United Arab Emirates

Data artifacts incentivize machine learning models to learn non-transferable generalizations by taking advantage of shortcuts in the data, and
there is growing evidence that data artifacts play a role for the strong results that 
deep learning models achieve in recent natural language processing benchmarks.
In this paper, we focus on task-oriented dialogue and investigate whether popular 
datasets such as MultiWOZ contain such data artifacts.
We found that by only keeping frequent phrases in the training
examples, state-of-the-art models perform similarly compared 
to the variant trained with full data, suggesting 
they exploit these spurious correlations
to solve the task. Motivated by this, we propose 
a contrastive learning based framework to encourage the model 
to ignore these cues and focus on learning generalisable patterns. We also experiment with adversarial filtering to remove easy training instances so that the model would focus on learning from the harder instances. We conduct a number of generalization
experiments --- e.g., cross-domain/dataset and adversarial tests --- to assess the robustness of our approach and found that it works exceptionally well.

EMNLP 2022

Robust Task-Oriented Dialogue Generation with Contrastive Pre-training and Adversarial Filtering

contrastive learning

dialogue systems

robustness

## 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.

findings / work in progress

Task-Oriented Dialogue (TOD) systems are drawing more and more attention in recent studies.
Current methods focus on constructing pre-trained models or fine-tuning strategies while the evaluation of TOD is limited by a policy mismatch problem.
That is, during evaluation, the user utterances are from the annotated dataset while these utterances should interact with previous responses which can have many alternatives besides annotated texts.
Therefore, in this work, we propose an interactive evaluation framework for TOD. 
We first build a goal-oriented user simulator based on pre-trained models and then use the user simulator to interact with the dialogue system to generate dialogues.
Besides, we introduce a sentence-level and a session-level score to measure the sentence fluency and session coherence in the interactive evaluation. 
Experimental results show that RL-based TOD systems trained by our proposed user simulator can achieve nearly 98\% inform and success rates in the interactive evaluation of MultiWOZ dataset and the proposed scores measure the response quality besides the inform and success rates.
We are hoping that our work will encourage simulator-based interactive evaluations in the TOD task.

Is MultiWOZ a Solved Task? An Interactive TOD Evaluation Framework with User Simulator

The Annals of Joseon Dynasty (AJD) contain the daily records of the Kings of Joseon, the 500-year kingdom preceding the modern nation of Korea.
The Annals were originally written in an archaic Korean writing system, `Hanja', and were translated into Korean from 1968 to 1993.
The resulting translation was however too literal and contained many archaic Korean words; thus, a new expert translation effort began in 2012. Since then, the records of only one king have been completed in a decade.
In parallel, expert translators are working on English translation, also at a slow pace and produced only one king's records in English so far.
Thus, we propose H2KE, a neural machine translation model, that translates historical documents in Hanja to more easily understandable Korean and to English.
Built on top of multilingual neural machine translation, H2KE learns to translate a historical document written in Hanja, from both a full dataset of outdated Korean translation and a small dataset of more recently translated contemporary Korean and English.
We compare our method against two baselines:
a recent model that simultaneously learns to restore and translate Hanja historical document
and a Transformer based model trained only on newly translated corpora.
The experiments reveal that our method significantly outperforms the baselines in terms of BLEU scores for both contemporary Korean and English translations.
We further conduct extensive human evaluation which shows that our translation is preferred over the original expert translations by both experts and non-expert Korean speakers.

Translating Hanja Historical Documents to Contemporary Korean and English

Compositional image retrieval (CIR) is a challenging retrieval task, where the query is composed of a reference image and a modification text, and the target is another image reflecting the modification to the reference image. Due to the great success of the pre-trained vision-and-language model CLIP and its favorable applicability to large-scale retrieval tasks, we propose a CIR model HyCoLe-HNM with CLIP as the backbone. In HyCoLe-HNM, we follow the contrastive pre-training method of CLIP to perform cross-modal representation learning. On this basis, we propose a hybrid compositional learning mechanism, which includes both image compositional learning and text compositional learning. In hybrid compositional learning, we borrow a gated fusion mechanism from a question answering model to perform compositional fusion, and propose a heuristic negative mining method to filter negative samples. Privileged information in the form of image-related texts is utilized in cross-modal representation learning and hybrid compositional learning. Experimental results show that HyCoLe-HNM achieves state-of-the-art performance on three CIR datasets, namely FashionIQ, Fashion200K, and MIT-States.

Exploring Compositional Image Retrieval with Hybrid Compositional Learning and Heuristic Negative Mining

While Transformer-based language models are generally very robust to pruning, there is the recently discovered outlier phenomenon: disabling only 48 out of 110M parameters in BERT-base drops its performance by nearly 30% on MNLI. We replicate the original evidence for the outlier phenomenon and we link it to the geometry of the embedding space. We find that in both BERT and RoBERTa the magnitude of hidden state coefficients corresponding to outlier dimensions correlate with the frequencies of encoded tokens in pre-training data, and they also contribute to the "vertical" self-attention pattern enabling the model to focus on the special tokens. This explains the drop in performance from disabling the outliers, and it suggests that to decrease anisotopicity in future models we need pre-training schemas that would better take into account the skewed token distributions.

Outlier Dimensions that Disrupt Transformers are Driven by Frequency

Modal verbs (e.g., can, should or must) occur highly frequently in scientific articles. Decoding their function is not straightforward: they are often used for hedging, but they may also denote abilities and restrictions. Understanding their meaning is important for accurate information extraction from scientific text.

To foster research on the usage of modals in this genre, we introduce the MIST (Modals In Scientific Text) dataset, which contains 3737 modal instances in five scientific domains annotated for their semantic, pragmatic, or rhetorical function. We systematically evaluate a set of competitive neural architectures on MIST. Transfer experiments reveal that leveraging non-scientific data is of limited benefit for modeling the distinctions in MIST. Our corpus analysis provides evidence that scientific communities differ in their usage of modal verbs, yet, classifiers trained on scientific data generalize to some extent to unseen scientific domains.

MiST: a Large-Scale Annotated Resource and Neural Models for Functions of Modal Verbs in English Scientific Text

In this work, we present a model for document-grounded response generation in dialog that is decomposed into two components according to Bayes' theorem.
One component is a traditional ungrounded response generation model and the other component models the reconstruction of the grounding document based on the dialog context and generated response.
We propose different approximate decoding schemes and evaluate our approach on multiple open-domain and task-oriented document-grounded dialog datasets.
Our experiments show that the model is more factual in terms of automatic factuality metrics than the baseline model.
Furthermore, we outline how introducing scaling factors between the components allows for controlling the tradeoff between factuality and fluency in the model output.
Finally, we compare our approach to a recently proposed method to control factuality in grounded dialog, CTRL (Rashkin et al., 2021), and show that both approaches can be combined to achieve additional improvements.

Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Model

Contrastive explanation methods go beyond transparency and address the contrastive aspect of explanations. Such explanations are emerging as an attractive option to provide actionable change to scenarios adversely impacted by classifiers' decisions. However, their extension to textual data is under-explored and there is little investigation on their vulnerabilities and limitations. 

This work motivates textual counterfactuals by highlighting the social limitations of non-contrastive explainability. We also lay the ground for a novel evaluation scheme inspired by the faithfulness of explanations. Accordingly, we extend the computation of three metrics, proximity, connectedness and stability, to textual data and we benchmark two successful contrastive methods, POLYJUICE and MiCE, on our suggested metrics. Experiments on sentiment analysis data show that the connectedness of counterfactuals to their original counterparts is not obvious in both models. More interestingly, the generated contrastive texts are more attainable with POLYJUICE which highlights the significance of latent representations in counterfactual search. Finally, we perform the first semantic adversarial attack on textual recourse methods. The results demonstrate the robustness of POLYJUICE and the role that latent input representations play in robustness and reliability.

Beyond Model Interpretability: On the Faithfulness and Adversarial Robustness of Contrastive Textual Explanations

The attention mechanism is considered the backbone of the widely-used Transformer architecture. It contextualizes the input by computing input-specific attention matrices. We find that this mechanism, while powerful and elegant, is not as important as typically thought for pretrained language models. We introduce PAPA, a new probing method that replaces the input-dependent attention matrices with constant ones---the average attention weights over multiple inputs. We use PAPA to analyze several established pretrained Transformers on six downstream tasks. We find that without any input-dependent attention, all models achieve competitive performance---an average relative drop of only 8% from the probing baseline. Further, little or no performance drop is observed when replacing half of the input-dependent attention matrices with constant (input-independent) ones. Interestingly, we show that better-performing models lose more from applying our method than weaker models, suggesting that the utilization of the input-dependent attention mechanism might be a factor in their success. Our results motivate research on simpler alternatives to input-dependent attention, as well as on methods for better utilization of this mechanism in the Transformer architecture.

How Much Does Attention Actually Attend? Questioning the Importance of Attention in Pretrained Transformers

A number of knowledge integration (KI) methods have recently been proposed to incorporate external knowledge into pretrained language models (LMs). Even though knowledge-enhanced LMs (KELMs) outperform base LMs on knowledge-intensive tasks, the inner-workings of these KI methods are not well-understood. For instance, it is unclear which knowledge is effectively integrated into KELMs and which is not; and if such integration led to catastrophic forgetting of already learned knowledge. We show that existing model interpretation methods such as linear probes and prompts have some key limitations in answering these questions. Then, we revisit KI from an information-theoretic view and propose a new theoretically sound probe model called Graph Convolution Simulator (GCS) for KI interpretation. GCS is eventually quite simple -- it uses graph attention on the corresponding knowledge graph for interpretation.
We conduct various experiments to verify that GCS provides reasonable interpretation results for two well-known KELMs: ERNIE and K-Adapter. Our experiments reveal that only little knowledge is successfully integrated in these models, and simply increasing the size of the KI corpus may not lead to better KELMs.

What Has Been Enhanced in my Knowledge-Enhanced Language Model?

This work introduces BioLORD, a new pre-training strategy for producing meaningful representations for clinical sentences and biomedical concepts. State-of-the-art methodologies operate by maximizing the similarity in representation of names referring to the same concept, and preventing collapse through contrastive learning. However, because biomedical names are not always self-explanatory, it sometimes results in non-semantic representations. BioLORD overcomes this issue by grounding its concept representations using definitions, as well as short descriptions derived from a multi-relational knowledge graph consisting of biomedical ontologies. Thanks to this grounding, our model produces more semantic concept representations that match more closely the hierarchical structure of ontologies. BioLORD establishes a new state of the art for text similarity on both clinical sentences (MedSTS) and biomedical concepts (MayoSRS).

Downloads

Next from EMNLP 2022

Is MultiWOZ a Solved Task? An Interactive TOD Evaluation Framework with User Simulator

Similar lecture

Robust Task-Oriented Dialogue Generation with Contrastive Pre-training and Adversarial Filtering