Thomas Lukasiewicz


pdf bib
Counter-GAP: Counterfactual Bias Evaluation through Gendered Ambiguous Pronouns
Zhongbin Xie | Vid Kocijan | Thomas Lukasiewicz | Oana-Maria Camburu
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

Bias-measuring datasets play a critical role in detecting biased behavior of language models and in evaluating progress of bias mitigation methods. In this work, we focus on evaluating gender bias through coreference resolution, where previous datasets are either hand-crafted or fail to reliably measure an explicitly defined bias. To overcome these shortcomings, we propose a novel method to collect diverse, natural, and minimally distant text pairs via counterfactual generation, and construct Counter-GAP, an annotated dataset consisting of 4008 instances grouped into 1002 quadruples. We further identify a bias cancellation problem in previous group-level metrics on Counter-GAP, and propose to use the difference between inconsistency across genders and within genders to measure bias at a quadruple level. Our results show that four pre-trained language models are significantly more inconsistent across different gender groups than within each group, and that a name-based counterfactual data augmentation method is more effective to mitigate such bias than an anonymization-based method.

pdf bib
Improving Language Models’ Meaning Understanding and Consistency by Learning Conceptual Roles from Dictionary
Myeongjun Jang | Thomas Lukasiewicz
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

The non-humanlike behaviour of contemporary pre-trained language models (PLMs) is a leading cause undermining their trustworthiness. A striking phenomenon of such faulty behaviours is the generation of inconsistent predictions, which produces logically contradictory results, such as generating different predictions for texts delivering the same meaning or violating logical properties. Previous studies exploited data augmentation or implemented specialised loss functions to alleviate the issue. However, their usage is limited, because they consume expensive training resources for large-sized PLMs and can only handle a certain consistency type. To this end, we propose a practical approach that alleviates the inconsistent behaviour issue by fundamentally improving PLMs’ meaning awareness. Based on the conceptual role theory, our method allows PLMs to capture accurate meaning by learning precise interrelationships between concepts from word-definition pairs in a dictionary. Next, we propose an efficient parameter integration technique that updates only a few additional parameters to combine the learned interrelationship with PLMs’ pre-trained knowledge. Our experimental results reveal that the approach can concurrently improve multiple types of consistency, enables efficient knowledge integration, and easily applies to other languages.

pdf bib
Consistency Analysis of ChatGPT
Myeongjun Jang | Thomas Lukasiewicz
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

ChatGPT has gained a huge popularity since its introduction. Its positive aspects have been reported through many media platforms, and some analyses even showed that ChatGPT achieved a decent grade in professional exams, adding extra support to the claim that AI can now assist and even replace humans in industrial fields. Others, however, doubt its reliability and trustworthiness. This paper investigates the trustworthiness of ChatGPT and GPT-4 regarding logically consistent behaviour, focusing specifically on semantic consistency and the properties of negation, symmetric, and transitive consistency. Our findings suggest that while both models appear to show an enhanced language understanding and reasoning ability, they still frequently fall short of generating logically consistent predictions. We also ascertain via experiments that prompt designing, few-shot learning and employing larger large language models (LLMs) are unlikely to be the ultimate solution to resolve the inconsistency issue of LLMs.

pdf bib
An Empirical Analysis of Parameter-Efficient Methods for Debiasing Pre-Trained Language Models
Zhongbin Xie | Thomas Lukasiewicz
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

The increasingly large size of modern pre-trained language models not only makes them inherit more human-like biases from the training corpora, but also makes it computationally expensive to mitigate such biases. In this paper, we investigate recent parameter-efficient methods in combination with counterfactual data augmentation (CDA) for bias mitigation. We conduct extensive experiments with prefix tuning, prompt tuning, and adapter tuning on different language models and bias types to evaluate their debiasing performance and abilities to preserve the internal knowledge of a pre-trained model. We find that the parameter-efficient methods (i) are effective in mitigating gender bias, where adapter tuning is consistently the most effective one and prompt tuning is more suitable for GPT-2 than BERT, (ii) areless effective when it comes to racial and religious bias, which may be attributed to the limitations of CDA, and (iii) can perform similarly to or sometimes better than full fine-tuning with improved time and memory efficiency, as well as maintain the internal knowledge in BERT and GPT-2, evaluated via fact retrieval and downstream fine-tuning.

pdf bib
Faithfulness Tests for Natural Language Explanations
Pepa Atanasova | Oana-Maria Camburu | Christina Lioma | Thomas Lukasiewicz | Jakob Grue Simonsen | Isabelle Augenstein
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Explanations of neural models aim to reveal a model’s decision-making process for its predictions. However, recent work shows that current methods giving explanations such as saliency maps or counterfactuals can be misleading, as they are prone to present reasons that are unfaithful to the model’s inner workings. This work explores the challenging question of evaluating the faithfulness of natural language explanations (NLEs). To this end, we present two tests. First, we propose a counterfactual input editor for inserting reasons that lead to counterfactual predictions but are not reflected by the NLEs. Second, we reconstruct inputs from the reasons stated in the generated NLEs and check how often they lead to the same predictions. Our tests can evaluate emerging NLE models, proving a fundamental tool in the development of faithful NLEs.

pdf bib
KNOW How to Make Up Your Mind! Adversarially Detecting and Alleviating Inconsistencies in Natural Language Explanations
Myeongjun Jang | Bodhisattwa Prasad Majumder | Julian McAuley | Thomas Lukasiewicz | Oana-Maria Camburu
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

While recent works have been considerably improving the quality of the natural language explanations (NLEs) generated by a model to justify its predictions, there is very limited research in detecting and alleviating inconsistencies among generated NLEs. In this work, we leverage external knowledge bases to significantly improve on an existing adversarial attack for detecting inconsistent NLEs. We apply our attack to high-performing NLE models and show that models with higher NLE quality do not necessarily generate fewer inconsistencies. Moreover, we propose an off-the-shelf mitigation method to alleviate inconsistencies by grounding the model into external background knowledge. Our method decreases the inconsistencies of previous high-performing NLE models as detected by our attack.


pdf bib
Beyond Distributional Hypothesis: Let Language Models Learn Meaning-Text Correspondence
Myeongjun Jang | Frank Mtumbuka | Thomas Lukasiewicz
Findings of the Association for Computational Linguistics: NAACL 2022

The logical negation property (LNP), which implies generating different predictions for semantically opposite inputs (p is true iff ¬p is false), is an important property that a trustworthy language model must satisfy. However, much recent evidence shows that large-size pre-trained language models (PLMs) do not satisfy this property. In this paper, we perform experiments using probing tasks to assess PLMs’ LNP understanding. Unlike previous studies that only examined negation expressions, we expand the boundary of the investigation to lexical semantics. Through experiments, we observe that PLMs violate the LNP frequently. To alleviate the issue, we propose a novel intermediate training task, named meaning-matching, designed to directly learn a meaning text correspondence, instead of relying on the distributional hypothesis. Through multiple experiments, we find that the task enables PLMs to learn lexical semantic information. Also, through fine-tuning experiments on 7 GLUE tasks, we confirm that it is a safe intermediate task that guarantees a similar or better performance of downstream tasks. Finally, we observe that our proposed approach outperforms our previous counterparts despite its time and resource efficiency.

pdf bib
Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations in a Label-Abundant Setup
Yordan Yordanov | Vid Kocijan | Thomas Lukasiewicz | Oana-Maria Camburu
Findings of the Association for Computational Linguistics: EMNLP 2022

Training a model to provide natural language explanations (NLEs) for its predictions usually requires the acquisition of task-specific NLEs, which is time- and resource-consuming. A potential solution is the few-shot out-of-domain transfer of NLEs from a parent task with many NLEs to a child task.In this work, we examine the setup in which the child task has few NLEs but abundant labels. We establish four few-shot transfer learning methods that cover the possible fine-tuning combinations of the labels and NLEs for the parent and child tasks. We transfer explainability from a large natural language inference dataset (e-SNLI) separately to two child tasks: (1) hard cases of pronoun resolution, where we introduce the small-e-WinoGrande dataset of NLEs on top of the WinoGrande dataset, and (2) commonsense validation (ComVE). Our results demonstrate that the parent task helps with NLE generation and we establish the best methods for this setup.

pdf bib
Learning to Model Multimodal Semantic Alignment for Story Visualization
Bowen Li | Thomas Lukasiewicz
Findings of the Association for Computational Linguistics: EMNLP 2022

