Canada

By scaling the model size, large pre-trained language models~(PLMs) have shown remarkable performance in various natural language processing tasks, mostly outperforming small PLMs by a large margin.However, due to the high computational cost, the huge number of parameters also restricts the applicability of large PLMs in real-world systems. In this paper, we focus on scaling up the parameters of PLMs \emph{only during} fine-tuning, to benefit from the over-parameterization, while without increasing \emph{the inference latency}. Given a relatively small PLM, we over-parameterize it by employing a matrix product operator, an efficient and almost lossless decomposition method to factorize its contained parameter matrices into a set of higher-dimensional tensors.Considering the efficiency, we further propose both static and dynamic strategies to select the most important parameter matrices for over-parameterization.Extensive experiments have demonstrated that our approach can significantly boost the fine-tuning performance of small PLMs and even help small PLMs outperform $3\times$ parameterized larger ones.Our code is publicly available at \url{https://github.com/zfgao66/OPF}.

&lt;iframe src=&quot;https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/9782798c-2a37-4e66-88f2-5aef2da37244&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

Small Pre-trained Language Models Can be Fine-tuned as Large Models via Over-Parameterization

over-parameterization

matrix decomposition

pre-trained language models

## Welcome to NAACL 2022!
The Annual Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL) is taking place July 10-15, 2022 as a hybrid event, in Seattle, WA and online. We are happy to welcome all of you to conference!  
<br><br>
The main conference program features oral presentations, in-person and virtual posters and demo sessions, a plenary session for our best paper presentations and awards, keynote presentations, a plenary panel on the place of linguistics and symbolic structures in NLP, and an Industrial Track panel on Careers in NLP.
<br><br>
Posters (including Findings of NAACL 2022) and demos are grouped by areas for both the in-person and the virtual sessions. For the virtual component, the talks will be on Zoom and the posters and the demos will be in GatherTown. The Student Research Workshop and will have an oral session and a poster session.
<br><br>
The program also features 6 Tutorials and 26 Workshops.
<br><br>
 We wish you a wonderful conference!
<br><br>
[The NAACL 2022 Organizing Committee](https://2022.naacl.org/committees/organization/)

NAACL 2022

2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics

By scaling the model size, large pre-trained language models~(PLMs) have shown remarkable performance in various natural language processing tasks, mostly outperforming small PLMs by a large margin.However, due to the high computational cost, the huge number of parameters also restricts the applicability of large PLMs in real-world systems. In this paper, we focus on scaling up the parameters of PLMs \emph{only during} fine-tuning, to benefit from the over-parameterization, while without increasing \emph{the inference latency}. Given a relatively small PLM, we over-parameterize it by employing a matrix product operator, an efficient and almost lossless decomposition method to factorize its contained parameter matrices into a set of higher-dimensional tensors.Considering the efficiency, we further propose both static and dynamic strategies to select the most important parameter matrices for over-parameterization.Extensive experiments have demonstrated that our approach can significantly boost the fine-tuning performance of small PLMs and even help small PLMs outperform $3\times$ parameterized larger ones.Our code is publicly available at \url{https://github.com/zfgao66/OPF}.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/9782798c-2a37-4e66-88f2-5aef2da37244" width="300" height="400"></iframe>

technical paper

### Welcome to ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics! 
<br>The conference will be held in Toronto, Canada, July 9-14, 2023.<br><br>
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.<br>
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)**
<br><br><br><br>

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.

Despite increasing interest in the automatic detection of media frames in NLP, the problem is typically simplified as single-label classification and adopts a topic-like view on frames, evading modelling the broader document-level narrative. In this work, we revisit a widely used conceptualization of framing from the communication sciences which explicitly captures elements of narratives, including conflict and its resolution, and integrate it with the narrative framing of key entities in the story as heroes, victims or villains. We adapt an effective annotation paradigm that breaks a complex annotation task into a series of simpler binary questions, and present an annotated data set of English news articles, and a case study on the framing of climate change in articles from news outlets across the political spectrum. Finally, we explore automatic multi-label prediction of our frames with supervised and semi-supervised approaches, and present a novel retrieval-based method which is both effective and transparent in its predictions. We conclude with a discussion of opportunities and challenges for future work on document-level models of narrative framing.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/115410da-044e-4d5c-936e-851d6c9c8f56" width="300" height="400"></iframe>

Conflicts, Villains, Resolutions: Towards models of Narrative Media Framing

Feature attribution methods (FAs) are popular approaches for providing insights into the model reasoning process of making predictions. The more faithful a FA is, the more accurately it reflects which parts of the input are more important for the prediction. Widely used faithfulness metrics, such as sufficiency and comprehensiveness use a hard erasure criterion, i.e. entirely removing or retaining the top most important tokens ranked by a given FA and observing the changes in predictive likelihood. However, this hard criterion ignores the importance of each individual token, treating them all equally for computing sufficiency and comprehensiveness. In this paper, we propose a simple yet effective soft erasure criterion. Instead of entirely removing or retaining tokens from the input, we randomly mask parts of the token vector representations proportionately to their FA importance. Extensive experiments across various natural language processing tasks and different FAs show that our soft-sufficiency and soft-comprehensiveness metrics consistently prefer more faithful explanations compared to hard sufficiency and comprehensiveness.

<iframe src="https://app.sli.do/event/oApzFnCrRo86e5qieE2QHQ/embed/polls/5a3ef18e-b39a-45bd-9997-e6d14f01dbe7" width="300" height="400"></iframe>

Incorporating Attribution Importance for Improving Faithfulness Metrics

Addressing the issues of who saying what to whom in multi-party conversations (MPCs) has recently attracted a lot of research attention. However, existing methods on MPC understanding typically embed interlocutors and utterances into sequential information flows, or utilize only the superficial of inherent graph structures in MPCs. To this end, we present a plug-and-play and lightweight method named graph-induced fine-tuning (GIFT) which can adapt various Transformer-based pre-trained language models (PLMs) for universal MPC understanding. In detail, the full and equivalent connections among utterances in regular Transformer ignore the sparse but distinctive dependency of an utterance on another in MPCs. To distinguish different relationships between utterances, four types of edges are designed to integrate graph-induced signals into attention mechanisms to refine PLMs originally designed for processing sequential texts. We evaluate GIFT by implementing it into three PLMs, and test the performance on three downstream tasks including addressee recognition, speaker identification and response selection. Experimental results show that GIFT can significantly improve the performance of three PLMs on three downstream tasks and two benchmarks with only 4 additional parameters per encoding layer, achieving new state-of-the-art performance on MPC understanding.

<iframe src="https://app.sli.do/event/oApzFnCrRo86e5qieE2QHQ/embed/polls/daf99da1-ba2e-4953-b47c-fd07a9c1ed6a" width="300" height="400"></iframe>

GIFT: Graph-Induced Fine-Tuning for Multi-Party Conversation Understanding

We introduce a new proxy score for evaluating bitext mining based on similarity in a multilingual embedding space: xsim++. In comparison to xsim, this improved proxy leverages rule-based approaches to extend English sentences in any evaluation set with synthetic, hard-to-distinguish examples which more closely mirror the scenarios we encounter during large-scale mining. We validate this proxy by running a significant number of bitext mining experiments for a set of low-resource languages, and subsequently train NMT systems on the mined data. In comparison to xsim, we show that xsim++ is better correlated with the downstream BLEU scores of translation systems trained on mined bitexts, providing a reliable proxy of bitext mining performance without needing to run expensive bitext mining pipelines. xsim++ also reports performance for different error types, offering more fine-grained feedbacks for model development.

<iframe src="https://app.sli.do/event/t38CPUax2NoHBQcXN6okdA/embed/polls/61672226-98d5-40e8-b320-ca021192fc91" width="300" height="400"></iframe>

xSIM++: An Improved Proxy to Bitext Mining Performance for Low-Resource Languages

We introduce a novel dependency parser, the hexatagger, that constructs dependency trees by tagging the words in a sentence with elements from a finite set of possible tags. In contrast to many approaches to dependency parsing, our approach is fully parallelizable at training time, i.e., the structure-building actions needed to build a dependency parse can be predicted in parallel to each other. Additionally, exact decoding is linear in time and space complexity. Furthermore, we derive a probabilistic dependency parser that predicts hexatags using no more than a linear model with features from a pretrained language model, i.e., we forsake a bespoke architecture explicitly designed for the task. Despite the generality and simplicity of our approach, we achieve state-of-the-art performance of 96.4 LAS and 97.4 UAS on the Penn Treebank test set. Additionally, our parser's linear time complexity and parallelism significantly improve computational efficiency, with a roughly 10-times speed-up over previous state-of-the-art models during decoding.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/2d3c6c31-5587-4246-a658-dc5d9a031067" width="300" height="400"></iframe>

Hexatagging: Projective Dependency Parsing as Tagging

The NLP community has mainly focused on scaling Large Language Models (LLMs) vertically, i.e., making them better for about 100 languages. We instead scale LLMs horizontally: we create, through continued pretraining, Glot500-m, an LLM that covers 511 predominantly low-resource languages. An important part of this effort is to collect and clean Glot500-c, a corpus that covers these 511 languages and allows us to train Glot500-m. We evaluate Glot500-m on five diverse tasks across these languages. We observe large improvements for both high-resource and low-resource languages compared to an XLM-R baseline. Our analysis shows that no single factor explains the quality of multilingual LLM representations. Rather, a combination of factors determines quality including corpus size, script, "help from related languages and the total capacity of the model. Our work addresses an important goal of NLP research: we should notlimit NLP to a small fraction of the world's languages and instead strive to support as many languages as possible to bring the benefits of NLP technology to all languages and cultures. Code, data and models are available at https://github.com/cisnlp/Glot500.

