Singapore

Many real-world tasks involve a mixed-initiative setup, wherein humans and AI systems collaboratively perform a task. While significant work has been conducted towards enabling humans to specify, through language, exactly how an agent should complete a task (i.e., low-level specification), prior work lacks on interpreting the high-level strategic intent of the human commanders. Parsing strategic intent from language will allow autonomous systems to independently operate according to the user&#39;s plan without frequent guidance or instruction. In this paper, we build a computational interface capable of translating unstructured language strategies into actionable intent in the form of goals and constraints. Leveraging a game environment, we collect a dataset of over 1000 examples, mapping language strategies to the corresponding goals and constraints, and show that our model, trained on this dataset, significantly outperforms human interpreters in inferring strategic intent (i.e., goals and constraints) from language (p &lt; 0.05). Furthermore, we show that our model (125M parameters) significantly outperforms ChatGPT for this task (p &lt; 0.05) in a low-data setting.

EMNLP 2023

A Computational Interface to Translate Strategic Intent from Unstructured Language in a Low-Data Setting

low-data

human-evaluation

text classification

Many real-world tasks involve a mixed-initiative setup, wherein humans and AI systems collaboratively perform a task. While significant work has been conducted towards enabling humans to specify, through language, exactly how an agent should complete a task (i.e., low-level specification), prior work lacks on interpreting the high-level strategic intent of the human commanders. Parsing strategic intent from language will allow autonomous systems to independently operate according to the user's plan without frequent guidance or instruction. In this paper, we build a computational interface capable of translating unstructured language strategies into actionable intent in the form of goals and constraints. Leveraging a game environment, we collect a dataset of over 1000 examples, mapping language strategies to the corresponding goals and constraints, and show that our model, trained on this dataset, significantly outperforms human interpreters in inferring strategic intent (i.e., goals and constraints) from language (p < 0.05). Furthermore, we show that our model (125M parameters) significantly outperforms ChatGPT for this task (p < 0.05) in a low-data setting.

poster

**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.

Making big purchases requires consumers to research or consult a salesperson to gain domain expertise. However, existing conversational recommender systems (CRS) often overlook users' lack of background knowledge, focusing solely on gathering preferences. 
In this work, we define a new problem space for conversational agents that aim to provide both product recommendations and educational value through mixed-type mixed-initiative dialog. 
We introduce SalesOps, a framework that facilitates the simulation and evaluation of such systems by leveraging recent advancements in large language models (LLMs).
We build SalesBot and ShopperBot, a pair of LLM-powered agents that can simulate either side of the framework. 
A comprehensive human study compares SalesBot against professional salespeople, revealing that although SalesBot approaches professional performance in terms of fluency and informativeness, it lags behind in recommendation quality. We emphasize the distinct limitations both face in providing truthful information, highlighting the challenges of ensuring faithfulness in the CRS context. We release our code and make all data available.

Salespeople vs SalesBot: Exploring the Role of Educational Value in Conversational Recommender Systems

We explore the role of dialog acts in style transfer, specifically empathy style transfer -- rewriting a sentence to make it more empathetic without changing its meaning. Specifically, we use two novel few-shot prompting strategies: target prompting, which only uses examples of the target style (unlike traditional prompting with source/target pairs), and dialog-act-conditioned prompting, which first estimates the dialog act of the source sentence and then makes it more empathetic using few-shot examples of the same dialog act. Our study yields two key findings: (1) Target prompting typically improves empathy more effectively while maintaining the same level of semantic similarity; (2) Dialog acts matter. Dialog-act-conditioned prompting enhances empathy while preserving both semantics and the dialog-act type. Different dialog acts benefit differently from different prompting methods, highlighting the need for further investigation of the role of dialog acts in style transfer.

Conditioning on Dialog Acts improves Empathy Style Transfer

A particularly successful class of approaches for few-shot learning combines language models with prompts - hand-crafted task descriptions that complement data samples. However, designing prompts by hand for each task commonly requires domain knowledge and substantial guesswork. We observe, in the context of classification tasks, that instruction finetuned language models are remarkably robust towards some dimensions of a prompt's design. We subsequently propose a simple method to eliminate the need for handcrafted prompts, named AuT-Few.
This approach consists of (i) a prompt retrieval module that selects suitable task instructions from the instruction-tuning knowledge base, and (ii) the generation of two distinct, semantically meaningful, class descriptions and a selection mechanism via cross-validation. Over 12 datasets, spanning 8 classification tasks, we show that AuT-Few outperforms current state-of-the-art few-shot learning methods. Moreover, AuT-Few is the best ranking method across datasets on the RAFT few-shot benchmark. Notably, these results are achieved without task-specific handcrafted prompts on unseen tasks.

Automated Few-Shot Classification with Instruction-Finetuned Language Models

Despite its relevance, the maturity of NLP for social media pales in comparison with general-purpose models, metrics and benchmarks. This fragmented landscape makes it hard for the community to know, for instance, given a task, which is the best performing model and how it compares with others. To alleviate this issue, we introduce a unified benchmark for NLP evaluation in social media, SuperTweetEval, which includes a heterogeneous set of tasks and datasets combined, adapted and constructed from scratch. We benchmarked the performance of a wide range of models on SuperTweetEval and our results suggest that, despite the recent advances in language modelling, social media remains challenging.

SuperTweetEval: A Challenging, Unified and Heterogeneous Benchmark for Social Media NLP Research

Graph reasoning contributes to the integration of discretely-distributed attentive information (clues) for Multi-party Dialogue Reading Comprehension (MDRC). This is attributed primarily to multi-hop reasoning over global conversational structures. However, existing approaches barely apply questions for anti-noise graph reasoning. More seriously, the local semantic structures in utterances are neglected, although they are beneficial for bridging across semantically-related clues. In this paper, we propose a question-aware global-to-local graph reasoning approach. It expands the canonical Interlocutor-Utterance graph by introducing a question node, enabling comprehensive global graph reasoning. More importantly, it constructs a semantic-role graph for each utterance, and accordingly performs local graph reasoning conditioned on the semantic relations. We design a two-stage encoder network to implement the progressive reasoning from the global graph to local. The experiments on the benchmark datasets Molweni and FriendsQA show that our approach yields significant improvements, compared to BERT and ELECTRA baselines. It achieves 73.6\% and 77.2\% F$1$-scores on Molweni and FriendsQA, respectively, outperforming state-of-the-art methods that employ different pretrained language models as backbones.

GLGR: Question-aware Global-to-Local Graph Reasoning for Multi-party Dialogue Reading Comprehension

Deep neural classifiers trained with cross-entropy loss (CE loss) often suffer from poor calibration, necessitating the task of out-of-distribution (OOD) detection. Traditional supervised OOD detection methods require expensive manual annotation of in-distribution and OOD samples. To address the annotation bottleneck, we introduce SELFOOD, a self-supervised OOD detection method that requires only in-distribution samples as supervision. We cast OOD detection as an inter-document intra-label (IDIL) ranking problem and train the classifier with our pairwise ranking loss, referred to as IDIL loss. Specifically, given a set of in-distribution documents and their labels, for each label, we train the classifier to rank the softmax scores of documents belonging to that label to be higher than the scores of documents that belong to other labels. Unlike CE loss, our IDIL loss function reaches zero when the desired confidence ranking is achieved and gradients are backpropagated to decrease probabilities associated with incorrect labels rather than continuously increasing the probability of the correct label. Extensive experiments with several classifiers on multiple classification datasets demonstrate the effectiveness of our method in both coarse- and fine-grained settings.

SELFOOD: Self-Supervised Out-Of-Distribution Detection via Learning to Rank | VIDEO

Interpreting answers to yes-no questions in social media is difficult. Yes and no keywords are uncommon, and the few answers that include them are rarely to be interpreted what the keywords suggest. In this paper, we present a new corpus of 4,442 yes-no question-answer pairs from Twitter. We discuss linguistic characteristics of answers whose interpretation is yes or no, as well as answers whose interpretation is unknown. We show that large language models are far from solving this problem, even after fine-tuning and blending other corpora for the same problem but outside social media.

Interpreting Answers to Yes-No Questions in User-Generated Content

Answering time-sensitive questions from long documents requires temporal reasoning over the times in questions and documents. An important open question is whether large language models can perform such reasoning solely using a provided text document, or whether they can benefit from additional temporal information extracted using other systems. We address this research question by applying existing temporal information extraction systems to construct temporal graphs of events, times, and temporal relations in questions and documents. We then investigate different approaches for fusing these graphs into Transformer models. Experimental results show that our proposed approach for fusing temporal graphs into input text substantially enhances the temporal reasoning capabilities of Transformer models with or without fine-tuning. Additionally, our proposed method outperforms various graph convolution-based approaches and establishes a new state-of-the-art performance on SituatedQA and three splits of TimeQA.

Fusing Temporal Graphs into Transformers for Time-Sensitive Question Answering

Most existing debiasing methods for multimodal models, including causal intervention and inference methods, utilize approximate heuristics to represent the biases, such as shallow features from early stages of training or unimodal features for multimodal tasks like VQA, etc., which may not be accurate. In this paper, we study bias arising from confounders in a causal graph for multimodal data, and examine a novel approach that leverages causally-motivated information minimization to learn the confounder representations. Robust predictive features contain diverse information that helps a model generalize to out-of-distribution data. Hence, minimizing the information content of features obtained from a pretrained biased model helps learn the simplest predictive features that capture the underlying data distribution. We treat these features as confounder representations and use them via methods motivated by causal theory to remove bias from models. We find that the learned confounder representations indeed capture dataset biases and the proposed debiasing methods improve out-of-distribution (OOD) performance on multiple multimodal datasets without sacrificing in-distribution performance. Additionally, we introduce a novel metric to quantify the sufficiency of spurious features in models' predictions that further demonstrates the effectiveness of our proposed methods.

Debiasing Multimodal Models via Causal Information Minimization

Automatically generated reports from medical images promise to improve the workflow of radiologists. Existing methods consider an image-to-report modeling task by directly generating a fully-fledged report from an image. However, this conflates the content of the report (e.g., findings and their attributes) with its style (e.g., format and choice of words), which can lead to clinically inaccurate reports. To address this, we propose a two-step approach for radiology report generation. First, we extract the content from an image; then, we verbalize the extracted content into a report that matches the style of a specific radiologist. For this, we leverage RadGraph---a graph representation of reports---together with large language models (LLMs). In our quantitative evaluations, we find that our approach leads to beneficial performance. Our human evaluation with clinical raters highlights that the AI-generated reports are indistinguishably tailored to the style of individual radiologist despite leveraging only a few examples as context.

Premium content

A Computational Interface to Translate Strategic Intent from Unstructured Language in a Low-Data Setting

Downloads

Next from EMNLP 2023

Salespeople vs SalesBot: Exploring the Role of Educational Value in Conversational Recommender Systems

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES