United Arab Emirates

Language models pre-trained on large self-supervised corpora, followed by task-specific fine-tuning has become the dominant paradigm in NLP. These pre-training datasets often have a one-to-many structure---e.g. in dialogue there are many valid responses for a given context. However, only some of these responses will be desirable in our downstream task.  This raises the question of how we should train the model such that it can emulate the desirable behaviours, but not the undesirable ones. Current approaches train in a one-to-one setup---only a single target response is given for a single dialogue context---leading to models only learning to predict the average response, while ignoring the full range of possible responses. Using text-based games as a testbed, our approach, PASA, uses discrete latent variables to capture the range of different behaviours represented in our larger pre-training dataset. We then use knowledge distillation to distil the posterior probability distribution into a student model. This probability distribution is far richer than learning from only the hard targets of the dataset, and thus allows the student model to benefit from the richer range of actions the teacher model has learned. Results show up to 49\% empirical improvement over the previous state-of-the-art model on the Jericho Walkthroughs dataset.

EMNLP 2022

Learn What Is Possible, Then Choose What Is Best: Disentangling One-To-Many Relations in Language Through Text-based Games

one-to-many

text-based games

knowledge distillation

language models

## 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

Large language models can produce fluent dialogue but often hallucinate factual inaccuracies. While retrieval-augmented models help alleviate this issue, they still face a difficult challenge of both reasoning to provide correct knowledge and generating conversation simultaneously. In this work, we propose a modular model, Knowledge to Response (K2R), for incorporating knowledge into conversational agents, which breaks down this problem into two easier steps. K2R first generates a knowledge sequence, given a dialogue context, as an intermediate step. After this "reasoning step", the model then attends to its own generated knowledge sequence, as well as the dialogue context, to produce a final response. In detailed experiments, we find that such a model hallucinates less in knowledge-grounded dialogue tasks,  and has advantages in terms of interpretability and modularity. In particular, it can be used to fuse QA and dialogue systems together to enable dialogue agents to give knowledgeable answers, or QA models to give conversational responses in a zero-shot setting.

Reason first, then respond: Modular Generation for Knowledge-infused Dialogue

Supervised training of existing deep learning models for sequence labeling relies on large scale labeled datasets. Such datasets are generally created with crowd-source labeling. However, crowd-source labeling for tasks of sequence labeling can be expensive and time-consuming. Further, crowd-source labeling by external annotators may not be appropriate for data that contains user private information. Considering the above limitations of crowd-source labeling, we study interactive sequence labeling that allows training directly with the user feedback, which alleviates the annotation cost and maintains the user privacy. We identify two bias, namely, context bias and feedback bias, by formulating interactive sequence labeling via a Structural Causal Model (SCM). To alleviate the context and feedback bias based on the SCM, we identify the frequent context tokens as confounders in the backdoor adjustment and further propose an entropy-based modulation that is inspired by information theory. entities more sample-efficiently. With extensive experiments, we validate that our approach can effectively alleviate the biases and our models can be efficiently learnt  with the user feedback.

Context-aware Information-theoretic Causal De-biasing for Interactive Sequence Labeling

This paper proposes StuBot, a text-based conversational agent that provides adaptive feedback for learning by teaching. StuBot first asks the users to teach the learning content by summarizing and explaining it in their own words. After the users inputted the explanation text for teaching, StuBot uses a machine reading comprehension (MRC) engine to provide adaptive feedback with further questions about the insufficient parts of the explanation text. We conducted a within-subject study to evaluate the effectiveness of adaptive feedback by StuBot. Both the quantitative and qualitative results showed that learning by teaching with adaptive feedback can improve learning performance, immersion, and overall experience.

StuBot: Learning by Teaching a Conversational Agent Through Machine Reading Comprehension

In this article, we explore the potential and challenges of applying transformer-based pre-trained language models (PLMs) and statistical methods to a particularly challenging, yet highly important and largely uncharted domain: normative discussions in tax law research. On our conviction, the role of NLP in this essentially contested territory is to make explicit implicit normative assumptions, and to foster debates across ideological divides. To this goal, we propose the first steps towards a method that automatically labels normative statements in tax law research, and that suggests the normative background of these statements. Our results are encouraging, but it is clear that there is still room for improvement.

On What it Means to Pay Your Fair Share: Towards Automatically Mapping Different Conceptions of Tax Justice in Legal Research Literature

Creating balanced labeled textual corpora for complex tasks, like legal analysis, is a challenging and expensive process that often requires the collaboration of domain experts. To address this problem, we propose a data augmentation method based on the combination of GloVe word embeddings and the WordNet ontology. We present an example of application in the legal domain, specifically on decisions of the Court of Justice of the European Union. Our evaluation with human experts confirms that our method is more robust than the alternatives.

Combining WordNet and Word Embeddings in Data Augmentation for Legal Texts

We propose a 'legal approach' to hate speech detection by operationalization of the decision as to whether a post is subject to criminal law into an NLP task. Comparing existing regulatory regimes for hate speech, we base our investigation on the European Union's framework as it provides a widely applicable legal minimum standard. Accurately deciding whether a post is punishable or not usually requires legal education. We show that, by breaking the legal assessment down into a series of simpler sub-decisions, even laypersons can annotate consistently. Based on a newly annotated dataset, our experiments show that directly learning an automated model of punishable content is challenging. However, learning the two sub-tasks of 'target group' and 'targeting conduct' instead of a holistic, end-to-end approach to the legal assessment yields better results. Overall, our method also provides decisions that are more transparent than those of end-to-end models, which is a crucial point in legal decision-making.

A Legal Approach to Hate Speech – Operationalizing the EU's Legal Framework against the Expression of Hatred as an NLP Task

Verbose and complicated legal terminology in online service terms and conditions (T\&C) means that users typically don't read these documents before accepting the terms of such unilateral service contracts. With such services becoming part of mainstream digital life, highlighting Terms of Service (ToS) clauses that impact on the collection and use of user data and privacy are important concerns. Advances in text summarization can help to create informative and concise summaries of the terms, but existing approaches geared towards news and microblogging corpora are not directly applicable to the ToS domain, which is hindered by a lack of T\&C-relevant resources for training and evaluation. This paper presents a ToS model, developing a hybrid extractive-classifier-abstractive pipeline that highlights the privacy and data collection/use-related sections in a ToS document and paraphrases these into concise and informative sentences. Relying on significantly less training data (4313 training pairs) than previous representative works (287,226 pairs), our model outperforms extractive baselines by at least 50\% in ROUGE-1 score and 54\% in METEOR score. The paper also contributes to existing community efforts by curating a dataset of online service T\&C, through a developed web scraping tool.

Privacy Pitfalls of Online Service Terms and Conditions: a Hybrid Approach for Classification and Summarization

With the legal sector embracing digitization, the increasing availability of information has led to a need for systems that can automatically summarize legal documents. Most existing research on legal text summarization has so far focused on extractive models, which can result in awkward summaries, as sentences in legal documents can be very long and detailed. In this study, we apply two abstractive summarization models on a Dutch legal domain dataset. The results show that existing models transfer quite well across domains and languages: the ROUGE scores of our experiments are comparable to state-of-the-art studies on English news article texts. Examining one of the models showed the capability of rewriting long legal sentences to much shorter ones, using mostly vocabulary from the source document. Human evaluation shows that for both models hand-made summaries are still perceived as more relevant and readable, and automatic summaries do not always capture elements such as background, considerations and judgement. Still, generated summaries are valuable if only a keyword summary or no summary at all is present.

Abstractive Summarization of Dutch Court Verdicts Using Sequence-to-sequence Models

Legalese can often be filled with verbose domain-specific jargon which can make it challenging to understand and use for non-experts. Creating succinct summaries of legal documents often makes it easier for user comprehension. However, obtaining labeled data for every domain of legal text is challenging, which makes cross-domain transferability of text generation models for legal text, an important area of research. In this paper, we explore the ability of existing state-of-the-art T5 \& BART-based summarization models to transfer across legal domains. We leverage publicly available datasets across four domains for this task, one of which is a new resource for summarizing privacy policies, that we curate and release for academic research. Our experiments demonstrate the low cross-domain transferability of these models, while also highlighting the benefits of combining different domains. Further, we compare the effectiveness of standard metrics for this task and illustrate the vast differences in their performance.

Towards Cross-Domain Transferability of Text Generation Models for Legal Text

Seeking legal advice is often expensive. Recent advancements in machine learning for solving complex problems can be leveraged to help make legal services more accessible to the public. However, real-life applications encounter significant challenges. State-of-the-art language models are growing increasingly large, making parameter-efficient learning increasingly important. Unfortunately, parameter-efficient methods perform poorly with small amounts of data, which are common in the legal domain (where data labelling costs are high). To address these challenges, we propose parameter-efficient legal domain adaptation, which uses vast unsupervised legal data from public legal forums to perform legal pre-training. This method exceeds or matches the fewshot performance of existing models such as LEGAL-BERT on various legal tasks while tuning only approximately 0.1\% of model parameters. Additionally, we show that our method can achieve calibration comparable to existing methods across several tasks. To the best of our knowledge, this work is among the first to explore parameter-efficient methods of tuning language models in the legal domain.

Downloads

Next from EMNLP 2022

Reason first, then respond: Modular Generation for Knowledge-infused Dialogue

Similar lecture

Learn What Is Possible, Then Choose What Is Best: Disentangling One-To-Many Relations in Language Through Text-based Games