Ieva Staliūnaitė

Yunjie He, Philip John Gorinski, Ieva Staliunaite et al.

Multi-hop QA (Question Answering) is the task of finding the answer to a question across multiple documents. In recent years, a number of Deep Learning-based approaches have been proposed to tackle this complex task, as well as a few standard benchmarks to assess models Multi-hop QA capabilities. In this paper, we focus on the well-established HotpotQA benchmark dataset, which requires models to perform answer span extraction as well as support sentence prediction. We present two extensions to the SOTA Graph Neural Network (GNN) based model for HotpotQA, Hierarchical Graph Network (HGN): (i) we complete the original hierarchical structure by introducing new edges between the query and context sentence nodes; (ii) in the graph propagation step, we propose a novel extension to Hierarchical Graph Attention Network GATH (Graph ATtention with Hierarchies) that makes use of the graph hierarchy to update the node representations in a sequential fashion. Experiments on HotpotQA demonstrate the efficiency of the proposed modifications and support our assumptions about the effects of model related variables.

Ieva Staliūnaitė, Philip John Gorinski, Ignacio Iacobacci

Multihop Question Answering is a complex Natural Language Processing task that requires multiple steps of reasoning to find the correct answer to a given question. Previous research has explored the use of models based on Graph Neural Networks for tackling this task. Various architectures have been proposed, including Relational Graph Convolutional Networks (RGCN). For these many node types and relations between them have been introduced, such as simple entity co-occurrences, modelling coreferences, or "reasoning paths" from questions to answers via intermediary entities. Nevertheless, a thoughtful analysis on which relations, node types, embeddings and architecture are the most beneficial for this task is still missing. In this paper we explore a number of RGCN-based Multihop QA models, graph relations, and node embeddings, and empirically explore the influence of each on Multihop QA performance on the WikiHop dataset.

Ieva Raminta Staliūnaitė, James Bishop, Andreas Vlachos

The task of Error Prediction, namely predicting whether a model output is correct, is commonly tackled with Uncertainty Quantification (UQ). However, while uncertainty metrics capture when models lack knowledge or capacity to make a prediction, they also reflect aleatoric uncertainty, which is inherent in the model input and context. This paper presents a method for improving error prediction for Large Language Models (LLMs), by disentangling input ambiguity from UQ signal. We conduct experiments on the task of Question Answering (QA) with six UQ metrics and show that UQ metrics are more predictive of errors on unambiguous instances than on questions with multiple plausible answers. We use Gated Experts and Selective Prediction to incorporate gold and predicted ambiguity labels into the error prediction pipeline. We find that ambiguity information improves error prediction scores across model families, training and evaluation paradigms, datasets (including allegedly unambiguous ones), and sources of aleatoric uncertainty, yielding improvements of over 10 points of PRR for individual UQ metrics on standard datasets.

Ieva Raminta Staliūnaitė, Julius Cheng, Andreas Vlachos

The predictive uncertainty of machine translation (MT) models is typically used as a quality estimation proxy. In this work, we posit that apart from confidently translating when a single correct translation exists, models should also maintain uncertainty when the input is ambiguous. We use uncertainty to measure gender bias in MT systems. When the source sentence includes a lexeme whose gender is not overtly marked, but whose target-language equivalent requires gender specification, the model must infer the appropriate gender from the context and can be susceptible to biases. Prior work measured bias via gender accuracy, however it cannot be applied to ambiguous cases. Using semantic uncertainty, we are able to assess bias when translating both ambiguous and unambiguous source sentences, and find that high translation accuracy does not correlate with exhibiting uncertainty appropriately, and that debiasing affects the two cases differently.

Max Glockner, Ieva Staliūnaitė, James Thorne et al.

Automated fact-checking systems verify claims against evidence to predict their veracity. In real-world scenarios, the retrieved evidence may not unambiguously support or refute the claim and yield conflicting but valid interpretations. Existing fact-checking datasets assume that the models developed with them predict a single veracity label for each claim, thus discouraging the handling of such ambiguity. To address this issue we present AmbiFC, a fact-checking dataset with 10k claims derived from real-world information needs. It contains fine-grained evidence annotations of 50k passages from 5k Wikipedia pages. We analyze the disagreements arising from ambiguity when comparing claims against evidence in AmbiFC, observing a strong correlation of annotator disagreement with linguistic phenomena such as underspecification and probabilistic reasoning. We develop models for predicting veracity handling this ambiguity via soft labels and find that a pipeline that learns the label distribution for sentence-level evidence selection and veracity prediction yields the best performance. We compare models trained on different subsets of AmbiFC and show that models trained on the ambiguous instances perform better when faced with the identified linguistic phenomena.

Ieva Staliūnaitė, Philip John Gorinski, Ignacio Iacobacci

Determining the plausibility of causal relations between clauses is a commonsense reasoning task that requires complex inference ability. The general approach to this task is to train a large pretrained language model on a specific dataset. However, the available training data for the task is often scarce, which leads to instability of model training or reliance on the shallow features of the dataset. This paper presents a number of techniques for making models more robust in the domain of causal reasoning. Firstly, we perform adversarial training by generating perturbed inputs through synonym substitution. Secondly, based on a linguistic theory of discourse connectives, we perform data augmentation using a discourse parser for detecting causally linked clauses in large text, and a generative language model for generating distractors. Both methods boost model performance on the Choice of Plausible Alternatives (COPA) dataset, as well as on a Balanced COPA dataset, which is a modified version of the original data that has been developed to avoid superficial cues, leading to a more challenging benchmark. We show a statistically significant improvement in performance and robustness on both datasets, even with only a small number of additionally generated data points.

Ieva Staliūnaitė, Ignacio Iacobacci

Many NLP tasks have benefited from transferring knowledge from contextualized word embeddings, however the picture of what type of knowledge is transferred is incomplete. This paper studies the types of linguistic phenomena accounted for by language models in the context of a Conversational Question Answering (CoQA) task. We identify the problematic areas for the finetuned RoBERTa, BERT and DistilBERT models through systematic error analysis - basic arithmetic (counting phrases), compositional semantics (negation and Semantic Role Labeling), and lexical semantics (surprisal and antonymy). When enhanced with the relevant linguistic knowledge through multitask learning, the models improve in performance. Ensembles of the enhanced models yield a boost between 2.2 and 2.7 points in F1 score overall, and up to 42.1 points in F1 on the hardest question classes. The results show differences in ability to represent compositional and lexical information between RoBERTa, BERT and DistilBERT.