United Arab Emirates

With the recent surge of NLP technologies in the financial domain, banks and other financial entities have adopted virtual agents (VA) to assist customers. A challenging problem for VAs in this domain is determining a user&#39;s reason or intent for contacting the VA, especially when the intent was unseen or open during the VA&#39;s training. One method for handling open intents is adaptive decision boundary (ADB) post-processing, which learns tight decision boundaries from intent representations to separate known and open intents. We propose incorporating two methods for supervised pre-training of intent representations: prefix tuning and fine-tuning just the last layer of a large language model (LLM). With this proposal, our accuracy is 1.63% - 2.07% higher than the prior state-of-the-art ADB method for open intent classification on the banking77 benchmark amongst others. Notably, we only supplement the original ADB model with 0.1% additional trainable parameters. Ablation studies also determine that our method yields better results than full fine-tuning the entire model. We hypothesize that our findings could stimulate a new optimal method of downstream tuning that combines parameter efficient tuning modules with fine-tuning a subset of the base model&#39;s layers.

EMNLP 2022

Learning Better Intent Representations for Financial Open Intent Classification

partial fine-tuning

open intent detection

prefix tuning

With the recent surge of NLP technologies in the financial domain, banks and other financial entities have adopted virtual agents (VA) to assist customers. A challenging problem for VAs in this domain is determining a user's reason or intent for contacting the VA, especially when the intent was unseen or open during the VA's training. One method for handling open intents is adaptive decision boundary (ADB) post-processing, which learns tight decision boundaries from intent representations to separate known and open intents. We propose incorporating two methods for supervised pre-training of intent representations: prefix tuning and fine-tuning just the last layer of a large language model (LLM). With this proposal, our accuracy is 1.63% - 2.07% higher than the prior state-of-the-art ADB method for open intent classification on the banking77 benchmark amongst others. Notably, we only supplement the original ADB model with 0.1% additional trainable parameters. Ablation studies also determine that our method yields better results than full fine-tuning the entire model. We hypothesize that our findings could stimulate a new optimal method of downstream tuning that combines parameter efficient tuning modules with fine-tuning a subset of the base model's layers.

workshop paper

## 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.

The invention of transformer-based models such as BERT, GPT, and RoBERTa has enabled researchers and financial companies to finetune these powerful models and use them in different downstream tasks to achieve state-of-the-art performance. Recently, a lightweight alternative (approximately 0.1\% - 3\% of the original model parameters) to fine-tuning, known as prefix tuning has been introduced. This method freezes the model parameters and only updates the prefix to achieve performance comparable to full fine-tuning. Prefix tuning enables researchers and financial practitioners to achieve similar results with much fewer parameters. In this paper, we explore the robustness of prefix tuning when facing noisy data. Our experiments demonstrate that fine-tuning is more robust to noise than prefix tuning---the latter method faces a significant decrease in performance on most corrupted data sets with increasing noise levels. Furthermore, prefix tuning has high variances on the F1 scores compared to fine-tuning in many corruption methods. We strongly advocate that caution should be carefully taken when applying the state-of-the-art prefix tuning method to noisy data.

Exploring Robustness of Prefix Tuning in Noisy Data: A Case Study in Financial Sentiment Analysis

Investment management professionals (IMPs) often make decisions after manual analysis of text transcripts of central banks' conferences or companies' earning calls. Their current software tools, while interactive, largely leave users unassisted in using these transcripts.  A key component to designing speech and NLP techniques for this community is to qualitatively characterize their perceptions of AI as well as their legitimate needs so as to (1) better apply existing NLP methods, (2) direct future research and (3) correct IMPs' perceptions of what AI is capable of.  This paper presents such a study, through a contextual inquiry with eleven IMPs, uncovering their information practices when using such transcripts. We then propose a taxonomy of user requirements and usability criteria to support IMP decision making, and validate the taxonomy through participatory design workshops with four IMPs. Our investigation suggests that: (1) IMPs view visualization methods and natural language processing algorithms primarily as time-saving tools that are incapable of enhancing either discovery or interpretation and (2) their existing software falls well short of the state of the art in both visualization and NLP.

A Taxonomical NLP Blueprint to Support Financial Decision Making through Information-Centred Interactions

This report describes our PromptShots submissions to a shared task on Evaluating the Rationales of Amateur Investors (ERAI). We participated in both pairwise comparison and unsupervised ranking tasks. For pairwise comparison, we employed instruction-based models based on T5-small and OpenAI InstructGPT language models. Surprisingly, we observed OpenAI InstructGPT language model few-shot trained on Chinese data works best in our submissions, ranking 3rd on the maximal loss (ML) pairwise accuracy. This model works better than training on the Google translated English data by a large margin, where the English few-shot trained InstructGPT model even performs worse than an instruction-based T5-small model finetuned on the English data. However, all instruction-based submissions do not perform well on the maximal potential profit (MPP) pairwise accuracy where there are more data and learning signals. The Chinese few-shot trained InstructGPT model still performs best in our setting. For unsupervised ranking, we utilized many language models, including many financial-specific ones, and Bayesian lexicons unsupervised-learned on both Chinese and English words using a method-of-moments estimator. All our submissions rank best in the MPP ranking, from 1st to 3rd. However, they all do not perform well for ML scoring. Therefore, both MPP and ML scores need different treatments since we treated MPP and ML using the same formula. Our only difference is the treatment of market sentiment lexicons.

