United Arab Emirates

We combine the capacity of sparsely gated Mixture-of-Experts (MoE) with the speed and stability of linear, mixing transformations to design the Sparse Mixer encoder model. Sparse Mixer slightly outperforms BERT on GLUE and SuperGLUE, but more importantly trains 65% faster and runs inference 61% faster. We also present a faster variant, prosaically named Fast Sparse Mixer, that marginally underperforms BERT on SuperGLUE, but trains and runs nearly twice as fast. We justify the design of these two models by carefully ablating through various mixing mechanisms, MoE configurations, and hyperparameters. Sparse Mixer overcomes many of the latency and stability concerns of MoE models and offers the prospect of serving sparse student models, without resorting to distilling them to dense variants.

EMNLP 2022

Sparse Mixers: Combining MoE and Mixing to build a more efficient BERT

effiency

mixing

sparsity

findings / work in progress

## 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.

Commonsense question answering (CQA) aims to choose the correct answers for commonsense questions. Most existing works focus on extracting and reasoning over external knowledge graphs (KG). However, the noise in KG prevents these models from learning effective representations. In this paper, we propose a Knowledge Enhanced Graph Contrastive Learning model (KE-GCL) by incorporating the contextual descriptions of entities and adopting a graph contrastive learning scheme. Specifically, for QA pairs we represent the knowledge from KG and contextual descriptions. Then, the representations of contextual descriptions as context nodes are inserted into KG, forming the knowledge-enhanced graphs.
Moreover, we design a contrastive learning method on graphs. For knowledge-enhanced graphs, we build their augmented views with an adaptive sampling strategy. After that, we reason over graphs to update their representations by scattering edges and aggregating nodes. To further improve GCL, hard graph negatives are chosen based on incorrect answers. Extensive experiments on two benchmark datasets demonstrate the effectiveness of our proposed KE-GCL, which outperforms previous methods consistently.

KE-GCL: Knowledge Enhanced Graph Contrastive Learning for Commonsense Question Answering

The role of the attention mechanism in encoding linguistic knowledge has received special interest in NLP. However, the ability of the attention heads to judge the grammatical acceptability of a sentence has been underexplored. This paper approaches the paradigm of acceptability judgments with topological data analysis (TDA), showing that the geometric properties of the attention graph can be efficiently exploited for two standard practices in linguistics: binary judgments and linguistic minimal pairs. Topological features enhance the BERT-based acceptability classifier scores by $8$\%-$24$\% on \textsc{CoLA} in three languages (English, Italian, and Swedish). By revealing the topological discrepancy between attention maps of minimal pairs, we achieve the human-level performance on the \textsc{BLiMP} benchmark, outperforming nine statistical and Transformer LM baselines. At the same time, TDA provides the foundation for analyzing the linguistic functions of attention heads and interpreting the correspondence between the graph features and grammatical phenomena. We publicly release the code and other materials used in the experiments.

Acceptability Judgements via Examining the Topology of Attention Maps

In simultaneous speech translation (SimulST), finding the best trade-off between high output quality and low latency is a challenging task. To meet the latency constraints posed by different application scenarios, multiple dedicated SimulST models are usually trained and maintained, generating high computational costs. 
In this paper, also motivated by the increased sensitivity towards sustainable AI, we investigate whether a single model trained offline can serve both offline and simultaneous applications under different latency regimes without additional training or adaptation. Experiments on en->{de, es} show that, aside from facilitating the adoption of well-established offline architectures and training strategies without affecting latency, offline training achieves similar or better quality compared to the standard SimulST training protocol, also being competitive with the state-of-the-art system.

Does Simultaneous Speech Translation need Simultaneous Models?

Word translation without parallel corpora has become feasible, rivaling the performance of supervised methods. 
Recent findings have shown the improvement in accuracy and robustness of unsupervised word translation (UWT) by utilizing visual observations, which are universal representations across languages.
Our work investigates the potential of using not only visual observations but also pretrained language-image models for enabling a more efficient and robust UWT. 
We develop a novel UWT method dubbed Word Alignment using Language-Image Pretraining (WALIP), leveraging visual observations via the shared image-text embedding space of CLIPs (Radford et al., 2021). 
WALIP has a two-step procedure. 
First, we retrieve word pairs with high confidences of similarity, computed using our proposed image-based fingerprints, which define the initial pivot for the alignment.
Second, we apply our robust Procrustes algorithm to estimate the linear mapping between two embedding spaces, which iteratively corrects and refines the estimated alignment.
Our extensive experiments show that WALIP improves upon the state-of-the-art performance of bilingual word alignment for a few language pairs across different word embeddings and displays great robustness to the dissimilarity of language pairs or training corpora for two word embeddings.

Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignment

Being able to rank the similarity of short text segments is an interesting bonus feature of neural machine translation. Translation-based similarity measures include direct and pivot translation probability, as well as translation cross-likelihood, which has not been studied so far. We analyze these measures in the common framework of multilingual NMT, releasing the NMTScore library. Compared to baselines such as sentence embeddings, translation-based measures prove competitive in paraphrase identification and are more robust against adversarial or multilingual input, especially if proper normalization is applied. When used for reference-based evaluation of data-to-text generation in 2 tasks and 17 languages, translation-based measures show a relatively high correlation to human judgments.

NMTScore: A Multilingual Analysis of Translation-based Text Similarity Measures

Some claim language models understand us. Others won't hear it. To clarify, I investigate three views of human language understanding: as-mapping, as-reliability and as-representation. I argue that while behavioral reliability is necessary for understanding, internal representations are sufficient; they climb the right hill. I review state-of-the-art language and multi-modal models: they are pragmatically challenged by under-specification of form. I question the Scaling Paradigm: limits on resources may prohibit scaled-up models from approaching understanding. Last, I describe how as-representation advances a science of understanding. We need work which probes model internals, adds more of human language, and measures what models can learn.

Language Models Understand Us, Poorly

Despite their recent popularity and well-known advantages, dense retrievers still lag behind sparse methods such as BM25 in their ability to reliably match salient phrases and rare entities in the query and to generalize to out-of-domain data. It has been argued that this is an inherent limitation of dense models. We rebut this claim by introducing the Salient Phrase Aware Retriever (SPAR), a dense retriever with the lexical matching capacity of a sparse model. We show that a dense Lexical Model Λ can be trained to imitate a sparse one, and SPAR is built by augmenting a standard dense retriever with Λ. Empirically, SPAR shows superior performance on a range of tasks including five question answering datasets, MS MARCO passage retrieval, as well as the EntityQuestions and BEIR benchmarks for out-of-domain evaluation, exceeding the performance of state-of-the-art dense and sparse retrievers. The code and models of SPAR are available at: https://github.com/facebookresearch/dpr-scale/tree/main/spar

Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?

Automatic product attribute value extraction refers to the task of identifying values of an attribute from the product information. Product attributes are essential in improving online shopping experience for customers. Most existing methods focus on extracting attribute values from product title and description.
However, in many real-world applications, a product is usually represented by multiple modalities beyond title and description, such as product specifications, text and visual information from the product image, etc. In this paper, we propose \textsc{SMARTAVE}, a \underline{S}tructure \underline{M}ltimodal tr\underline{A}nsforme\underline{R} for produc\underline{T} \underline{A}ttribute \underline{V}alue \underline{E}xtraction, which jointly encodes the structured product information from multiple modalities. Specifically, in \textsc{SMARTAVE} encoder, we introduce hyper-tokens to represent the modality-level information, and local-tokens to represent the original text and visual inputs. Structured attention patterns are designed among the hyper-tokens and local-tokens for learning effective product representation. The attribute values are then extracted based on the learned embeddings. We conduct extensive experiments on two multimodal product datasets. Experimental results demonstrate the superior performance of the proposed approach over several state-of-the-art methods. Ablation studies validate the effectiveness of the structured attentions in modeling the multimodal product information.

SMARTAVE: Structured Multimodal Transformer for Product Attribute Value Extraction

It is still a pipe dream that personal AI assistants on the phone and AR glasses can assist our daily life in addressing our questions like ``how to adjust the date for this watch?'' and ``how to set its heating duration? (while pointing at an oven)''. The queries used in conventional tasks (i.e. Video Question Answering, Video Retrieval, Moment Localization) are often factoid and based on pure text. In contrast, we present a new task called Task-oriented Question-driven Video Segment Retrieval (TQVSR). Each of our questions is an image-box-text query that focuses on affordance of items in our daily life and expects relevant answer segments to be retrieved from a corpus of instructional video-transcript segments. To support the study of this TQVSR task, we construct a new dataset called AssistSR. We design novel guidelines to create high-quality samples. This dataset contains 3.2k multimodal questions on 1.6k video segments from instructional videos on diverse daily-used items. To address TQVSR, we develop a simple yet effective model called Dual Multimodal Encoders (DME) that significantly outperforms several baseline methods while still having large room for improvement in the future. Moreover, we present detailed ablation analyses. Code and data are available at https://github.com/StanLei52/TQVSR.

AssistSR: Task-oriented Video Segment Retrieval for Personal AI Assistant

Despite the potential of federated learning, it is known to be vulnerable to backdoor attacks. Many robust federated aggregation methods are proposed to reduce the potential backdoor risk. However, they are mainly validated in the CV field. In this paper, we find that NLP backdoors are hard to defend against than CV, and we provide a theoretical analysis that the malicious update detection error probabilities are determined by the relative backdoor strengths. NLP attacks tend to have small relative backdoor strengths, which may result in the failure of robust federated aggregation methods for NLP attacks. Inspired by the theoretical results, we can choose some dimensions with higher backdoor strengths to settle this issue. We propose a novel federated aggregation algorithm, Dim-Krum, for NLP tasks, and experimental results validate its effectiveness.

Sparse Mixers: Combining MoE and Mixing to build a more efficient BERT

Downloads

Next from EMNLP 2022

KE-GCL: Knowledge Enhanced Graph Contrastive Learning for Commonsense Question Answering

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Sparse Mixers: Combining MoE and Mixing to build a more efficient BERT

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from EMNLP 2022

KE-GCL: Knowledge Enhanced Graph Contrastive Learning for Commonsense Question Answering

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads