Canada

Hybrid retrievers can take advantage of both sparse and dense retrievers. Previous hybrid retrievers leverage indexing-heavy dense retrievers. In this work, we study &quot;Is it possible to reduce the indexing memory of hybrid retrievers without sacrificing performance&quot;? Driven by this question, we leverage an indexing-efficient dense retriever (i.e. DrBoost) and introduce a LITE retriever that further reduces the memory of DrBoost. LITE is jointly trained on contrastive learning and knowledge distillation from DrBoost. Then, we integrate BM25, a sparse retriever, with either LITE or DrBoost to form light hybrid retrievers. Our Hybrid-LITE retriever saves $13\times$ memory while maintaining $98.0\%$ performance of the hybrid retriever of BM25 and DPR. In addition, we study the generalization capacity of our light hybrid retrievers on out-of-domain dataset and a set of adversarial attacks datasets. Experiments showcase that light hybrid retrievers achieve better generalization performance than individual sparse and dense retrievers. Nevertheless, our analysis shows that there is a large room to improve the robustness of retrievers, suggesting a new research direction.

&lt;iframe src=&quot;https://app.sli.do/event/pk54NpNnxuhWHUa3vSMXH2/embed/polls/b91de0c2-38f8-4a40-ba8a-59a5abc675a5&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

A Study on the Efficiency and Generalization of Light Hybrid Retrievers

generalization.

memory efficiency

hybrid model

information retrieval

robustness

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community."<br>

*Message from the General Chair, Dirk Hovy*





<br>

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

Hybrid retrievers can take advantage of both sparse and dense retrievers. Previous hybrid retrievers leverage indexing-heavy dense retrievers. In this work, we study "Is it possible to reduce the indexing memory of hybrid retrievers without sacrificing performance"? Driven by this question, we leverage an indexing-efficient dense retriever (i.e. DrBoost) and introduce a LITE retriever that further reduces the memory of DrBoost. LITE is jointly trained on contrastive learning and knowledge distillation from DrBoost. Then, we integrate BM25, a sparse retriever, with either LITE or DrBoost to form light hybrid retrievers. Our Hybrid-LITE retriever saves $13\times$ memory while maintaining $98.0\%$ performance of the hybrid retriever of BM25 and DPR. In addition, we study the generalization capacity of our light hybrid retrievers on out-of-domain dataset and a set of adversarial attacks datasets. Experiments showcase that light hybrid retrievers achieve better generalization performance than individual sparse and dense retrievers. Nevertheless, our analysis shows that there is a large room to improve the robustness of retrievers, suggesting a new research direction.

<iframe src="https://app.sli.do/event/pk54NpNnxuhWHUa3vSMXH2/embed/polls/b91de0c2-38f8-4a40-ba8a-59a5abc675a5" width="300" height="400"></iframe>

poster

### 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.

Prompting-based large language models (LLMs) are surprisingly powerful at generating natural language reasoning steps or Chains-of-Thoughts (CoT) for multi-step question answering (QA). They struggle, however, when the necessary knowledge is either unavailable to the LLM or not up-to-date within its parameters. While using the question to retrieve relevant text from an external knowledge source helps LLMs, we observe that this one-step retrieve-and-read approach is insufficient for multi-step QA. Here, \textit{what to retrieve} depends on \textit{what has already been derived}, which in turn may depend on \textit{what was previously retrieved}. To address this, we propose IRCoT, a new approach for multi-step QA that interleaves retrieval with steps (sentences) in a CoT, guiding the retrieval with CoT and in turn using retrieved results to improve CoT. Using IRCoT with GPT3 substantially improves retrieval (up to 21 points) as well as downstream QA (up to 15 points) on four datasets: HotpotQA, 2WikiMultihopQA, MuSiQue, and IIRC. We observe similar substantial gains in out-of-distribution (OOD) settings as well as with much smaller models such as Flan-T5-large without additional training. IRCoT reduces model hallucination, resulting in factually more accurate CoT reasoning.

<iframe src="https://app.sli.do/event/pk54NpNnxuhWHUa3vSMXH2/embed/polls/7ed830d5-50b7-485e-87e1-a4d738e82fef" width="300" height="400"></iframe>

Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions

Recent generative approaches for multi-hop question answering (QA) utilize the fusion-in-decoder method to generate a single sequence output which includes both a final answer and a reasoning path taken to arrive at that answer, such as passage titles and key facts from those passages. While such models can lead to better interpretability and high quantitative scores, they often have difficulty accurately identifying the passages corresponding to key entities in the context, resulting in incorrect passage hops and a lack of faithfulness in the reasoning path. To address this, we propose a single-sequence prediction method over a local reasoning graph that integrates a graph structure connecting key entities in each context passage to relevant subsequent passages for each question. We use a graph neural network to encode this graph structure and fuse the resulting representations into the entity representations of the model. Our experiments show significant improvements in answer exact-match/F1 scores and faithfulness of grounding in the reasoning path on the HotpotQA dataset and achieve state-of-the-art numbers on the Musique dataset with only up to a 4% increase in model parameters.

<iframe src="https://app.sli.do/event/pk54NpNnxuhWHUa3vSMXH2/embed/polls/10601b15-5fff-4761-921d-6e089243e4c1" width="300" height="400"></iframe>

Single Sequence Prediction over Reasoning Graphs for Multi-hop QA

We present ELQA, a corpus of questions and answers in and about the English language. Collected from two online forums, the >70k questions (from English learners and others) cover wide-ranging topics including grammar, meaning, fluency, and etymology. The answers include descriptions of general properties of English vocabulary and grammar as well as explanations about specific (correct and incorrect) usage examples. Unlike most NLP datasets, this corpus is metalinguistic---it consists of language about language. As such, it can facilitate investigations of the metalinguistic capabilities of NLU models, as well as educational applications in the language learning domain. To study this, we define a free-form question answering task on our dataset and conduct evaluations on multiple LLMs (Large Language Models) to analyze their capacity to generate metalinguistic answers.

<iframe src="https://app.sli.do/event/pk54NpNnxuhWHUa3vSMXH2/embed/polls/73e3667b-34aa-40ba-9d50-285dcf2315e5" width="300" height="400"></iframe>

ELQA: A Corpus of Metalinguistic Questions and Answers about English

Energy-based models (EBMs) have gained popularity for controlled text generation due to their high applicability to a wide range of constraints. However, sampling from EBMs is non-trivial, as it often requires a large number of iterations to converge to plausible text, which slows down the decoding process and makes it less practical for real-world applications. In this work, we propose BOLT, which relies on tunable biases to directly adjust the language model's output logits. Unlike prior work, BOLT maintains the generator's autoregressive nature to assert a strong control on token-wise conditional dependencies and overall fluency, and thus converges faster. When compared with state-of-the-arts on controlled generation tasks using both soft constraints (e.g., sentiment control) and hard constraints (e.g., keyword-guided topic control), BOLT demonstrates significantly improved efficiency and fluency. On sentiment control, BOLT is 7x faster than competitive baselines, and more fluent in 74.4% of the evaluation samples according to human judges.

<iframe src="https://app.sli.do/event/pk54NpNnxuhWHUa3vSMXH2/embed/polls/4a7394f5-79e7-4c06-8a89-c6fb0fea28ac" width="300" height="400"></iframe>

BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases

Self-training (ST) has prospered again in language understanding by augmenting the fine-tuning of big pre-trained models when labeled data is insufficient. However, it remains challenging to incorporate ST into attribute-controllable language generation. Augmented only by self-generated pseudo text, generation models \emph{over-exploit} the previously learned text space and \emph{fail to explore} a larger one, suffering from a restricted generalization boundary and limited controllability. In this work, we propose DuNST, a novel ST framework to tackle these problems. DuNST jointly models text generation and classification as a dual process and further perturbs and escapes from the collapsed space by adding two kinds of flexible noise. In this way, our model could construct and utilize both pseudo text generated from given labels and pseudo labels predicted from available unlabeled text, which are gradually refined during the ST phase. We theoretically demonstrate that DuNST can be regarded as enhancing the exploration of the potentially larger real text space while maintaining exploitation, guaranteeing improved performance. Experiments on three controllable generation tasks show that DuNST significantly boosts control accuracy with comparable generation fluency and diversity against several strong baselines.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/89fcd878-3aa1-49b8-8d72-6558a4b64e38" width="300" height="400"></iframe>

DuNST: Dual Noisy Self Training for Semi-Supervised Controllable Text Generation

Text generation often involves producing coherent and grammatically correct texts that also satisfy a given set of semantic constraints. While most approaches for conditional text generation have primarily focused on lexical constraints, they often struggle to effectively incorporate syntactic constraints, which provide a richer language for approximating semantic constraints.We address this gap by introducing NeuroStructural Decoding, a new decoding algorithm that incorporates syntactic constraints to further improve the quality of the generated text. We build NeuroStructural Decoding on the NeuroLogic Decoding (Lu etal. 2021) algorithm, which enables language generation models to produce fluent text while satisfying complex lexical constraints. Our algorithm is powerful and scalable. It tracks lexico-syntactic constraints (e.g., we need to observe {dog} as subject and {ball} as object)during decoding by parsing the partial generations at each step. To this end, we adapt a dependency parser to generate parses for incomplete sentences. Our approach is evaluated on three different language generation tasks, and the results show improved performance in both lexical and syntactic metrics compared to previous methods. The results suggest this is a promising solution for integrating fine-grained controllable generation into the conventional beam search decoding.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/deab9cfc-42b5-40fe-a560-2db373b2df32" width="300" height="400"></iframe>