Story visualization aims to generate a sequence of images to narrate each sentence in a multi-sentence story, where the images should be realistic and keep global consistency across dynamic scenes and characters. Current works face the problem of semantic misalignment because of their fixed architecture and diversity of input modalities. To address this problem, we explore the semantic alignment between text and image representations by learning to match their semantic levels in the GAN-based generative model. More specifically, we introduce dynamic interactions according to learning to dynamically explore various semantic depths and fuse the different-modal information at a matched semantic level, which thus relieves the text-image semantic misalignment problem. Extensive experiments on different datasets demonstrate the improvements of our approach, neither using segmentation masks nor auxiliary captioning networks, on image quality and story consistency, compared with state-of-the-art methods.

pdf bib
Syntactically Rich Discriminative Training: An Effective Method for Open Information Extraction
Frank Mtumbuka | Thomas Lukasiewicz
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Open information extraction (OIE) is the task of extracting facts "(Subject, Relation, Object)” from natural language text. We propose several new methods for training neural OIE models in this paper. First, we propose a novel method for computing syntactically rich text embeddings using the structure of dependency trees. Second, we propose a new discriminative training approach to OIE in which tokens in the generated fact are classified as “real” or “fake”, i.e., those tokens that are in both the generated and gold tuples, and those that are only in the generated tuple but not in the gold tuple. We also address the issue of repetitive tokens in generated facts and improve the models’ ability to generate implicit facts. Our approach reduces repetitive tokens by a factor of 23%. Finally, we present paraphrased versions of the CaRB, OIE2016, and LSOIE datasets, and show that the models’ performance substantially improves when trained on augmented datasets. Our best model beats the SOTA of IMoJIE on the recent CaRB dataset, with an improvement of 39.63% in F1 score.

pdf bib
BECEL: Benchmark for Consistency Evaluation of Language Models
Myeongjun Jang | Deuk Sin Kwon | Thomas Lukasiewicz
Proceedings of the 29th International Conference on Computational Linguistics

Behavioural consistency is a critical condition for a language model (LM) to become trustworthy like humans. Despite its importance, however, there is little consensus on the definition of LM consistency, resulting in different definitions across many studies. In this paper, we first propose the idea of LM consistency based on behavioural consistency and establish a taxonomy that classifies previously studied consistencies into several sub-categories. Next, we create a new benchmark that allows us to evaluate a model on 19 test cases, distinguished by multiple types of consistency and diverse downstream tasks. Through extensive experiments on the new benchmark, we ascertain that none of the modern pre-trained language models (PLMs) performs well in every test case, while exhibiting high inconsistency in many cases. Our experimental results suggest that a unified benchmark that covers broad aspects (i.e., multiple consistency types and tasks) is essential for a more precise evaluation.


pdf bib
Knowledge Base Completion Meets Transfer Learning
Vid Kocijan | Thomas Lukasiewicz
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

The aim of knowledge base completion is to predict unseen facts from existing facts in knowledge bases. In this work, we introduce the first approach for transfer of knowledge from one collection of facts to another without the need for entity or relation matching. The method works for both canonicalized knowledge bases and uncanonicalized or open knowledge bases, i.e., knowledge bases where more than one copy of a real-world entity or relation may exist. Such knowledge bases are a natural output of automated information extraction tools that extract structured data from unstructured text. Our main contribution is a method that can make use of a large-scale pretraining on facts, collected from unstructured text, to improve predictions on structured data from a specific domain. The introduced method is the most impactful on small datasets such as ReVerb20K, where we obtained a 6% absolute increase of mean reciprocal rank and 65% relative decrease of mean rank over the previously best method, despite not relying on large pre-trained models like BERT.

pdf bib
Controlling Text Edition by Changing Answers of Specific Questions
Lei Sha | Patrick Hohenecker | Thomas Lukasiewicz
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021


pdf bib
Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanations
Oana-Maria Camburu | Brendan Shillingford | Pasquale Minervini | Thomas Lukasiewicz | Phil Blunsom
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

