NLP Verification: Towards a General Methodology for Certifying Robustness

Deep neural networks have exhibited substantial success in the field of Natural Language Processing (NLP) and ensuring their safety and reliability is crucial: there are safety critical contexts where such models must be robust to variability or attack, and give guarantees over their output. Unlike Computer Vision, NLP lacks a unified verification methodology and, despite recent advancements in literature, they are often light on the pragmatical issues of NLP verification. In this paper, we make an attempt to distil and evaluate general components of an NLP verification pipeline, that emerges from the progress in the field to date. Our contributions are two-fold. Firstly, we give a general characterisation of verifiable subspaces that result from embedding sentences into continuous spaces. We identify, and give an effective method to deal with, the technical challenge of semantic generalisability of verified subspaces; and propose it as a standard metric in the NLP verification pipelines (alongside with the standard metrics of model accuracy and model verifiability). Secondly, we propose a general methodology to analyse the effect of the embedding gap, a problem that refers to the discrepancy between verification of geometric subpspaces on the one hand, and semantic meaning of sentences which the geometric subspaces are supposed to represent, on the other hand. In extreme cases, poor choices in embedding of sentences may invalidate verification results. We propose a number of practical NLP methods that can help to identify the effects of the embedding gap; and in particular we propose the metric of falsifiability of semantic subpspaces as another fundamental metric to be reported as part of the NLP verification pipeline. We believe that together these general principles pave the way towards a more consolidated and effective development of this new domain.

FurNav: Development and Preliminary Study of a Robot Direction Giver

When giving directions to a lost-looking tourist, would you first reference the street-names, cardinal directions, landmarks, or simply tell them to walk five hundred metres in one direction then turn left? Depending on the circumstances, one could reasonably make use of any of these direction giving styles. However, research on direction giving with a robot does not often look at how these different direction styles impact perceptions of the robots intelligence, nor does it take into account how users prior dispositions may impact ratings. In this work, we look at generating natural language for two navigation styles using a created system for a Furhat robot, before measuring perceived intelligence and animacy alongside users prior dispositions to robots in a small preliminary study (N=7). Our results confirm findings by previous work that prior negative attitudes towards robots correlates negatively with propensity to trust robots, and also suggests avenues for future research. For example, more data is needed to explore the link between perceived intelligence and direction style. We end by discussing our plan to run a larger scale experiment, and how to improve our existing study design.

FurChat: An Embodied Conversational Agent using LLMs, Combining Open and Closed-Domain Dialogue with Facial Expressions

We demonstrate an embodied conversational agent that can function as a receptionist and generate a mixture of open and closed-domain dialogue along with facial expressions, by using a large language model (LLM) to develop an engaging conversation. We deployed the system onto a Furhat robot, which is highly expressive and capable of using both verbal and nonverbal cues during interaction. The system was designed specifically for the National Robotarium to interact with visitors through natural conversations, providing them with information about the facilities, research, news, upcoming events, etc. The system utilises the state-of-the-art GPT-3.5 model to generate such information along with domain-general conversations and facial expressions based on prompt engineering.

Mirages: On Anthropomorphism in Dialogue Systems

Automated dialogue or conversational systems are anthropomorphised by developers and personified by users. While a degree of anthropomorphism is inevitable, conscious and unconscious design choices can guide users to personify them to varying degrees. Encouraging users to relate to automated systems as if they were human can lead to transparency and trust issues, and high risk scenarios caused by over-reliance on their outputs. As a result, natural language processing researchers have begun to investigate factors that induce personification and develop resources to mitigate such effects. However, these efforts are fragmented, and many aspects of anthropomorphism have yet to be considered. In this paper, we discuss the linguistic factors that contribute to the anthropomorphism of dialogue systems and the harms that can arise, arguing that it can reinforce stereotypes of gender roles and notions of acceptable language. We recommend that future efforts towards developing dialogue systems take particular care in their design, development, release, and description; and attend to the many linguistic cues that can elicit personification by users.

iLab at SemEval-2023 Task 11 Le-Wi-Di: Modelling Disagreement or Modelling Perspectives?

There are two competing approaches for modelling annotator disagreement: distributional soft-labelling approaches (which aim to capture the level of disagreement) or modelling perspectives of individual annotators or groups thereof. We adapt a multi-task architecture -- which has previously shown success in modelling perspectives -- to evaluate its performance on the SEMEVAL Task 11. We do so by combining both approaches, i.e. predicting individual annotator perspectives as an interim step towards predicting annotator disagreement. Despite its previous success, we found that a multi-task approach performed poorly on datasets which contained distinct annotator opinions, suggesting that this approach may not always be suitable when modelling perspectives. Furthermore, our results explain that while strongly perspectivist approaches might not achieve state-of-the-art performance according to evaluation metrics used by distributional approaches, our approach allows for a more nuanced understanding of individual perspectives present in the data. We argue that perspectivist approaches are preferable because they enable decision makers to amplify minority views, and that it is important to re-evaluate metrics to reflect this goal.