<iframe src="https://app.sli.do/event/6qSnTPZvioRLfFJpZUjhCw/embed/polls/91e37030-46eb-45c7-84e9-0ced5cc63a58" width="300" height="400"></iframe>

Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages

Captions that describe or explain charts help improve recall and comprehension of the depicted data and provide a more accessible medium for people with visual disabilities. However, current approaches for automatically generating such captions struggle to articulate the perceptual or cognitive features that are the hallmark of charts (e.g., complex trends and patterns). In response, we introduce VisText: a dataset of 12,441 pairs of charts and captions that describe the charts' construction, report key statistics, and identify perceptual and cognitive phenomena. In VisText, a chart is available as three representations: a rasterized image, a backing data table, and a \textit{scene graph}\,---\,a hierarchical representation of a chart's visual elements akin to a web page's Document Object Model (DOM). To evaluate the impact of VisText, we fine-tune state-of-the-art language models on our chart captioning task and apply prefix-tuning to produce captions that vary the semantic content they convey. Our models generate coherent, semantically rich captions and perform on par with state-of-the-art chart captioning models across machine translation and text generation metrics. Through qualitative analysis, we identify six broad categories of errors that our models make that can inform future work.

<iframe src="https://app.sli.do/event/6qSnTPZvioRLfFJpZUjhCw/embed/polls/39fe060b-64fd-48c9-8a81-0a562c455e2c" width="300" height="400"></iframe>

VisText: A Benchmark for Semantically Rich Chart Captioning

The wide accessibility of social media has provided linguistically under-represented communities with an extraordinary opportunity to create content in their native languages. This, however, comes with certain challenges in script normalization, particularly where the speakers of a language in a bilingual community rely on another script or orthography to write their native language. This paper addresses the problem of script normalization for several such languages that are mainly written in a Perso-Arabic script. Using synthetic data with various levels of noise and a transformer-based model, we demonstrate that the problem can be effectively remediated. We conduct a small-scale evaluation of real data as well. Our experiments indicate that script normalization is also beneficial to improve the performance of downstream tasks such as machine translation and language identification.

<iframe src="https://app.sli.do/event/6qSnTPZvioRLfFJpZUjhCw/embed/polls/8b9224c6-170f-4601-8e7b-828bd18f0ad9" width="300" height="400"></iframe>

Script Normalization for Unconventional Writing of Under-Resourced Languages in Bilingual Communities

Due to the huge amount of parameters, finetuning of pretrained language models (PLMs) is prone to overfitting in the low resource scenarios. In this work, we present a novel method that operates on the hidden representations of a PLM to reduce overfitting. During fine-tuning, our method inserts random autoencoders between the hidden layers of a PLM, which transform activations from the previous layers into multi-view compressed representations before feeding them into the upper layers. The autoencoders are plugged out after fine-tuning, so our method does not add extra parameters or increase computation cost during inference. Our method demonstrates promising performance improvement across a wide range of sequence- and token-level lowresource NLP tasks.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/9890d1ef-3b05-49fd-8f69-d2e33eaaff3b" width="300" height="400"></iframe>

Towards Robust Low-Resource Fine-Tuning with Multi-View Compressed Representations

Identifying those at risk for depression is a crucial issue and social media provides an excellent platform for examining the linguistic patterns of depressed individuals. A significant challenge in depression classification problem is ensuring that prediction models are not overly dependent on topic keywords (i.e., depression keywords) such that it fails to predict when such keywords are unavailable. One promising approach is masking—that is, by selectively masking various words and asking the model to predict the masked words, the model is forced to learn the inherent language patterns of depression. This study evaluates seven masking techniques. Moreover, predicting the masked words during pre-training or fine-tuning phase was also examined. Last, six class imbalance ratios were compared to determine the robustness of masked word selection methods. Key findings demonstrate that selective masking outperforms random masking in terms of F1-score. The most accurate and robust models are identified. Our research also indicates that reconstructing the masked words during the pre-training phase is more advantageous than during the fine-tuning phase. Further discussion and implications are discussed. This is the first study to comprehensively compare masked word selection methods, which has broad implications for the field of depression classification and general NLP. Our code can be found at: https://github.com/chanapapan/Depression-Detection.

Downloads

Next from ACL 2023

Conflicts, Villains, Resolutions: Towards models of Narrative Media Framing

Similar lecture

ElitePLM: An Empirical Study on General Language Ability Evaluation of Pretrained Language Models