Is Incoherence Surprising? Targeted Evaluation of Coherence Prediction from Language Models

By Anne Beyer, Sharid Lo'aiciga, David Schlangen. 2021

25 citations recorded by the source corpus.

Coherent discourse is distinguished from a mere collection of utterances by the satisfaction of a diverse set of constraints, for example choice of expression, logical relation between denoted events, and implicit compatibility with world-knowledge. Do neural language models encode such constraints? We design an extendable set of test suites addressing different aspects of discourse and dialogue coherence. Unlike most previous coherence evaluation studies, we address specific linguistic devices beyond sentence order perturbations, which allow for a more fine-grained analysis of what constitutes coherence and what neural models trained on a language modelling objective are capable of encoding. Extending the targeted evaluation paradigm for neural language models (Marvin and Linzen, 2018) to phenomena beyond syntax, we show that this paradigm is equally suited to evaluate linguistic qualities that contribute to the notion of coherence.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Pascale Fung
2. Andrea Madotto
3. Wenliang Dai
4. Nayeon Lee
5. Yan Xu
6. Etsuko Ishii
7. Ziwei Ji
8. Dan Su

In Natural Language Processing

1. Pascale Fung
2. Nayeon Lee
3. Andrea Madotto
4. Etsuko Ishii
5. Yejin Bang
6. Yan Xu
7. Rita Frieske
8. Dan Su

Citations in the corpus

• Survey of Hallucination in Natural Language Generation (2022, background): “Two possible types of inconsistency occur in open-domain dialogue generation: (1) self-inconsistency [147, 159] or incoherence [8, 29] among the system utterances, such as when the system contradicts its previous utterance; (2) external inconsistency with an external source, such as factually incorr”
• Explaining Dialogue Evaluation Metrics using Adversarial Behavioral Analysis (2022, background): “Beyer et al. (2021a); Pishdad et al. (2020) both rely on this concept of calculating surprisal but use pairs of coherent and in-coherent language uses.”