United Arab Emirates

In this work we analyze the named entity representations learned by Transformer-based language models. We investigate the role entities play in two tasks: a language modeling task, and a sequence classification task. For this purpose we collect a novel news topic classification dataset with 12 topics called RefNews-12. We perform two complementary methods of analysis. First, we use diagnostic models allowing us to quantify to what degree entity information is present in the hidden representations. Second, we perform entity mention substitution to measure how substitute-entities with different properties impact model performance. By controlling for model uncertainty we are able to show that entities are identified, and depending on the task, play a measurable role in the model&#39;s predictions. Additionally, we show that the entities&#39; types alone are not enough to account for this. Finally, we find that the the frequency with which entities occur are important for the masked language modeling task, and that the entities&#39; distributions over topics are important for topic classification.

EMNLP 2022

Probing the representations of named entities in Transformer-based Language Models

refnews-12

substitution

model uncertainty

entity

representation

named entity

language model

transformer

### Welcome to ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics! 
 The conference will be held in Toronto, Canada, July 9-14, 2023. 
Following the succession of the recent conferences in our field, ACL 2023 will adopt a hybrid format.
While the impact of Covid has considerably diminished in terms of traveling, obtaining visas to Canada
entails a very long process. Moreover, the global economic conditions pose challenges for many individuals to travel to conferences. Recognizing these circumstances, we know many participants may not be
able to attend the conference in person. Therefore, we are committed to providing a great virtual platform
so everyone has the opportunity to interact with other participants and enjoy the conference. Based on the
current registered participants, approxiately 30% have chosen to attend the conference virtually. Whether
you join us in person or virtually, we sincerely hope everyone has a remarkable conference experience. 
This General Chair’s message is where I express my gratitude to the many individuals who have made
enormous contributions to the conference over the past year.

Read [**ACL 2023 General Chair's message**](https://docs.google.com/document/d/1WobYM7norbG4dI48s75HfJoD89qgX5a_F-6U8AteLSA/edit?usp=sharing/) in full.

##### **[Conference Handbook](https://2023.aclweb.org/downloads/acl2023-handbook.pdf)**

ACL 2023

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing.

In this work we analyze the named entity representations learned by Transformer-based language models. We investigate the role entities play in two tasks: a language modeling task, and a sequence classification task. For this purpose we collect a novel news topic classification dataset with 12 topics called RefNews-12. We perform two complementary methods of analysis. First, we use diagnostic models allowing us to quantify to what degree entity information is present in the hidden representations. Second, we perform entity mention substitution to measure how substitute-entities with different properties impact model performance. By controlling for model uncertainty we are able to show that entities are identified, and depending on the task, play a measurable role in the model's predictions. Additionally, we show that the entities' types alone are not enough to account for this. Finally, we find that the the frequency with which entities occur are important for the masked language modeling task, and that the entities' distributions over topics are important for topic classification.

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.

In the interest of interpreting neural NLI models and their reasoning strategies, 
we carry out a systematic probing study which investigates whether these models
capture the crucial semantic features central to natural logic: monotonicity and concept inclusion.
Correctly identifying valid inferences in downward-monotone contexts is a known stumbling block for NLI performance,
subsuming linguistic phenomena such as negation scope and generalized quantifiers.
To understand this difficulty, we emphasize monotonicity as a property of a context and examine the extent to which 
models capture relevant monotonicity information in the vector representations which are 
intermediate to their decision making process.
Drawing on the recent advancement of the probing paradigm,
we compare the presence of monotonicity features across various models.
We find that monotonicity information is notably weak in the representations of popular
NLI models which achieve high scores on benchmarks, 
and observe that previous improvements to these models based on fine-tuning strategies 
have introduced stronger monotonicity features together with their improved performance on challenge sets.

