Malta

Document-level translation models are usually evaluated using general metrics such as BLEU, which are not informative about the benefits of context. Current work on context-aware evaluation, such as contrastive methods, only measure translation accuracy on words that need context for disambiguation. Such measures cannot reveal whether the translation model uses the correct supporting context. We propose to complement accuracy-based evaluation with measures of context utilization. We find that perturbation-based analysis (comparing models&#39; performance when provided with correct versus random context) is an effective measure of overall context utilization. For a finer-grained phenomenon-specific evaluation, we propose to measure how much the supporting context contributes to handling context-dependent discourse phenomena. We show that automatically-annotated supporting context gives similar conclusions to human-annotated context and can be used as alternative for cases where human annotations are not available. Finally, we highlight the importance of using discourse-rich datasets when assessing context utilization.

EACL 2024

On Measuring Context Utilization in Document-Level MT Systems

input attribution

discourse phenomena

document level translation

context utilization

Welcome to the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL). Continuing its mission of expanding and involving the science community of all European countries, EACL has selected the Malta community for the 18th EACL. Considering the importance of physical interaction among researchers, the conference will be held at the Hotel Radisson Blu, St. Julians, in Malta, from 17 to 22 of March, 2024. The conference will also feature the possibility to participate virtually. As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language. 
#### [Conference Handbook](https://drive.google.com/file/d/13Wn38q0yev6U3RTgnf4Tn5T9GuAuZ-xW/view?usp=sharing) *downloadable*

To access the EACL 2024 event page you need to register [**here**](https://acl.swoogo.com/EACL2024). 

Please register!

As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language.

Document-level translation models are usually evaluated using general metrics such as BLEU, which are not informative about the benefits of context. Current work on context-aware evaluation, such as contrastive methods, only measure translation accuracy on words that need context for disambiguation. Such measures cannot reveal whether the translation model uses the correct supporting context. We propose to complement accuracy-based evaluation with measures of context utilization. We find that perturbation-based analysis (comparing models' performance when provided with correct versus random context) is an effective measure of overall context utilization. For a finer-grained phenomenon-specific evaluation, we propose to measure how much the supporting context contributes to handling context-dependent discourse phenomena. We show that automatically-annotated supporting context gives similar conclusions to human-annotated context and can be used as alternative for cases where human annotations are not available. Finally, we highlight the importance of using discourse-rich datasets when assessing context utilization.

workshop paper

Foundational large language models (LLMs) can be instruction-tuned to perform open-domain question answering, facilitating applications like chat assistants. While such efforts are often carried out in a single language, we empirically analyze cost-efficient strategies for multilingual scenarios. Our study employs the Alpaca dataset and machine translations of it to form multilingual data, which is then used to tune LLMs through either low-rank adaptation or full-parameter training. Under a controlled computation budget, comparisons show that multilingual tuning is on par or better than tuning a model for each language. Furthermore, multilingual tuning with downsampled data can be as powerful and more robust. Our findings serve as a guide for expanding language support through instruction tuning.

Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca

The knowledge encapsulated in a model is the core factor determining its final performance on downstream tasks. Much research in NLP has focused on efficient methods for storing and adapting different types of knowledge, e.g., in dedicated modularized structures, and on how to effectively combine these modules, e.g., via parameter averaging at test time. However, given the many possible options in composing knowledge, a thorough understanding of the mechanisms involved is missing, and hence it remains unclear which strategies to utilize. In this work, we address this research gap by proposing a novel framework for zero-shot module composition, which encompasses existing and some novel variations for selecting, weighting, and combining parameter modules under a single unified notion. Focusing on the scenario of domain knowledge and adapter layers, our framework provides a systematic unification of concepts, allowing us to conduct the first comprehensive benchmarking study on various zero-shot knowledge composition strategies. In particular, we test two module combination methods (parameter averaging, output ensembling), and five selection and weighting strategies (uniform, and based on entropy, domain prior, TF-IDF, and semantic similarity) for their effectiveness and efficiency on 21 training and 10 evaluation domains across three models. Our results highlight the efficacy of ensembling, but also hint at the power of simple though often-ignored weighting methods. We further conduct various in-depth analyses, that, for instance, allow us to understand the role of weighting vs. top-k selection, and we show that, to a certain extent, the performance of adapter composition can even be predicted.

What the Weight?! A Unified Framework for Zero-Shot Knowledge Composition

State-of-the-art conversational AI systems raise concerns due to their potential risks of generating unsafe, toxic, unethical, or dangerous content. Previous works have developed datasets to teach conversational agents the appropriate social paradigms to respond effectively to specifically designed hazardous content. However, models trained on these adversarial datasets still struggle to recognize subtle unsafe situations that appear naturally in conversations or introduce an inappropriate response in a casual context. To understand the extent of this problem, we study prosociality in both adversarial and casual dialog contexts and audit the response quality of general-purpose language models in terms of propensity to produce unsafe content. We propose a dual-step fine-tuning process to address these issues using a socially aware n-pair contrastive loss. Subsequently, we train a base model that integrates prosocial behavior by leveraging datasets like Moral Integrity Corpus (MIC) and ProsocialDialog. Experimental results on several dialog datasets demonstrate the effectiveness of our approach in generating socially appropriate responses.

