models on unstructured data (earning call transcripts), and reach the state-of-the-art levels (94\%) for this task. We release 3.691 earning call transcripts and also annotated data set, labeled particularly for the digital strategy maturity by linguists. Our work provides an empirical baseline for research in industry and management science.

Downloads

Next from EMNLP 2022

Influence Functions for Sequence Tagging Models

Similar lecture

Calibrating Trust of Multi-Hop Question Answering Systems with Decompositional Probes