Topic
Coreference
About: Coreference is a research topic. Over the lifetime, 2122 publications have been published within this topic receiving 60353 citations.
Papers published on a yearly basis
1 / 2
Papers
TL;DR: This chapter discusses the theoretical and empirical literature that addresses aging and discourse comprehension and a series of five studies guided by a particular working memory viewpoint regarding the formation of inferences during discourse processing are described.
Abstract: Publisher Summary This chapter discusses the theoretical and empirical literature that addresses aging and discourse comprehension. A series of five studies guided by a particular working memory viewpoint regarding the formation of inferences during discourse processing is described in the chapter. Compensatory strategies may be used with different degrees of likelihood across the life span largely as a function of efficiency with which inhibitory mechanisms function because these largely determine the facility with which memory can be searched. The consequences for discourse comprehension in particular may be profound because the establishment of a coherent representation of a message hinges on the timely retrieval of information necessary to establish coreference among certain critical ideas. Discourse comprehension is an ideal domain for assessing limited capacity frameworks because most models of discourse processing assume that multiple components, demanding substantially different levels of cognitive resources, are involved. For example, access to a lexical representation from either a visual array or an auditory message is virtually capacity free.
3,698 citations
7 Dec 2015
TL;DR: This paper presents Flickr30K Entities, which augments the 158k captions from Flickr30k with 244k coreference chains linking mentions of the same entities in images, as well as 276k manually annotated bounding boxes corresponding to each entity, essential for continued progress in automatic image description and grounded language understanding.
Abstract: The Flickr30k dataset has become a standard benchmark for sentence-based image description. This paper presents Flickr30k Entities, which augments the 158k captions from Flickr30k with 244k coreference chains linking mentions of the same entities in images, as well as 276k manually annotated bounding boxes corresponding to each entity. Such annotation is essential for continued progress in automatic image description and grounded language understanding. We present experiments demonstrating the usefulness of our annotations for text-to-image reference resolution, or the task of localizing textual entity mentions in an image, and for bidirectional image-sentence retrieval. These experiments confirm that we can further improve the accuracy of state-of-the-art retrieval methods by training with explicit region-to-phrase correspondence, but at the same time, they show that accurately inferring this correspondence given an image and a caption remains really challenging.
2,021 citations
11 Jun 2019
TL;DR: The authors showed that BERT's attention heads exhibit patterns such as attending to delimiter tokens, specific positional offsets, or broadly attending over the whole sentence, with heads in the same layer often exhibiting similar behaviors.
Abstract: Large pre-trained neural networks such as BERT have had great recent success in NLP, motivating a growing body of research investigating what aspects of language they are able to learn from unlabeled data. Most recent analysis has focused on model outputs (e.g., language model surprisal) or internal vector representations (e.g., probing classifiers). Complementary to these works, we propose methods for analyzing the attention mechanisms of pre-trained models and apply them to BERT. BERT’s attention heads exhibit patterns such as attending to delimiter tokens, specific positional offsets, or broadly attending over the whole sentence, with heads in the same layer often exhibiting similar behaviors. We further show that certain attention heads correspond well to linguistic notions of syntax and coreference. For example, we find heads that attend to the direct objects of verbs, determiners of nouns, objects of prepositions, and coreferent mentions with remarkably high accuracy. Lastly, we propose an attention-based probing classifier and use it to further demonstrate that substantial syntactic information is captured in BERT’s attention.
1,396 citations
TL;DR: The learning approach to coreference resolution of noun phrases in unrestricted text is presented, indicating that on the general noun phrase coreference task, the learning approach holds promise and achieves accuracy comparable to that of nonlearning approaches.
Abstract: In this paper, we present a learning approach to coreference resolution of noun phrases in unrestricted text. The approach learns from a small, annotated corpus and the task includes resolving not just a certain type of noun phrase (e.g., pronouns) but rather general noun phrases. It also does not restrict the entity types of the noun phrases; that is, coreference is assigned whether they are of "organization," "person," or other types. We evaluate our approach on common data sets (namely, the MUC-6 and MUC-7 coreference corpora) and obtain encouraging results, in-dicating that on the general noun phrase coreference task, the learning approach holds promise and achieves accuracy comparable to that of nonlearning approaches. Our system is the first learning-based system that offers performance comparable to that of state-of-the-art nonlearning systems on these data sets.
1,157 citations
TL;DR: The CoQA dataset as mentioned in this paper contains 127k questions with answers, obtained from 8k conversations about text passages from seven diverse domains, and the answers are free-form text with their corresponding evidence highlighted in the passage.
Abstract: Humans gather information through conversations involving a series of interconnected questions and answers. For machines to assist in information gathering, it is therefore essential to enable them to answer conversational questions. We introduce CoQA, a novel dataset for building Conversational Question Answering systems. Our dataset contains 127k questions with answers, obtained from 8k conversations about text passages from seven diverse domains. The questions are conversational, and the answers are free-form text with their corresponding evidence highlighted in the passage. We analyze CoQA in depth and show that conversational questions have challenging phenomena not present in existing reading comprehension datasets, e.g., coreference and pragmatic reasoning. We evaluate strong dialogue and reading comprehension models on CoQA. The best system obtains an F1 score of 65.4%, which is 23.4 points behind human performance (88.8%), indicating there is ample room for improvement. We present CoQA as a challenge to the community at https://stanfordnlp.github.io/coqa
1,068 citations
Related Topics (5)
Performance Metrics
| Year | Papers |
|---|---|
| 2025 | 34 |
| 2024 | 65 |
| 2023 | 172 |
| 2022 | 212 |
| 2021 | 173 |
| 2020 | 156 |