What kinds of errors do reference resolution models make and what can we learn from them? (2022.findings-naacl)
Copied to clipboard
| Challenge: | Referring resolution is the task of identifying the referent of a natural language expression. |
| Approach: | They propose a model that restores weakening of the spatial natural constraints on referring expressions by evaluating their performance on different datasets. |
| Outcome: | The proposed model shows improved performance on the most challenging kinds of referring expressions on different datasets. |
Similar Papers
Visual Referring Expression Recognition: What Do Systems Actually Learn? (N18-2)
Copied to clipboard
| Challenge: | Existing systems for referring expression recognition ignore linguistic structure, instead relying on shallow correlations introduced by unintended biases in the data selection and annotation process. |
| Approach: | They propose to use a system trained on the input image without the input referring expression to achieve a precision of 71.2% in top-2 predictions. |
| Outcome: | The proposed model can achieve 71.2% accuracy on the input image without the input referring expression and 84.2% on the object category given the input. |
Bridging Resolution: A Survey of the State of the Art (2020.coling-main)
Copied to clipboard
| Challenge: | bridging resolution is an anaphora resolution task that is less studied than entity coreference resolution. |
| Approach: | This paper presents a survey of the current state of research on bridging resolution . it identifies and resolves bridling/associative anaphors, which are anamorphic references to non-identical associated antecedents. |
| Outcome: | The proposed task is more difficult than entity coreference resolution because of the lack of annotated corpora and lack of standardized evaluation protocols. |
Social Norms Guide Reference Resolution (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing tools for natural language resolution fail to handle ambiguous referents . ambiguity arises when the language is underspecified or there are multiple candidate referent. |
| Approach: | They investigate how pragmatic modulators outside of the linguistic content are critical for correct interpretation of referents in underspecified contexts. |
| Outcome: | The proposed method can be used to resolve referents in human environments. |
Conundrums in Entity Coreference Resolution: Making Sense of the State of the Art (2020.emnlp-main)
Copied to clipboard
| Challenge: | despite significant progress on entity coreference resolution, there is a general lack of understanding of what has been improved. |
| Approach: | They present an empirical analysis of entity coreference resolvers to provide an understanding of what has been improved. |
| Outcome: | The proposed model improves the performance of entity coreference resolvers. |
End-to-End Neural Bridging Resolution (2022.coling-1)
Copied to clipboard
| Challenge: | state-of-the-art resolvers for bridging resolution are weaker than entity coreference resolution. |
| Approach: | They evaluate bridging resolvers in an end-to-end setting and strengthen them with better encoders . they also try to gain a better understanding of them through perturbation experiments . |
| Outcome: | bridging resolvers are evaluated in an end-to-end setting and strengthened with better encoders . bribridging resolution is the task of identifying briating anaphors and linking them to their antecedents - a paper by the journal bribing resolution argues . |
Using Lexical Alignment and Referring Ability to Address Data Sparsity in Situated Dialog Reference Resolution (D18-1)
Copied to clipboard
| Challenge: | Existing work on exophoric reference resolution for situated dialogs is limited to a literary model . et al., 2010) showed that it is possible to improve dialogic reference resolving by incrementally adapting word semantic model parameters to idiosyncratic language use by dyad partners. |
| Approach: | They propose to use a logistic regression model to adapt a model to idiosyncratic language . they first train a log regression model and then use it to learn the general referring ability of each word . |
| Outcome: | The proposed methods improve dialogic reference resolution without annotation of referring expressions even with little background data. |
Probing for Referential Information in Language Models (2020.acl-main)
Copied to clipboard
| Challenge: | Neural network-based language models (LMs) have been shown to learn relevant properties of language without being explicitly trained for them. |
| Approach: | They extend their previous work to analyze whether language models capture anaphoric relations and pronoun-antecedent relations in English. |
| Outcome: | The Transformer outperforms the LSTM in all analyses. |
Bridging resolution: Task definition, corpus resources and rule-based experiments (C18-1)
Copied to clipboard
| Challenge: | Recent work on bridging resolution has been based on the corpus ISNotes, as this was the only corpus available with unrestricted bridling annotations. |
| Approach: | They propose a rule-based system to resolve bridging annotations in ISNotes corpus and apply it to new corpora. |
| Outcome: | The proposed system achieves state-of-the-art performance on ISNotes corpus, but low performance on in-domain corpora. |
Resolving Indirect Referring Expressions for Entity Selection (2023.acl-long)
Copied to clipboard
| Challenge: | Recent advances in language modeling have enabled new conversational systems. |
| Approach: | They propose to use a dataset of indirect referring expressions to solve the problem of reference resolution when people use natural expressions . they propose to model the problem using 42K indirect referred expressions across three domains and a public dataset of entity pairs and utterances. |
| Outcome: | The proposed models achieve 82%-87% accuracy in realistic settings, while reasonable invites further advances. |
CK-Transformer: Commonsense Knowledge Enhanced Transformers for Referring Expression Comprehension (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing frameworks for referring expression comprehension with commonsense knowledge are lacking in the field of multimodal referring . |
| Approach: | They propose a framework for commonsense knowledge Enhanced Transformers which integrates commonsensible knowledge into representations of objects in an image. |
| Outcome: | The proposed framework improves on the existing state of the art in referring expression comprehension with commonsense knowledge (CK-Transformer) it achieves 3.14% accuracy over the existing framework. |