Improving Dialog Safety using Socially Aware Contrastive Learning

In the realm of dialogue systems, user simulation techniques have emerged as a game-changer, redefining the evaluation and enhancement of task-oriented dialogue (TOD) systems. These methods are crucial for replicating real user interactions, enabling applications like synthetic data augmentation, error detection, and robust evaluation. However, existing approaches often rely on rigid rule-based methods or on annotated data. This paper introduces DAUS, a Domain-Aware User Simulator. Leveraging large language models, we fine-tune DAUS on real examples of task-oriented dialogues. Results on two relevant benchmarks showcase significant improvements in terms of user goal fulfillment. Notably, we have observed that fine-tuning enhances the simulator's coherence with user goals, effectively mitigating hallucinations—a major source of inconsistencies in simulator responses.

Reliable LLM-based User Simulator for Task-Oriented Dialogue Systems

This paper introduces a novel approach to form-filling and dialogue system evaluation by leveraging Large Language Models (LLMs). The proposed method establishes a setup wherein multiple modules collaborate on addressing the form-filling task. The dialogue system is constructed on top of LLMs, focusing on defining specific roles for individual modules. We show that using multiple independent sub-modules working cooperatively on this task can improve performance and handle the typical constraints of using LLMs, such as context limitations. The study involves testing the modular setup on four selected forms of varying topics and lengths, employing commercial and open-access LLMs. The experimental results demonstrate that the modular setup consistently outperforms the baseline, showcasing the effectiveness of this approach. Furthermore, our findings reveal that open-access models perform comparably to commercial models for the specified task.

Evaluating Modular Dialogue System for Form Filling Using Large Language Models

An effective multi-turn instruction-following assistant can be developed by creating a simulator that can generate useful interaction data. Apart from relying on its intrinsic weights, an ideal user simulator should also be able to bootstrap external knowledge rapidly in its raw form to simulate the multifarious diversity of text available over the internet. Previous user simulators generally lacked diversity, were mostly closed domain, and necessitated rigid schema making them inefficient to rapidly scale to incorporate external knowledge. In this regard, we introduce Kaucus, a Knowledge-Augmented User Simulator framework, to outline a process of creating diverse user simulators, that can seamlessly exploit external knowledge as well as benefit downstream assistant model training. Through two GPT-J based simulators viz., a Retrieval Augmented Simulator and a Summary Controlled Simulator we generate diverse simulator-assistant interactions. Through reward and preference model-based evaluations, we find that these interactions serve as useful training data and create more helpful downstream assistants. We also find that incorporating knowledge through retrieval augmentation or summary control helps create better assistants.

KAUCUS - Knowledgeable User Simulators for Training Large Language Models

Similarity-weighted Construction of Contextualized Commonsense Knowledge Graphs for Knowledge-intense Argumentation Tasks

Clarification requests are a mechanism to help solve communication problems, e.g. due to ambiguity or underspecification, in instruction-following interactions. Despite their importance, even skilful models struggle with producing or interpreting such repair acts. In this work, we test three hypotheses concerning the effects of action taking as an auxiliary task in modelling iCR policies. Contrary to initial expectations, we conclude that its contribution to learning an iCR policy is limited, but some information can still be extracted from prediction uncertainty. We present further evidence that even well-motivated, Transformer-based models fail to learn good policies for when to ask Instruction CRs (iCRs), while the task of determining what to ask about can be more successfully modelled. Considering the implications of these findings, we further discuss the shortcomings of the data-driven paradigm for learning meta-communication acts.

Taking Action Towards Graceful Interaction: The Effects of Performing Actions on Modelling Policies for Instruction Clarification Requests

In this work, we analyze the uncertainty that is inherently present in the labels used for supervised machine learning in natural language inference (NLI). In cases where multiple annotations per instance are available, neither the majority vote nor the frequency of individual class votes is a trustworthy representation of the labeling uncertainty. 
We propose modeling the votes via a Bayesian mixture model to recover the data-generating process, i.e., the “true” latent classes, and thus gain insight into the class variations. This will enable a better understanding of the confusion happening during the annotation process. We also assess the stability of the proposed estimation procedure by systematically varying the numbers of i) instances and ii) labels. Thereby, we observe that few instances with many labels can predict the latent class borders reasonably well, while the estimation fails for many instances with only a few labels. This leads us to conclude that multiple labels are a crucial building block for properly analyzing label uncertainty.

More Labels or Cases? Assessing Label Variation in Natural Language Inference

Punctuation restoration is a crucial step after Automatic Speech Recognition (ASR) systems to enhance transcript readability and facilitate subsequent NLP tasks. Nevertheless, conventional lexical-based approaches are inadequate for solving the punctuation restoration task in Spanish, where ambiguity can be often found between unpunctuated declaratives and questions. In this study, we propose a novel hybrid acoustic-lexical punctuation restoration system for Spanish transcription, which consolidates acoustic and lexical signals through a modular process. Our experiment results show that the proposed system can effectively improve F1 score of question marks and overall punctuation restoration on both public and internal Spanish conversational datasets. Additionally, benchmark comparison against LLMs (Large Language Model) indicates the superiority of our approach in accuracy, reliability and latency. Furthermore, we demonstrate that the Word Error Rate (WER) of the ASR module also benefits from our proposed system.

Downloads

Next from EACL 2024

Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca

Similar lecture

On Measuring Context Utilization in Document-Level MT Systems

.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 EACL 2024

Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca

Similar lecture

On Measuring Context Utilization in Document-Level MT Systems

Downloads