United States

A trending paradigm for multiple-choice question answering (MCQA) is using a text-to-text framework. By unifying data in different tasks into a single text-to-text format, it trains a generative encoder-decoder model which is both powerful and universal. However, a side effect of twisting a generation target to fit the classification nature of MCQA is the underutilization of the decoder and the knowledge that can be decoded. To exploit the generation capability and underlying knowledge of a pre-trained encoder-decoder model, in this paper, we propose a generationenhanced MCQA model named GenMC. It generates a clue from the question and then leverages the clue to enhance a reader for MCQA. It outperforms text-to-text models on multiple MCQA datasets.


NAACL 2022

Clues Before Answers: Generation-Enhanced Multiple-Choice QA

text-to-text

encoder-decoder

question answering

generation

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

ACL 2025

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

technical paper

## 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! 
 
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.
 
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.
 
The program also features 6 Tutorials and 26 Workshops.
 
 We wish you a wonderful conference!
 
[The NAACL 2022 Organizing Committee](https://2022.naacl.org/committees/organization/)

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

Causal inference methods that control for text-based confounders are becoming increasingly important in the social sciences and other disciplines where text is readily available. However, these methods rely on a critical assumption that there is no treatment leakage: that is, the text only contains information about the confounder and no information about treatment assignment. When this assumption does not hold, methods that control for text to adjust for confounders face the problem of post-treatment (collider) bias. However, the assumption that there is no treatment leakage may be unrealistic in real-world situations involving text, as human language is rich and flexible. Language appearing in a public policy document or health records may refer to the future and the past simultaneously, and thereby reveal information about the treatment assignment.

In this article, we define the treatment-leakage problem, and discuss the identification as well as the estimation challenges it raises. Second, we delineate the conditions under which leakage can be addressed by removing the treatment-related signal from the text in a pre-processing step we define as text distillation. Lastly, using simulation, we show how treatment leakage introduces a bias in estimates of the average treatment effect (ATE) and how text distillation can mitigate this bias.

Conceptualizing Treatment Leakage in Text-based Causal Inference

Counterfactually Augmented Data (CAD) aims to improve out-of-domain generalizability, an indicator of model robustness. The improvement is credited to promoting core features of the construct over spurious artifacts that happen to correlate with it. Yet, over-relying on core features may lead to unintended model bias. Especially, construct-driven CAD---perturbations of core features---may induce models to ignore the context in which core features are used. Here, we test models for sexism and hate speech detection on challenging data: non-hate and non-sexist usage of identity and gendered terms. On these hard cases, models trained on CAD, especially construct-driven CAD, show higher false positive rates than models trained on the original, unperturbed data. Using a diverse set of CAD---construct-driven and construct-agnostic---reduces such unintended bias.


Counterfactually Augmented Data and Unintended Bias: The Case of Sexism and Hate Speech Detection

Analyzing ideology and polarization is of critical importance in advancing our grasp of modern politics. Recent research has made great strides towards understanding the ideological bias (i.e., stance) of news media along the left-right spectrum. In this work, we instead take a novel and more nuanced approach for the study of ideology based on its left or right positions on the issue being discussed. Aligned with the theoretical accounts in political science, we treat ideology as a multi-dimensional construct, and introduce the first diachronic dataset of news articles whose ideological positions are annotated by trained political scientists and linguists at the paragraph level. We showcase that, by controlling for the author's stance, our method allows for the quantitative and temporal measurement and analysis of polarization as a multidimensional ideological distance. We further present baseline models for ideology prediction, outlining a challenging task distinct from stance detection.

Political Ideology and Polarization: A Multi-dimensional Approach

Personalized dialogue systems explore the problem of generating responses that are consistent with the user's personality, which has raised much attention in recent years. Existing personalized dialogue systems have tried to extract user profiles from dialogue history to guide personalized response generation. Since the dialogue history is usually long and noisy, most existing methods truncate the dialogue history to model the user's personality. Such methods can generate some personalized responses, but a large part of dialogue history is wasted, leading to sub-optimal performance of personalized response generation. In this work, we propose to refine the user dialogue history on a large scale, based on which we can handle more dialogue history and obtain more abundant and accurate persona information. Specifically, we design an MSP model which consists of three personal information refiners and a personalized response generator. With these multi-level refiners, we can sparsely extract the most valuable information (tokens) from the dialogue history and leverage other similar users' data to enhance personalization. Experimental results on two real-world datasets demonstrate the superiority of our model in generating more informative and personalized responses.

Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generation

Significance testing—especially the paired-permutation test—has played a vital role in developing NLP systems to provide confidence that the difference in performance between two systems (i.e., the test statistic) is not due to luck. However, practitioners rely on Monte Carlo approximation to perform this test due to a lack of a suitable exact algorithm. In this paper, we provide an efficient exact algorithm for the paired-permutation test for a family of structured test statistics. Our algorithm runs in $\mathcalO(G N (\log GN )(\log N))$ time where $N$ is the dataset size and $G$ is the range of the test statistic. We found that our exact algorithm was $10$x faster than the Monte Carlo approximation with $20000$ samples on a common dataset

Exact Paired-Permutation Testing for Structured Test Statistics

Current text-image approaches~(e.g., CLIP) typically adopt dual-encoder architecture 
using pre-trained vision-language representation. However, these models still pose non-trivial memory requirements and substantial incremental indexing time, which makes them less practical on mobile devices. In this paper, we present an effective two-stage framework 
to compress large pre-trained dual-encoder for lightweight text-image retrieval. The resulting model is smaller~(39\% of the original), 
faster~(1.6x/2.9x for processing image/text respectively), yet performs on par with or better than the original full model on Flickr30K and MSCOCO benchmarks. We also open-source an accompanying realistic mobile image search application.

Leaner and Faster: Two-Stage Model Compression for Lightweight Text-Image Retrieval

We show how to scale structured inference of HMMs and PCFGs by leveraging tensor rank decompostion and changing variable elimination order.

Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs

In order to build more human-like cognitive agents, systems capable of detecting various human emotions must be designed to respond appropriately. Confusion, the combination of an emotional and cognitive state, is under-explored. In this paper, we build upon prior work to develop models that detect confusion from three modalities: video (facial features), audio (prosodic features), and text (transcribed speech features). Our research improves the data collection process by allowing for continuous (as opposed to discrete) annotation of confusion levels. We also craft models based on recurrent neural networks (RNNs) given their ability to predict sequential data. In our experiments, we find that text and video modalities are the most important in predicting confusion while the explored audio features are relatively unimportant predictors of confusion in our data.

Multimodal Modeling of Task-Mediated Confusion

I am a Data Scientist working under Dr. Brenda Curtis at the National Institute on Drug Abuse (NIDA).  I am also a third year PhD student in Computer Science at the University of Pennsylvania working under H. Andrew Schwartz and Lyle Ungar. My primary research interest is community centered NLP: developing methods to measure relationships between individuals and their communities using social media language. I'm also interested in machine learning applications to substance use and recovery. 

Nonsuicidal Self-Injury and Substance Use Disorders: A Shared Language of Addiction

Assessing sentence readability for German language learners with broad linguistic modeling or readability formulas: When do linguistic insights make a difference?

Downloads

Next from NAACL 2022

Conceptualizing Treatment Leakage in Text-based Causal Inference

Similar lecture

Right Answer, Wrong Score: Uncovering the Inconsistencies of LLM Evaluation in Multiple-Choice Question Answering

.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 NAACL 2022

Conceptualizing Treatment Leakage in Text-based Causal Inference

Similar lecture

Right Answer, Wrong Score: Uncovering the Inconsistencies of LLM Evaluation in Multiple-Choice Question Answering

Downloads