PromptShots at the FinNLP-2022 ERAI Task: Pairwise Comparison and Unsupervised Ranking

Using insights from social media for making investment decisions has become mainstream. However, in the current era of information ex- plosion, it is essential to mine high-quality so- cial media posts. The FinNLP-2022 ERAI task deals with assessing Maximum Possible Profit (MPP) and Maximum Loss (ML) from social me- dia posts relating to finance. In this paper, we present our team LIPI's approach. We ensem- bled a range of Sentence Transformers to quan- tify these posts. Unlike other teams with vary- ing performances across different metrics, our system performs consistently well. Our code is available here  https://github.com/sohomghosh/LIPI_ERAI_ FinNLP_EMNLP- 2022/

LIPI at the FinNLP-2022 ERAI Task: Ensembling Sentence Transformers for Assessing Maximum Possible Profit and Loss from Online Financial Posts

In this paper, we describe our system for the FinNLP-2022 shared task: Evaluating the Rationales of Amateur Investors (ERAI). The ERAI shared tasks focuses on mining profitable information from financial texts by predicting the possible Maximal Potential Profit (MPP) and Maximal Loss (ML) based on the posts from amateur investors. There are two sub-tasks in ERAI: Pairwise Comparison and Unsupervised Rank, both target on the prediction of MPP and ML. To tackle the two tasks, we frame this task as a text-pair classification task where the input consists of two documents and the output is the label of whether the first document will lead to higher MPP or lower ML. Specifically, we propose to take advantage of the transferability of Sentiment Analysis data with an assumption that a more positive text will lead to higher MPP or higher ML to facilitate the prediction of MPP and ML. In experiment on the ERAI blind test set, our systems trained on Sentiment Analysis data and ERAI training data ranked 1st and 8th in ML and MPP pairwise comparison respectively. Code available in this link.

DCU-ML at the FinNLP-2022 ERAI Task: Investigating the Transferability of Sentiment Analysis Data for Evaluating Rationales of Investors

Evaluating the Rationales of Amateur Investors (ERAI) is a task about mining expert-like viewpoints from social media. This paper summarizes our solutions to the ERAI shared task, which is co-located with the FinNLP workshop at EMNLP 2022. There are 2 sub-tasks in ERAI. Sub-task 1 is a pair-wised comparison task, where we propose a BERT-based pre-trained model projecting opinion pairs in a common space for classification. Sub-task 2 is an unsupervised learning task ranking the opinions' maximal potential profit (MPP) and maximal loss (ML), where our model leverages the regression method and multi-layer perceptron to rank the MPP and ML values. The proposed approaches achieve competitive accuracy of 54.02\% on ML Accuracy and 51.72\% on MPP Accuracy for pairwise tasks, also 12.35\% and -9.39\% regression unsupervised ranking task for MPP and ML.

UOA at the FinNLP-2022 ERAI Task: Leveraging the Class Label Description for Financial Opinion Mining

Identifying posts of high financial quality from opinions is of extraordinary significance for investors. Hence, this paper focuses on evaluating the rationales of amateur investors (ERAI) in a shared task, and we present our solutions. The pairwise comparison task aims at extracting the post that will trigger higher MPP and ML values from pairs of posts. The goal of the unsupervised ranking task is to find the top 10\% of posts with higher MPP and ML values. We initially model the shared task as text classification and regression problems. We then propose a multi-learning approach applied by financial domain pre-trained models and multiple linear classifiers for factor combinations to integrate better relationships and information between training data. The official results have proved that our method achieves 48.28\% and 52.87\% for MPP and ML accuracy on pairwise tasks, 14.02\% and -4.17\% regarding unsupervised ranking tasks for MPP and ML. Our source code is  available.

aiML at the FinNLP-2022 ERAI Task: Combining Classification and Regression Tasks for Financial Opinion Mining

The financial reports usually reveal the recent development of the company and often cause the volatility in the company's share price. The opinions causing higher maximal potential profit and lower maximal loss can help the amateur investors choose rational strategies. FinNLP-2022 ERAI task aims to quantify the opinions' potentials of leading higher maximal potential profit and lower maximal loss. In this paper, different strategies were applied to solve the ERAI tasks. Valinna `RoBERTa-wwm' showed excellent performance and helped us rank second in `MPP' label prediction task. After integrating some tricks, the modified `RoBERTa-wwm' outperformed all other models in `ML' ranking task.

Yet at the FinNLP-2022 ERAI Task: Modified models for evaluating the Rationales of Amateur Investors

In this paper, we discuss the various approaches by the \textit{Jetsons} team for the ``Pairwise Comparison'' sub-task of the ERAI shared task to compare financial opinions for profitability and loss. Our BERT-Chinese model considers a pair of opinions and predicts the one with a higher maximum potential profit (MPP) with 62.07\% accuracy. We analyze the performance of our approaches on both the MPP and maximal loss (ML) problems and deeply dive into why BERT-Chinese outperforms other models.

Jetsons at the FinNLP-2022 ERAI Task: BERT-Chinese for mining high MPP posts

In this report, we describe our Transformers for euphemism detection baseline (TEDB) submissions to a shared task on euphemism detection 2022. We cast the task of predicting euphemism as text classification. We considered Transformer-based models which are the current state-of-the-art methods for text classification. We explored different training schemes, pretrained models, and model architectures. Our best result of 0.816 F1-score (0.818 precision and 0.814 recall) consists of a euphemism-detection-finetuned TweetEval/TimeLMs-pretrained RoBERTa model as a feature extractor frontend with a KimCNN classifier backend trained end-to-end using a cosine annealing scheduler. We observed pretrained models on sentiment analysis and offensiveness detection to correlate with more F1-score while pretraining on other tasks, such as sarcasm detection, produces less F1-scores. Also, putting more word vector channels does not improve the performance in our experiments.

Learning Better Intent Representations for Financial Open Intent Classification

Downloads

Next from EMNLP 2022

Exploring Robustness of Prefix Tuning in Noisy Data: A Case Study in Financial Sentiment Analysis

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES