United Arab Emirates

Encoding both language-specific and language-agnostic information into a single high-dimensional space is a common practice of pre-trained Multi-lingual Language Models (pMLM). Such encoding has been shown to perform effectively on natural language tasks requiring semantics of the whole sentence (e.g., translation). However, its effectiveness appears to be limited on tasks requiring partial information of the utterance (e.g., multi-lingual entity retrieval, template retrieval, and semantic alignment). In this work, a novel Fine-grained Multilingual Disentangled Autoencoder (FMDA) is proposed to disentangle fine-grained semantic information from language-specific information in a multi-lingual setting. FMDA is capable of successfully extracting the disentangled template semantic and residual semantic representations. Experiments conducted on the MASSIVE dataset demonstrate that the disentangled encoding can boost each other during the training, thus consistently outperforming the original pMLM and the strong language disentanglement baseline on monolingual template retrieval and cross-lingual semantic retrieval tasks across multiple languages.

EMNLP 2022

Fine-grained Multi-lingual Disentangled Autoencoder for Language-agnostic Representation Learning

cross-lingual alignment; semantic extraction; multilingual language model

**Welcome to ACL-IJCNLP 2021!**

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP). 

As in previous years, the program of the conference includes a poster session, tutorials, workshops and demonstrations in addition to the main conference.


We were able to keep the registration fees similar to those charged for the virtual ACL 2020. The one fee allows attendance at the main conference and any/all tutorials and workshops. These fees would be $125 Regular Early and $175 Regular Late; $50 Student Early and $75 Student Late. Early registration closes at midnight July 11, 2021 (Eastern Daylight Time).

**Reminder:** It is ACL’s policy that at least one author of each accepted paper (including ACL Finding papers) must register for the conference.

**Reminder2:** Underline site will open closer to the event. If you already registered you will receive access detail

Registration is now open

ACL-IJCNLP 2021

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP).

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.

Token free approaches have been successfully applied to a series of word and span level tasks. In this work, we evaluate a byte-level sequence to sequence model (ByT5) on the 51 languages in the MASSIVE multilingual semantic parsing dataset. We examine multiple experimental settings: (i) zero-shot, (ii) full gold data and (iii) zero-shot with synthetic data. By leveraging a state-of-the-art label projection method for machine translated examples, we are able to reduce the gap in exact match to only 5 points with respect to a model trained on gold data from all the languages. We additionally provide insights on the cross-lingual transfer of ByT5 and show how the model compares with respect to mT5 across all parameter sizes. 

Byte-Level Massively Multilingual Semantic Parsing

Multilingual spoken language understanding (SLU) consists of two sub-tasks, namely intent detection and slot filling. To improve the performance of these two sub-tasks, we propose to use consistency regularization based on a hybrid data augmentation strategy. The consistency regularization enforces the predicted distributions for an example and its semantically equivalent augmentation to be consistent. We conduct experiments on the MASSIVE dataset under both full-dataset and zero-shot settings. Experimental results demonstrate that our proposed method improves the performance on both intent detection and slot filling tasks. Our system ranked 1st in the MMNLU-22 competition under the full-dataset setting.

HIT-SCIR at MMNLU-22: Consistency Regularization for Multilingual Spoken Language Understanding

Cross-lingual phenomena are quite common in informal contexts like social media, where users are likely to mix their native language with English or other languages. However, few studies have focused so far on analyzing cross-lingual interactions in voice-assistant data, which present peculiar features in terms of sentence length, named entities, and use of spoken language. Also, little attention has been posed to European countries, where English is frequently used as a second language. In this paper, we present a large-scale empirical analysis of cross-lingual phenomena (code-mixing, linguistic borrowing, foreign named entities) in the interactions with a large-scale voice assistant in European countries. To do this, we first introduce a general, highly-scalable technique to generate synthetic mixed training data annotated with token-level language labels and we train two neural network models to predict them.  We evaluate the models both on the synthetic dataset and on a real dataset of code-switched utterances, showing that the best performance is obtained by a character convolution based model. The results of the analysis highlight different behaviors between countries, having Italy with the highest ratio of cross-lingual utterances and Spain with a marked preference in keeping Spanish words. Our research, paired to the increase of the cross-lingual phenomena in time, motivates further research in developing multilingual Natural Language Understanding (NLU) models, which can naturally deal with cross-lingual interactions.

Play música alegre: A Large-Scale Empirical Analysis of Cross-Lingual Phenomena in Voice Assistant Interactions

The joint intent classification and slot filling task seeks to detect the intent of an utterance and extract its semantic concepts. In the zero-shot cross-lingual setting, a model is trained on a source language and then transferred to other target languages through multi-lingual representations without additional training data. While prior studies show that pre-trained multilingual sequence-to-sequence (Seq2Seq) models can facilitate zero-shot transfer, there is little understanding on how to design the output template for the joint prediction tasks. In this paper, we examine three aspects of the output template -- (1) label mapping, (2) task dependency, and (3) word order. Experiments on the MASSIVE dataset consisting of 51 languages show that our output template significantly improves the performance of pre-trained cross-lingual language models.

Zero-Shot Cross-Lingual Sequence Tagging as Seq2Seq Generation for Joint Intent Classification and Slot Filling

Voice assistants are becoming central to our lives. The convenience of using voice assistants to do simple tasks has created an industry for voice-enabled devices like TVs, thermostats, air conditioners, etc. It has also improved the quality of life of elders by making the world more accessible. Voice assistants engage in task-oriented dialogues using machine-learned language understanding models. However, training deep-learned models take a lot of training data, which is time-consuming and expensive. Furthermore, it is even more problematic if we want the voice assistant to understand hundreds of languages. In this paper, we present a zero-shot deep learning algorithm that uses only the English part of the Massive dataset and achieves a high level of accuracy across 51 languages. The algorithm uses a delexicalized translation model to generate multilingual data for data augmentation. The training data is further weighted to improve the accuracy of the worst-performing languages. We report on our experiments with code-switching, word order, multilingual ensemble methods, and other techniques and their impact on overall accuracy.

$C5L7$: A Zero-Shot Algorithm for Intent and Slot Detection in Multilingual Task Oriented Languages

We expect to interact with home assistants irrespective of our language. However, scaling the Natural Language Understanding pipeline to multiple languages while keeping the same level of accuracy remains a challenge. In this work, we leverage the inherent multilingual aspect of translation models for the task of multilingual intent classification and slot filling. Our experiments reveal that they work equally well with general-purpose multilingual text-to-text models. Furthermore, their accuracy can be further improved by artificially increasing the size of the training set. Unfortunately, increasing the training set also increases the overlap with the test set, leading to overestimating their true capabilities. As a result, we propose two new evaluation methods capable of accounting for an overlap between the training and test set.

Machine Translation for Multilingual Intent Detection and Slots Filling

The detection of mental health conditions based on an individual's use of language has received considerable attention in the NLP community. However, most work has focused on single-task and single-domain models, limiting the semantic space that they are able to cover and risking significant cross-domain loss. In this paper, we present two approaches towards a unified framework for cross-domain and cross-task learning for the detection of depression, post-traumatic stress disorder and suicide risk across different platforms that further utilizes inductive biases across tasks. Firstly, we develop a lightweight model using a general set of features that sets a new state of the art on several tasks while matching the performance of more complex task- and domain-specific systems on others. We also propose a multi-task approach and further extend our framework to explicitly capture the affective characteristics of someone's language, further consolidating transfer of inductive biases and of shared linguistic characteristics. Finally, we present a novel dynamically adaptive loss weighting approach that allows for more stable learning across imbalanced datasets and better neural generalization performance. Our results demonstrate the effectiveness of our unified framework for mental ill-health detection across a number of diverse English datasets.

A unified framework for cross-domain and cross-task learning of mental health conditions

Detecting "toxic" language in internet content is a pressing social and technical challenge. In this work, we focus on Perspective API from Jigsaw, a state-of-the-art tool that promises to score the "toxicity'' of text, with a recent model update that claims impressive results (Lees et al., 2022). We seek to challenge certain normative claims about toxic language by proposing a new benchmark, Selected Adversarial SemanticS, or SASS. We evaluate Perspective on SASS, and compare to low-effort alternatives, like zero-shot and few-shot GPT-3 prompt models, in binary classification settings. We find that Perspective exhibits troubling shortcomings across a number of our toxicity categories. SASS provides a new tool for evaluating performance on previously undetected toxic language that avoids common normative pitfalls. Our work leads us to emphasize the importance of questioning assumptions made by tools already in deployment for toxicity detection in order to anticipate and prevent disparate harms.

Critical Perspectives: A Benchmark Revealing Pitfalls in PerspectiveAPI

Speech production is nuanced and unique to every individual, but today's Spoken Dialogue Systems (SDSs) are trained to use general speech patterns to successfully improve performance on various evaluation metrics. However, these patterns do not apply to certain user groups - often the very people that can benefit the most from SDSs. For example, people with dementia produce more disfluent speech than the general population. In order to evaluate systems with specific user groups in mind, and to guide the design of such systems to deliver maximum benefit to these users, data must be collected securely. In this short paper we present CVR-SI, a bespoke tool for ethical data collection. Designed for the healthcare domain, we argue that it should also be used in more general settings. We detail how off-the-shelf solutions fail to ensure that sensitive data remains secure and private. We then describe the ethical design and security features of our device, with a full guide on how to build both the hardware and software components of CVR-SI. Our design ensures inclusivity to all researchers in this field, particularly those who are not hardware experts. This guarantees everyone can collect appropriate data for human evaluation ethically, securely, and in a timely manner.

Securely Capturing People's Interactions with Voice Assistants at Home: A Bespoke Tool for Ethical Data Collection

While much attention has been paid to identifying explicit hate speech, implicit hateful expressions that are disguised in coded or indirect language are pervasive and remain a major challenge for existing hate speech detection systems. This paper presents the first attempt to apply Entity Linking (EL) techniques to both explicit and implicit hate speech detection, where we show that such real world knowledge about entity mentions in a text does help models better detect hate speech, and the benefit of adding it into the model is more pronounced when explicit entity triggers (e.g., rally, KKK) are present. We also discuss cases where real world knowledge does not add value to hate speech detection, which provides more insights into understanding and modeling the subtleties of hate speech.

Downloads

Next from EMNLP 2022

Byte-Level Massively Multilingual Semantic Parsing

Similar lecture

Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks