Anaphora With Non-nominal Antecedents in Computational Linguistics: a Survey

Abstract

This article provides an extensive overview of the literature related to the phenomenon of non-nominal-antecedent anaphora (also known as abstract anaphora or discourse deixis), a type of anaphora in which an anaphor like “that” refers to an antecedent (marked in boldface) that is syntactically non-nominal, such as the first sentence in “It’s way too hot here. That’s why I’m moving to Alaska.” Annotating and automatically resolving these cases of anaphora is interesting in its own right because of the complexities involved in identifying non-nominal antecedents, which typically represent abstract objects such as events, facts, and propositions. There is also practical value in the resolution of non-nominal-antecedent anaphora, as this would help computational systems in machine translation, summarization, and question answering, as well as, conceivably, any other task dependent on some measure of text understanding. Most of the existing approaches to anaphora annotation and resolution focus on nominal-antecedent anaphora, classifying many of the cases where the antecedents are syntactically non-nominal as non-anaphoric. There has been some work done on this topic, but it remains scattered and difficult to collect and assess. With this article, we hope to bring together and synthesize work done in disparate contexts up to now in order to identify fundamental problems and draw conclusions from an overarching perspective. Having a good picture of the current state of the art in this field can help researchers direct their efforts to where they are most necessary. Because of the great variety of theoretical approaches that have been brought to bear on the problem, there is an equally diverse array of terminologies that are used to describe it, so we will provide an overview and discussion of these terminologies. We also describe the linguistic properties of non-nominal-antecedent anaphora, examine previous annotation efforts that have addressed this topic, and present the computational approaches that aim at resolving non-nominal-antecedent anaphora automatically. We close with a review of the remaining open questions in this area and some of our recommendations for future research.

Conceptual Graphs and Terminological Idiosyncrasy in UNCLOS and CBD

“…Expression in natural language makes frequent use of anaphoric relations and co-references, the resolution of which is essential for a good understanding of the text. This is for example the use of a pronoun which replaces a nominal antecedent, or the use of the referring word (pronoun, verb) which takes the place of a non-nominal antecedent, a source of more complex syntactic structures [47,48]. Anaphora resolution is performed here by setting a relation node between the antecedent (the replaced term) and the other term syntactically associated to the pronoun.…”

Speech Pauses and Pronominal Anaphors

“…The corpora annotated with abstract pronominal anaphora are only few (Kolhatkar et al, 2018), comprising the ARRAU corpus, which consists of both texts and transcriptions of dialogues (Poesio and Artstein, 2008). Part of the ARRAU corpus, the Wall Street Journal (WSJ) texts, has been used in the first benchmark for the resolution of tpngs anaphors in English (Marasovic et al, 2017).…”

Proceedings of the Second Workshop on Advances in Language and Vision Research

“…Extending the coreference annotation paradigm is thus the best bet although not a lot Textual coreference Annotated data for the coreference resolution task has mainly focused on news texts and concrete nouns, excluding reference to events and other coreferential relations such as bridging, deixis, and ambiguous items well documented in the linguistic literature but deemed infrequent or too difficult to process (Poesio, 2016). In contrast, there is a growing body of literature interested in phenomena beyond the nominal case (Kolhatkar et al, 2018;Nedoluzhko and Lapshinova-Koltunski, 2016), resulting in new, although still small in size, annotated corpora (Lapshinova-Koltunski et al, 2018;Zeldes, 2017;Uryupina et al, 2020).…”