Singapore

Controlling chatbot utterance generation with multiple attributes such as 
personalities, emotions and dialogue acts is a practically useful but 
under-studied problem.
We propose a novel framework called DASC 
that possesses strong controllability with a weighted decoding paradigm, 
while improving generation quality with the grounding in an 
attribute semantics space. Generation with multiple attributes is then 
intuitively implemented with an interpolation of multiple attribute embeddings,
which results in substantial reduction in the model sizes. 
Experiments show that DASC can achieve high control accuracy 
in generation task with the simultaneous control of 3 aspects while also producing interesting and 
reasonably sensible responses, even in an out-of-distribution robustness 
test.

EMNLP 2023

Semantic Space Grounded Weighted Decoding for Multi-Attribute Controllable Dialogue Generation

weighted decoding

multi-attribute controllable generation

dialogue generation

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.

Instruction-based multitasking has played a critical role in the success of large language models (LLMs) in multi-turn dialog applications. While publicly available LLMs have shown promising performance, when exposed to complex instructions with multiple constraints, they lag against state-of-the-art models like ChatGPT. In this work, we hypothesize that the availability of large-scale complex demonstrations is crucial in bridging this gap. Focusing on dialog applications, we propose a novel framework, CESAR, that unifies a large number of dialog tasks in the same format and allows programmatic induction of complex instructions without any manual effort.

We apply CESAR on InstructDial, a benchmark for instruction-based dialog tasks. We further enhance InstructDial with new datasets and tasks and utilize CESAR to induce complex tasks with compositional instructions. This results in a new benchmark called InstructDial++, which includes 63 datasets with 86 basic tasks and 68 composite tasks. Through rigorous experiments, we demonstrate the scalability of CESAR in providing rich instructions. Models trained on InstructDial++ can follow compositional prompts, such as prompts that ask for multiple stylistic constraints.

CESAR: Automatic Induction of Compositional Instructions for Multi-turn Dialogs | VIDEO

Simultaneous Speech Translation (SimulST) is a task focused on ensuring high-quality translation of speech in low-latency situations. 
Despite this, the modality gap (\emph{e.g.}, unknown word boundaries) between audio and text presents a challenge. 
This gap hinders the effective application of policies from simultaneous text translation (SimulMT) and compromises the performance of offline speech translation. 
To address this issue, we first leverage the Montreal Forced Aligner (MFA) and utilize audio transcription pairs in pre-training the acoustic encoder, and introduce a token-level cross-modal alignment that allows the wait-$k$ policy from SimulMT to better adapt to SimulST. 
This token-level boundary alignment simplifies the decision-making process for predicting read/write actions, as if the decoder were directly processing text tokens. 
Subsequently, to optimize the SimulST task, we propose a robust and random wait-$k$-tokens strategy. 
This strategy allows a single model to meet various latency requirements and minimizes error accumulation of boundary alignment during inference. 
Our experiments on the MuST-C dataset show that our method achieves better trade-off between translation quality and latency.

Training Simultaneous Speech Translation with Robust and Random Wait-k-Tokens Strategy

We address a fundamental challenge in Natural Language Generation (NLG) model evaluation---the design and evaluation of evaluation metrics. Recognizing the limitations of existing automatic metrics and noises from how current human evaluation was conducted, we propose MetricEval, a framework informed by measurement theory, the foundation of educational test design, for conceptualizing and evaluating the reliability and validity of NLG evaluation metrics. The framework formalizes the source of measurement error and offers statistical tools for evaluating evaluation metrics based on empirical data. With our framework, one can quantify the uncertainty of the metrics to better interpret the result. To exemplify the use of our framework in practice, we analyzed a set of evaluation metrics for summarization and identified issues related to conflated validity structure in human-eval and reliability in LLM-based metrics. Through MetricEval, we aim to promote the design, evaluation, and interpretation of valid and reliable metrics to advance robust and effective NLG models.

Evaluating Evaluation Metrics: A Framework for Analyzing NLG Evaluation Metrics using Measurement Theory

Evaluating the performance of Grammatical Error Correction (GEC) systems is a challenging task due to its subjectivity. Designing an evaluation metric that is as objective as possible is crucial to the development of GEC task. However, mainstream evaluation metrics, i.e., reference-based metrics, introduce bias into the multi-reference evaluation by extracting edits without considering the presence of multiple references. To overcome this issue, we propose Chunk-LE Multi-reference Evaluation (CLEME), designed to evaluate GEC systems in the multi-reference evaluation setting. CLEME builds chunk sequences with consistent boundaries for the source, the hypothesis and references, thus eliminating the bias caused by inconsistent edit boundaries. Furthermore, we observe the consistent boundary could also act as the boundary of grammatical errors, based on which the F$_{0.5}$ score is then computed following the correction independence assumption. We conduct experiments on six English reference sets based on the CoNLL-2014 shared task. Extensive experiments and detailed analyses demonstrate the correctness of our discovery and the effectiveness of CLEME. Further analysis reveals that CLEME is robust to evaluate GEC systems across reference sets with varying numbers of references and annotation styles. All the source codes of CLEME are released at https://github.com/THUKElab/CLEME.

CLEME: Debiasing Multi-reference Evaluation for Grammatical Error Correction

The recent success of large language models (LLMs) has shown great potential to develop more powerful conversational recommender systems (CRSs), which rely on natural language conversations to satisfy user needs. In this paper, we embark on an investigation into the utilization of ChatGPT for CRSs, revealing the inadequacy of the existing evaluation protocol. It might overemphasize the matching with ground-truth items annotated by humans while neglecting the interactive nature of CRSs.

To overcome the limitation, we further propose an **i**nteractive **Eva**luation approach based on **L**L**M**s, named **iEvaLM**, which harnesses LLM-based user simulators. Our evaluation approach can simulate various system-user interaction scenarios. Through the experiments on two public CRS datasets, we demonstrate notable improvements compared to the prevailing evaluation protocol. Furthermore, we emphasize the evaluation of explainability, and ChatGPT showcases persuasive explanation generation for its recommendations. Our study contributes to a deeper comprehension of the untapped potential of LLMs for CRSs and provides a more flexible and realistic evaluation approach for future research about LLM-based CRSs.

Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models

Large Language Models (LLMs) play powerful, black-box readers in the retrieve-then-read pipeline, making remarkable progress in knowledge-intensive tasks. This work introduces a new framework, Rewrite-Retrieve-Read instead of the previous retrieve-then-read for the retrieval-augmented LLMs from the perspective of the query rewriting. Unlike prior studies focusing on adapting either the retriever or the reader, our approach pays attention to the adaptation of the search query itself, for there is inevitably a gap between the input text and the needed knowledge in retrieval. We first prompt an LLM to generate the query, then use a web search engine to retrieve contexts. Furthermore, to better align the query to the frozen modules, we propose a trainable scheme for our pipeline. A small language model is adopted as a trainable rewriter to cater to the black-box LLM reader. The rewriter is trained using the feedback of the LLM reader by reinforcement learning. Evaluation is conducted on downstream tasks, open-domain QA and multiple-choice QA. Experiments results show consistent performance improvement, indicating that our framework is proven effective and scalable, and brings a new framework for retrieval-augmented LLM.

Query Rewriting in Retrieval-Augmented Large Language Models

Most research on multimodal open-domain dialogue agents has focused on pretraining and multi-task learning using additional rich datasets beyond a given target dataset. However, methods for exploiting these additional datasets can be quite limited in real-world settings, creating a need for more efficient methods for constructing agents based solely on
the target dataset. To address these issues, we present a new learning strategy called visionlanguage warm-up tasks for multimodal dialogue models (VLAW-MDM). This strategy does not require the use of large pretraining or multi-task datasets but rather relies solely on learning from target data. Moreover, our proposed approach automatically generate captions for images and incorporate them into the model’s input to improve the contextualization of visual information. Using this novel
approach, we empirically demonstrate that our learning strategy is effective for limited data and relatively small models. The result show that our method achieved comparable and in some cases superior performance compared to existing state-of-the-art models on various evaluation metrics. The code is available at https://github.com/BeneciaLee/VLAW-MDM

A Framework for Vision-Language Warm-up Tasks in Multimodal Dialogue Models | VIDEO

The goal of document-grounded dialogue (DocGD) is to generate a response by anchoring the evidence in a supporting document in accordance with the dialogue context. This entails four causally interconnected variables. While task-specific pre-training has significantly enhanced performances on numerous downstream tasks, existing DocGD methods still rely on general pre-trained language models without a specifically tailored pre-training approach that explicitly captures the causal relationships. To address this, we present the first causally-complete dataset construction strategy for developing million-scale DocGD pre-training corpora. Additionally, we propose a causally-perturbed pre-training strategy to better capture causality by introducing perturbations on the variables and optimizing the overall causal effect. Experiments conducted on three benchmark datasets demonstrate that our causal pre-training yields substantial and consistent improvements in fully-supervised, low-resource, few-shot, and zero-shot settings.

Causal Document-Grounded Dialogue Pre-training | VIDEO

A persistent challenge to table question answering (TableQA) by generating executable programs has been adapting to varied table structures, typically requiring domain-specific logical forms. In response, this paper introduces a unified TableQA framework that: (1) provides a unified representation for structured tables as multi-index Pandas data frames, (2) uses Python as a powerful querying language, and (3) uses few-shot prompting to translate NL questions into Python programs, which are executable on Pandas data frames. Furthermore, to answer complex relational questions with extended program functionality and external knowledge, our framework allows customized APIs that Python programs can call. We experiment with four TableQA datasets that involve tables of different structures --- relational, multi-table, and hierarchical matrix shapes --- and achieve prominent improvements over past state-of-the-art systems. In ablation studies, we (1) show benefits from our multi-index representation and APIs over baselines that use only an LLM, and (2) demonstrate that our approach is modular and can incorporate additional APIs.

API-Assisted Code Generation for Question Answering on Varied Table Structures

Contrastive learning has been demonstrated effective in unsupervised sentence representation learning. Given one sentence, positive pairs are obtained by passing the sentence to the encoder twice using the different dropout masks, and negative pairs are obtained by taking another sentence in the same mini-batch. However, the method suffers from the surface structure bias, i.e., sentences with similar surface structures will be regarded as close in semantics while sentences with dissimilar surface structures will be viewed as distinct in semantics. This leads to the result that paraphrasing a sentence that is dissimilar in surface structure will receive a lower semantic similarity score than inserting a negative word into the sentence. In this paper, we first verify the bias by collecting a sentence transformation testset. Then we systematically probe the existing models by proposing novel splits based on benchmark datasets in accordance with semantic and surface structure similarity. We tackle the bias in two aspects: balancing the learning target by augmenting with data that counters the bias, and meanwhile preserving word semantics by leveraging recall loss to prevent catastrophic forgetting. We evaluate our model on standard semantic textual similarity (STS) tasks using different pre-trained backbones and achieve state-of-the-art averaged performance across the STS benchmarks. Particularly, our models that are fine-tuned with $RoBERTa_{base}$ and $RoBERTa_{large}$ achieve significantly better performance on most benchmark datasets.

Downloads

Next from EMNLP 2023

CESAR: Automatic Induction of Compositional Instructions for Multi-turn Dialogs | VIDEO