NEUROSTRUCTURAL DECODING: Neural Text Generation with Structural Constraints

The success of NLP systems often relies on the availability of large, high-quality datasets. However, not all samples in these datasets are equally valuable for learning, as some may be redundant or noisy. Several methods for characterizing datasets based on model-driven meta-information (e.g., model's confidence) have been developed, but the relationship and complementary effects of these methods have received less attention. In this paper, we introduce infoVerse, a universal framework for dataset characterization, which provides a new feature space that effectively captures multidimensional characteristics of datasets by incorporating various model-driven meta-information. infoVerse reveals distinctive regions of the dataset that are not apparent in the original semantic space, hence guiding users (or models) in identifying which samples to focus on for exploration, assessment, or annotation. Additionally, we propose a novel sampling method on infoVerse to select a set of data points that maximizes informativeness. In three real-world applications (data pruning, active learning, and data annotation), the samples chosen on infoVerse space consistently outperform strong baselines in all applications. Our code and demo are publicly available.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/08b44b70-ed6a-4a5d-9966-114993b2e995" width="300" height="400"></iframe>

infoVerse: A Universal Framework for Dataset Characterization with Multidimensional Meta-information

While transformer-based systems have enabled greater accuracies with fewer training examples, data acquisition obstacles still persist for rare-class tasks -- when the class label is very infrequent (e.g. < 5% of samples). Active learning has in general been proposed to alleviate such challenges, but choice of selection strategy, the criteria by which rare-class examples are chosen, has not been systematically evaluated. Further, transformers enable iterative transfer-learning approaches. We propose and investigate transfer- and active learning solutions to the rare class problem of dissonance detection through utilizing models trained on closely related tasks and the evaluation of acquisition strategies, including a proposed probability-of-rare-class (PRC) approach. We perform these experiments for a specific rare-class problem: collecting language samples of cognitive dissonance from social media. We find that PRC is a simple and effective strategy to guide annotations and ultimately improve model accuracy while transfer-learning in a specific order can improve the cold-start performance of the learner but does not benefit iterations of active learning.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/e698f551-a292-465f-ba85-2fc71b35eb07" width="300" height="400"></iframe>

Transfer and Active Learning for Dissonance Detection: Addressing the Rare-Class Challenge

Video-grounded dialogue understanding is a challenging problem that requires machine to perceive, parse and reason over situated semantics extracted from weakly aligned video and dialogues. Most existing benchmarks treat both modalities the same as a frame-independent visual understanding task, while neglecting the intrinsic attributes in multimodal dialogues, such as scene and topic transitions. In this paper, we present \textbf{\underline{V}ideo-grounded \underline{S}cene\&\underline{T}opic \underline{A}wa\underline{R}e dialogue~(VSTAR)} dataset, a large scale video-grounded dialogue understanding dataset based on 395 TV series. Based on VSTAR, we propose two benchmarks for video-grounded dialogue understanding: scene segmentation and topic segmentation, and one benchmark for video-grounded dialogue generation. Comprehensive experiments are performed on these benchmarks to demonstrate the importance of multimodal information and segments in video-grounded dialogue understanding and generation.

<iframe src="https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/8a8de5d9-923b-404d-ac56-b7305af71ccd" width="300" height="400"></iframe>

VSTAR: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic Transitions

We present PATRON, a prompt-based data selection method for pre-trained language model fine-tuning under cold-start scenarios, i.e., no initial labeled data are available. In PATRON, we design (1) a prompt-based uncertainty propagation approach to estimate the importance of data points and (2) a partition-then-rewrite (PTR) strategy to promote sample diversity when querying for annotations. Experiments on six text classification datasets show that PATRON outperforms the strongest cold-start data selection baselines by up to 6.9%. Besides, with 128 labels only, PATRON achieves 91.0% and 92.1\% of the fully supervised performance based on vanilla fine-tuning and prompt-based learning respectively. Our implementation of PATRON will be published upon acceptance.

<iframe src="https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/2553cb40-23f5-4e4f-9d38-97b5e96776ea" width="300" height="400"></iframe>

Downloads

Next from ACL 2023

Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions

Similar lecture

MoR: Better Handling Diverse Queries with a Mixture of Sparse, Dense, and Human Retrievers

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES