Singapore

EMNLP 2023

In-context Learning of Large Language Models for Controlled Dialogue Summarization: A Holistic Benchmark and Empirical Analysis

large language models

dialogue summarization

controlled text generation

workshop paper

**Welcome to EMNLP 2023!**

On behalf of the EMNLP 2023 Organizing Committee, I extend a warm and heartfelt welcome to all of you to the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP). It is with immense pleasure and excitement that we gather here in Singapore, a vibrant hub of innovation and technological advancement.

The conference program is packed with insightful presentations, thought-provoking workshops, and engaging networking opportunities. In addition to the technical sessions, we have also planned several social events that will provide you with the opportunity to connect with your colleagues.

The conference is held in person at the Resorts World Convention Centre in Singapore, and available on-line with the help of Underline.

For those in Singapore, I hope that you will find time to explore the exciting Sentosa Island, Gardens by the Bay, Singapore Botanic Gardens and the many other attractions unique to Singapore.

Of course, we are grateful to our sponsors and partners for their generous support of EMNLP 2023, whose contributions make it possible for us to host this world-class event.

Yuji Matsumoto (RIKEN AIP) 
EMNLP 2023 General Chair

To access the **EMNLP 2023** event page on Underline, you need to register for the Conference. 
Please follow **[this link](https://2023.emnlp.org/registration/)** for more details.

EMNLP 2023 took place in Singapore from Dec 6th to Dec 10th, 2023.

Generating Extractive and Abstractive Summaries in Parallel from Scientific Articles Incorporating Citing Statements

Supervising the Centroid Baseline for Extractive Multi-Document Summarization

DebateKG – Automatic Policy Debate Case Creation with Semantic Knowledge Graphs

Analyzing Multi-Sentence Aggregation in Abstractive Summarization via the Shapley Value

Improving Multi-Stage Long Document Summarization with Enhanced Coarse Summarizer

Symbolic Planning and Code Generation for Grounded Dialogue

Frame semantic parsing is an important component of task-oriented dialogue systems. Current models rely on a significant amount training data to successfully identify the intent and slots in the user's input utterance. This creates a significant barrier for adding new domains to virtual assistant capabilities, as creation of this data requires highly specialized NLP expertise. In this work we propose OpenFSP, a framework that allows for easy creation of new domains from a handful of simple labels that can be generated without specific NLP knowledge. Our approach relies on creating a small, but expressive, set of domain agnostic slot types that enables easy annotation of new domains. Given such annotation, a matching algorithm relying on sentence encoders predicts the intent and slots for domains defined by end-users. Experiments on the TopV2 dataset shows that our model trained on these simple labels have strong performance against supervised baselines.

Towards Zero-Shot Frame Semantic Parsing with Task Agnostic Ontologies and Simple Labels

We compare MR-based and LM-based approaches in QA tasks and propose a novel methodology that leverages directional predicate entailment (inference) to address their limitations. Additionally, we present a Boolean QA task, demonstrating that
entailment graphs (EGs) exhibit comparable directional inference capabilities to large language models (LLMs). Our results highlight the importance of inference in open-domain QA and the improvements brought by leveraging EGs.

Complementary Roles of Inference and Language Models in QA

Modern dialog systems rely on Deep Learning to train transformer-based model architectures and rely on large amounts of training data. We investigate a controlled strategy for dialog synthesis. Our method generates utterances based on dialog annotations in a sequence-to-sequence manner. We perform our experiments in multiple settings, simulating various amounts of ground-truth data.

Controlled Data Augmentation for Training Task-Oriented Dialog Systems with Low Resource Data | VIDEO

If a question cannot be answered with the available information, robust systems for question answering (QA) should know not to answer. One way to build QA models that do this is with additional training data comprised of unanswerable questions, created either by employing annotators or through automated methods for unanswerable question generation. To show that the model complexity of existing automated approaches is not justified, we examine a simpler data augmentation method for unanswerable question generation in English: performing antonym and entity swaps on answerable questions. Compared to the prior state-of- the-art, data generated with our training-free and lightweight strategy results in better models (+1.6 F1 points on SQuAD 2.0 data with BERT-large), and has higher human-judged relatedness and readability. We quantify the raw benefits of our approach compared to no augmentation across multiple encoder models, using different amounts of generated data, and also on TydiQA-MinSpan data (+9.3 F1 points with BERT-large). Our results establish swaps as a simple but strong baseline for future work.

Premium content

In-context Learning of Large Language Models for Controlled Dialogue Summarization: A Holistic Benchmark and Empirical Analysis

Downloads

Next from EMNLP 2023

Generating Extractive and Abstractive Summaries in Parallel from Scientific Articles Incorporating Citing Statements