Decomposing Natural Logic Inferences for Neural NLI

Improving our understanding of how information is encoded in vector space can yield valuable interpretability insights. Alongside vector dimensions, we argue that it is possible for the vector norm to also carry linguistic information. We develop a method to test this: an extension of the probing framework which allows for relative intrinsic interpretations of probing results. It relies on introducing noise that ablates information encoded in embeddings, grounded in random baselines and confidence intervals. We apply the method to well-established probing tasks and find evidence that confirms the existence of separate information containers in English GloVe and BERT embeddings. Our correlation analysis aligns with the experimental findings that different encoders use the norm to encode different kinds of information: GloVe stores syntactic and sentence length information in the vector norm, while BERT uses it to encode contextual incongruity.

Probing with Noise: Unpicking the Warp and Weft of Embeddings

Extractive question answering (QA) models tend to exploit spurious correlations to make predictions when a training set has unintended biases. This tendency results in models not being generalizable to examples where the correlations do not hold. Determining the spurious correlations QA models can exploit is crucial in building generalizable QA models in real-world applications; moreover, a method needs to be developed that prevents these models from learning the spurious correlations even when a training set is biased. In this study, we discovered that the relative position of an answer, which is defined as the relative distance from an answer span to the closest question-context overlap word, can be exploited by QA models as superficial cues for making predictions. Specifically, we find that when the relative positions in a training set are biased, the performance on examples with relative positions unseen during training is significantly degraded. To mitigate the performance degradation for unseen relative positions, we propose an ensemble-based debiasing method that does not require prior knowledge about the distribution of relative positions. We demonstrate that the proposed method mitigates the models' reliance on relative positions using the biased and full SQuAD dataset. We hope that this study can help enhance the generalization ability of QA models in real-world applications.

Look to the Right: Mitigating Relative Position Bias in Extractive Question Answering

Language models suffer from various degenerate behaviors. These differ between tasks: machine translation (MT) exhibits length bias, while tasks like story generation exhibit excessive repetition. Recent work has attributed the difference to task constrainedness, but evidence for this claim has always involved many confounding variables. To study this question directly, we introduce a new experimental framework that allows us to smoothly vary task constrainedness, from MT at one end to fully open-ended generation at the other, while keeping all other aspects fixed. We find that: (1) repetition decreases smoothly with constrainedness, explaining the difference in repetition across tasks; (2) length bias surprisingly also decreases with constrainedness, suggesting some other cause for the difference in length bias; (3) across the board, these problems affect the mode, not the whole distribution; (4) the differences cannot be attributed to a change in the entropy of the distribution, since another method of changing the entropy, label smoothing, does not produce the same effect.

A Continuum of Generation Tasks for Investigating Length Bias and Degenerate Repetition

Linguistic analysis of language models is one of the ways to explain and describe their reasoning, weaknesses, and limitations. 
In the probing part of the model interpretability research, studies concern individual languages as well as individual linguistic structures. 
The question arises: are the detected regularities linguistically coherent, or on the contrary, do they dissonate at the typological scale? Moreover, the majority of studies address the inherent set of languages and linguistic structures, leaving the actual typological diversity knowledge out of scope.
In this paper, we present and apply the GUI-assisted framework allowing us to easily probe massive amounts of languages for all the morphosyntactic features present in the Universal Dependencies data. We show that reflecting the anglo-centric trend in NLP over the past years, most of the regularities revealed in the mBERT model are typical for the western-European languages. 
Our framework can be integrated with the existing probing toolboxes, model cards, and leaderboards, allowing practitioners to use and share their familiar probing methods to interpret multilingual models.
Thus we propose a toolkit to systematize the multilingual flaws in multilingual models, providing a reproducible experimental setup for 104 languages and 80 morphosyntactic features.

Universal and Independent: Multilingual Probing Framework for Exhaustive Model Interpretation and Evaluation

We study whether linguistic knowledge is a necessary condition for the good performance of modern language models, which we call the rediscovery hypothesis. First, we show that language models that are significantly compressed but perform well on their pretraining objectives retain good scores when probed for linguistic structures. This result supports the rediscovery hypothesis and leads to the second contribution of our paper: an information-theoretic framework that relates language modeling objectives with linguistic information.