To increase trust in artificial intelligence systems, a promising research direction consists of designing neural models capable of generating natural language explanations for their predictions. In this work, we show that such models are nonetheless prone to generating mutually inconsistent explanations, such as ”Because there is a dog in the image.” and ”Because there is no dog in the [same] image.”, exposing flaws in either the decision-making process of the model or in the generation of the explanations. We introduce a simple yet effective adversarial framework for sanity checking models against the generation of inconsistent natural language explanations. Moreover, as part of the framework, we address the problem of adversarial attacks with full target sequences, a scenario that was not previously addressed in sequence-to-sequence attacks. Finally, we apply our framework on a state-of-the-art neural natural language inference model that provides natural language explanations for its predictions. Our framework shows that this model is capable of generating a significant number of inconsistent explanations.

pdf bib
Does the Objective Matter? Comparing Training Objectives for Pronoun Resolution
Yordan Yordanov | Oana-Maria Camburu | Vid Kocijan | Thomas Lukasiewicz
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Hard cases of pronoun resolution have been used as a long-standing benchmark for commonsense reasoning. In the recent literature, pre-trained language models have been used to obtain state-of-the-art results on pronoun resolution. Overall, four categories of training and evaluation objectives have been introduced. The variety of training datasets and pre-trained language models used in these works makes it unclear whether the choice of training objective is critical. In this work, we make a fair comparison of the performance and seed-wise stability of four models that represent the four categories of objectives. Our experiments show that the objective of sequence ranking performs the best in-domain, while the objective of semantic similarity between candidates and pronoun performs the best out-of-domain. We also observe a seed-wise instability of the model using sequence ranking, which is not the case when the other objectives are used.

pdf bib
Systematic Comparison of Neural Architectures and Training Approaches for Open Information Extraction
Patrick Hohenecker | Frank Mtumbuka | Vid Kocijan | Thomas Lukasiewicz
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

The goal of open information extraction (OIE) is to extract facts from natural language text, and to represent them as structured triples of the form <subject,predicate, object>. For example, given the sentence “Beethoven composed the Ode to Joy.”, we are expected to extract the triple <Beethoven, composed, Ode to Joy>. In this work, we systematically compare different neural network architectures and training approaches, and improve the performance of the currently best models on the OIE16 benchmark (Stanovsky and Dagan, 2016) by 0.421 F1 score and 0.420 AUC-PR, respectively, in our experiments (i.e., by more than 200% in both cases). Furthermore, we show that appropriate problem and loss formulations often affect the performance more than the network architecture.


pdf bib
A Surprisingly Robust Trick for the Winograd Schema Challenge
Vid Kocijan | Ana-Maria Cretu | Oana-Maria Camburu | Yordan Yordanov | Thomas Lukasiewicz
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

The Winograd Schema Challenge (WSC) dataset WSC273 and its inference counterpart WNLI are popular benchmarks for natural language understanding and commonsense reasoning. In this paper, we show that the performance of three language models on WSC273 consistently and robustly improves when fine-tuned on a similar pronoun disambiguation problem dataset (denoted WSCR). We additionally generate a large unsupervised WSC-like dataset. By fine-tuning the BERT language model both on the introduced and on the WSCR dataset, we achieve overall accuracies of 72.5% and 74.7% on WSC273 and WNLI, improving the previous state-of-the-art solutions by 8.8% and 9.6%, respectively. Furthermore, our fine-tuned models are also consistently more accurate on the “complex” subsets of WSC273, introduced by Trichelair et al. (2018).

pdf bib
WikiCREM: A Large Unsupervised Corpus for Coreference Resolution
Vid Kocijan | Oana-Maria Camburu | Ana-Maria Cretu | Yordan Yordanov | Phil Blunsom | Thomas Lukasiewicz
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Pronoun resolution is a major area of natural language understanding. However, large-scale training sets are still scarce, since manually labelling data is costly. In this work, we introduce WikiCREM (Wikipedia CoREferences Masked) a large-scale, yet accurate dataset of pronoun disambiguation instances. We use a language-model-based approach for pronoun resolution in combination with our WikiCREM dataset. We compare a series of models on a collection of diverse and challenging coreference resolution problems, where we match or outperform previous state-of-the-art approaches on 6 out of 7 datasets, such as GAP, DPR, WNLI, PDP, WinoBias, and WinoGender. We release our model to be used off-the-shelf for solving pronoun disambiguation.