ANTONIO: Towards a Systematic Method of Generating NLP Benchmarks for Verification

Verification of machine learning models used in Natural Language Processing (NLP) is known to be a hard problem. In particular, many known neural network verification methods that work for computer vision and other numeric datasets do not work for NLP. Here, we study technical reasons that underlie this problem. Based on this analysis, we propose practical methods and heuristics for preparing NLP datasets and models in a way that renders them amenable to known verification methods based on abstract interpretation. We implement these methods as a Python library called ANTONIO that links to the neural network verifiers ERAN and Marabou. We perform evaluation of the tool using an NLP dataset R-U-A-Robot suggested as a benchmark for verifying legally critical NLP applications. We hope that, thanks to its general applicability, this work will open novel possibilities for including NLP verification problems into neural network verification competitions, and will popularise NLP problems within this community.

Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP

We report our efforts in identifying a set of previous human evaluations in NLP that would be suitable for a coordinated study examining what makes human evaluations in NLP more/less reproducible. We present our results and findings, which include that just 13\% of papers had (i) sufficiently low barriers to reproduction, and (ii) enough obtainable information, to be considered for reproduction, and that all but one of the experiments we selected for reproduction was discovered to have flaws that made the meaningfulness of conducting a reproduction questionable. As a result, we had to change our coordinated study design from a reproduce approach to a standardise-then-reproduce-twice approach. Our overall (negative) finding that the great majority of human evaluations in NLP is not repeatable and/or not reproducible and/or too flawed to justify reproduction, paints a dire picture, but presents an opportunity for a rethink about how to design and report human evaluations in NLP.

Fillers in Spoken Language Understanding: Computational and Psycholinguistic Perspectives

Disfluencies (i.e. interruptions in the regular flow of speech), are ubiquitous to spoken discourse. Fillers ("uh", "um") are disfluencies that occur the most frequently compared to other kinds of disfluencies. Yet, to the best of our knowledge, there isn't a resource that brings together the research perspectives influencing Spoken Language Understanding (SLU) on these speech events. This aim of this article is to synthesise a breadth of perspectives in a holistic way; i.e. from considering underlying (psycho)linguistic theory, to their annotation and consideration in Automatic Speech Recognition (ASR) and SLU systems, to lastly, their study from a generation standpoint. This article aims to present the perspectives in an approachable way to the SLU and Conversational AI community, and discuss moving forward, what we believe are the trends and challenges in each area.

Studying Alignment in Spontaneous Speech via Automatic Methods: How Do Children Use Task-specific Referents to Succeed in a Collaborative Learning Activity?

A dialogue is successful when there is alignment between the speakers, at different linguistic levels. In this work, we consider the dialogue occurring between interlocutors engaged in a collaborative learning task, and explore how performance and learning (i.e. task success) relate to dialogue alignment processes. The main contribution of this work is to propose new measures to automatically study alignment, to consider completely spontaneous spoken dialogues among children in the context of a collaborative learning activity. Our measures of alignment consider the children's use of expressions that are related to the task at hand, their follow-up actions of these expressions, and how it links to task success. Focusing on expressions related to the task gives us insight into the way children use (potentially unfamiliar) terminology related to the task. A first finding of this work is the discovery that the measures we propose can capture elements of lexical alignment in such a context. Through these measures, we find that teams with bad performance often aligned too late in the dialogue to achieve task success, and that they were late to follow up each other's instructions with actions. We also found that while interlocutors do not exhibit hesitation phenomena (which we measure by looking at fillers) in introducing expressions pertaining to the task, they do exhibit hesitation before accepting the expression, in the role of clarification. Lastly, we show that information management markers (measured by the discourse marker 'oh') occur in the general vicinity of the follow up actions from (automatically) inferred instructions. However, good performers tend to have this marker closer to these actions. Our measures still reflect some fine-grained aspects of learning in the dialogue, even if we cannot conclude that overall they are linked to the final measure of learning.

The importance of fillers for text representations of speech transcripts

While being an essential component of spoken language, fillers (e.g."um" or "uh") often remain overlooked in Spoken Language Understanding (SLU) tasks. We explore the possibility of representing them with deep contextualised embeddings, showing improvements on modelling spoken language and two downstream tasks - predicting a speaker's stance and expressed confidence.