Jointly Optimized Neural Coreference Resolution with Mutual Attention

Ma, Jie; Li, Jun; Li, Yufei; Hu, Xin; Pan, Yudai; Sun, Shen; Lin, Qika

doi:10.1145/3336191.3371787

Cited by 7 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, CEAF e φ4 [28] and CoN LL [36] in compliance with other studies on coreference resolution [20,29,24]. To obtain robust results, we apply five-fold cross-validation, according to the data splits given by Brack et al [5], and report averaged results.…”

Section: Automatic Coreference Resolutionmentioning

confidence: 92%

“…For computational efficiency, candidate spans and antecedents are pruned during training and inference. Joshi et al [20] enhance Lee et al's model with BERT-based word embeddings [13], while Ma et al [29] improve the model with better attention mechanisms and loss functions.…”

Section: Approaches For Coreference Resolutionmentioning

confidence: 99%

“…Message Understanding Conference (MUC-7) [31], Automatic Content Extraction (ACE05) [14], or OntoNotes 5.0 [37]. The OntoNotes 5.0 dataset [37] is the largest one and is used in many benchmark experiments for coreference resolution systems [24,20,29].…”

Section: Corpora For Coreference Resolution In Research Papersmentioning

confidence: 99%

See 2 more Smart Citations

Coreference Resolution in Research Papers from Multiple Domains

Brack¹,

Müller²,

Hoppe³

et al. 2021

Preprint

View full text Add to dashboard Cite

Coreference resolution is essential for automatic text understanding to facilitate high-level information retrieval tasks such as text summarisation or question answering. Previous work indicates that the performance of state-ofthe-art approaches (e.g. based on BERT) noticeably declines when applied to scientific papers. In this paper, we investigate the task of coreference resolution in research papers and subsequent knowledge graph population. We present the following contributions: (1) We annotate a corpus for coreference resolution that comprises 10 different scientific disciplines from Science, Technology, and Medicine (STM); (2) We propose transfer learning for automatic coreference resolution in research papers; (3) We analyse the impact of coreference resolution on knowledge graph (KG) population; (4) We release a research KG that is automatically populated from 55,485 papers in 10 STM domains. Comprehensive experiments show the usefulness of the proposed approach. Our transfer learning approach considerably outperforms state-of-the-art baselines on our corpus with an F1 score of 61.4 (+11.0), while the evaluation against a gold standard KG shows that coreference resolution improves the quality of the populated KG significantly with an F1 score of 63.5 (+21.8).

show abstract

Section: Automatic Coreference Resolutionmentioning

confidence: 92%

Section: Approaches For Coreference Resolutionmentioning

confidence: 99%

See 1 more Smart Citation

Coreference Resolution in Research Papers from Multiple Domains

Brack¹,

Müller²,

Hoppe³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…As INE always refer to named entities, pronouns refer to referential lexemes or named entities in texts. Anaphora resolution (or coreference resolution) aims at solving anaphora and linking, for example, pronouns with the named entities they refer to (Mitkov, 2014;Ma et al, 2020). Coreference and anaphora resolution for French have been studied in Guenoune et al (2020).…”

Section: Anaphora Resolutionmentioning

confidence: 99%

Indirectly Named Entity Recognition

Kauffmann

Rey

Atanassova

et al. 2021

J. Comp. Assist. Linguist. Res.

View full text Add to dashboard Cite

We define here indirectly named entities, as a term to denote multiword expressions referring to known named entities by means of periphrasis. While named entity recognition is a classical task in natural language processing, little attention has been paid to indirectly named entities and their treatment. In this paper, we try to address this gap, describing issues related to the detection and understanding of indirectly named entities in texts. We introduce a proof of concept for retrieving both lexicalised and non-lexicalised indirectly named entities in French texts. We also show example cases where this proof of concept is applied, and discuss future perspectives. We have initiated the creation of a first lexicon of 712 indirectly named entity entries that is available for future research.

show abstract

“…A candidate evidence span e i,k ∈ E i E to q i is represented by its start START(k) and end END(k) indexes respectively following (Ma et al, 2020), where E i represents the candidate evidence span set of…”

Section: Task Formulationmentioning

confidence: 99%

XTQA: Span-Level Explanations of the Textbook Question Answering

Ma¹,

Chai²,

Li³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Textbook Question Answering (TQA) is a task that one should answer a diagram/nondiagram question given a large multi-modal context consisting of abundant essays and diagrams. We argue that the explainability of this task should place students as a key aspect to be considered. To address this issue, we devise a novel architecture towards span-level eXplanations of the TQA (XTQA). It can provide not only the answers but also the span-level evidences to choose them for students based on our proposed coarse-to-fine grained algorithm. The algorithm first coarsely chooses top M paragraphs relevant to questions using the TF-IDF method, and then chooses top K evidence spans finely from all candidate spans within these paragraphs by computing the information gain of each span to questions. Experimental results show that our method significantly improves the state-of-the-art performance compared with baselines. The source code is available at https://github.com/keepsmile-001/opentqa.

show abstract

Jointly Optimized Neural Coreference Resolution with Mutual Attention

Cited by 7 publications

References 13 publications

Coreference Resolution in Research Papers from Multiple Domains

Coreference Resolution in Research Papers from Multiple Domains

Indirectly Named Entity Recognition

XTQA: Span-Level Explanations of the Textbook Question Answering

Contact Info

Product

Resources

About