The Rediscovery Hypothesis: Language Models Need to Meet Linguistics

In this paper, we set out to quantify the syntactic capacity of BERT in the evaluation regime of non-context free patterns, as occurring in Dutch. We devise a test suite based on a mildly context-sensitive formalism, from which we derive grammars that capture the linguistic phenomena of control verb nesting and verb raising. The grammars, paired with a small lexicon, provide us with a large collection of naturalistic utterances, annotated with verb-subject pairings, that serve as the evaluation test bed for an attention-based span selection probe. Our results, backed by extensive analysis, suggest that the models investigated fail in the implicit acquisition of the dependencies examined.

Discontinuous Constituency and BERT: A Case Study of Dutch

Garden path sentences (i.e. “the horse raced past the barn fell”) are sentences that readers initially incorrectly parse, requiring partial or total re-analysis of the sentence structure. Given human difficulty in parsing garden paths, we aim to compare transformer language models' performance on these sentences. We assess a BERT question-answering model's performance on comprehension questions based on garden path and control sentences. We then further investigate the semantic roles assigned to arguments of verbs in garden path and control sentences by utilizing a probe task to directly assess which semantic role(s) BERT assigns. We find that BERT has relatively low performance in question answering based on garden path contexts, and the model incorrectly assigns semantic roles, aligning for the most part with human performance.

The BERT Walked Down the Garden Path Assigned Semantic Roles

Understanding Transformer-based models has attracted significant attention, as they lie at the heart of recent technological advances across machine learning.
While most interpretability methods rely on running models over inputs, recent work has shown that a zero-pass approach, where parameters are interpreted directly without a forward/backward pass is feasible for \emph{some} Transformer parameters, and for two-layer attention networks.
In this work, we present a theoretical analysis where \emph{all} parameters of a trained Transformer are interpreted by projecting them into the \emph{embedding space}, that is, the space of vocabulary items they operate on.
We derive a simple theoretical framework to support our arguments and provide ample evidence for its validity. First, an empirical analysis showing that parameters of both pretrained and fine-tuned models can be interpreted in embedding space. Second, we present two applications of our framework: (a) aligning the parameters of different models that share a vocabulary, and (b) constructing a classifier \emph{without training} by
``translating'' the parameters of a fine-tuned classifier to parameters of a different model that was only pretrained. Overall, our findings open the door 
to interpretation methods that, at least in part, abstract away from model specifics and operate in the embedding space only.

Analyzing Transformers in Embedding Space

We study feature interactions in the context of feature attribution methods for post-hoc interpretability. 
Feature interactions are a mixed blessing: on the one hand, the ability to deal with interacting features is  seen as key to the success of neural networks in modern AI, allowing a model to build up hierarchical representations for its input. 
On the other hand, uncovering what exact role these interactions play in the decision making process of a model is challenging, leading to a diverse range of interaction attribution methods being proposed. 
In this paper, we introduce a unified framework that allows for direct comparison of these varied methods. Our framework is based on the `Explaining by Removing' framework of Covert et al. (2021) for feature attributions, and generalises it to feature interactions. To evaluate the faithfulness of methods for detecting feature interactions, we work out a grey box methodology, where we train deep learning models to perfection on a formal language classification task, using PCFGs. We show that under specific configurations, some interaction attribution methods are indeed able to uncover the grammatical rules acquired by a model. Our framework, and empirical results, thus provide a sound basis for comparing and extending methods for detecting feature interactions.

Downloads

Next from EMNLP 2022

Decomposing Natural Logic Inferences for Neural NLI

Similar lecture

Geometric Locality of Entity Embeddings in Masked Language Models

.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

Decomposing Natural Logic Inferences for Neural NLI

Similar lecture

Geometric Locality of Entity Embeddings in Masked Language Models

Downloads