Evaluating the Impact of a Hierarchical Discourse Representation on
Entity Coreference Resolution Performance
- URL: http://arxiv.org/abs/2104.10215v1
- Date: Tue, 20 Apr 2021 19:14:57 GMT
- Title: Evaluating the Impact of a Hierarchical Discourse Representation on
Entity Coreference Resolution Performance
- Authors: Sopan Khosla, James Fiacco, Carolyn Rose
- Abstract summary: In this work, we leverage automatically constructed discourse parse trees within a neural approach.
We demonstrate a significant improvement on two benchmark entity coreference-resolution datasets.
- Score: 3.7277082975620797
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Recent work on entity coreference resolution (CR) follows current trends in
Deep Learning applied to embeddings and relatively simple task-related
features. SOTA models do not make use of hierarchical representations of
discourse structure. In this work, we leverage automatically constructed
discourse parse trees within a neural approach and demonstrate a significant
improvement on two benchmark entity coreference-resolution datasets. We explore
how the impact varies depending upon the type of mention.
Related papers
- Enhancing Action Recognition by Leveraging the Hierarchical Structure of Actions and Textual Context [0.0]
We present a novel approach to improve action recognition by exploiting the hierarchical organization of actions.
Visual features are obtained from RGB and optical flow data, while text embeddings represent contextual information.
We also conduct an ablation study to assess the impact of different methods for integrating contextual and hierarchical data on action recognition performance.
arXiv Detail & Related papers (2024-10-28T17:59:35Z) - Coherent Entity Disambiguation via Modeling Topic and Categorical
Dependency [87.16283281290053]
Previous entity disambiguation (ED) methods adopt a discriminative paradigm, where prediction is made based on matching scores between mention context and candidate entities.
We propose CoherentED, an ED system equipped with novel designs aimed at enhancing the coherence of entity predictions.
We achieve new state-of-the-art results on popular ED benchmarks, with an average improvement of 1.3 F1 points.
arXiv Detail & Related papers (2023-11-06T16:40:13Z) - Speech Self-Supervised Representations Benchmarking: a Case for Larger
Probing Heads [32.45539981205672]
Self-supervised learning (SSL) leverages large datasets of unlabeled speech to reach impressive performance with reduced amounts of annotated data.
This study examines how benchmarking results are affected by changes in the probing head architecture.
arXiv Detail & Related papers (2023-08-28T09:49:48Z) - Probing Statistical Representations For End-To-End ASR [28.833851817220616]
This paper investigates cross-domain language model dependencies within transformer architectures using SVCCA.
It was found that specific neural representations within the transformer layers exhibit correlated behaviour which impacts recognition performance.
arXiv Detail & Related papers (2022-11-03T17:08:14Z) - Autoregressive Structured Prediction with Language Models [73.11519625765301]
We describe an approach to model structures as sequences of actions in an autoregressive manner with PLMs.
Our approach achieves the new state-of-the-art on all the structured prediction tasks we looked at.
arXiv Detail & Related papers (2022-10-26T13:27:26Z) - MINER: Improving Out-of-Vocabulary Named Entity Recognition from an
Information Theoretic Perspective [57.19660234992812]
NER model has achieved promising performance on standard NER benchmarks.
Recent studies show that previous approaches may over-rely on entity mention information, resulting in poor performance on out-of-vocabulary (OOV) entity recognition.
We propose MINER, a novel NER learning framework, to remedy this issue from an information-theoretic perspective.
arXiv Detail & Related papers (2022-04-09T05:18:20Z) - Layer-wise Analysis of a Self-supervised Speech Representation Model [26.727775920272205]
Self-supervised learning approaches have been successful for pre-training speech representation models.
Not much has been studied about the type or extent of information encoded in the pre-trained representations themselves.
arXiv Detail & Related papers (2021-07-10T02:13:25Z) - Enhancing the Generalization for Intent Classification and Out-of-Domain
Detection in SLU [70.44344060176952]
Intent classification is a major task in spoken language understanding (SLU)
Recent works have shown that using extra data and labels can improve the OOD detection performance.
This paper proposes to train a model with only IND data while supporting both IND intent classification and OOD detection.
arXiv Detail & Related papers (2021-06-28T08:27:38Z) - Structure-Regularized Attention for Deformable Object Representation [17.120035855774344]
Capturing contextual dependencies has proven useful to improve the representational power of deep neural networks.
Recent approaches that focus on modeling global context, such as self-attention and non-local operation, achieve this goal by enabling unconstrained pairwise interactions between elements.
We consider learning representations for deformable objects which can benefit from context exploitation by modeling the structural dependencies that the data intrinsically possesses.
arXiv Detail & Related papers (2021-06-12T03:10:17Z) - Keyphrase Extraction with Dynamic Graph Convolutional Networks and
Diversified Inference [50.768682650658384]
Keyphrase extraction (KE) aims to summarize a set of phrases that accurately express a concept or a topic covered in a given document.
Recent Sequence-to-Sequence (Seq2Seq) based generative framework is widely used in KE task, and it has obtained competitive performance on various benchmarks.
In this paper, we propose to adopt the Dynamic Graph Convolutional Networks (DGCN) to solve the above two problems simultaneously.
arXiv Detail & Related papers (2020-10-24T08:11:23Z) - Probing Linguistic Features of Sentence-Level Representations in Neural
Relation Extraction [80.38130122127882]
We introduce 14 probing tasks targeting linguistic properties relevant to neural relation extraction (RE)
We use them to study representations learned by more than 40 different encoder architecture and linguistic feature combinations trained on two datasets.
We find that the bias induced by the architecture and the inclusion of linguistic features are clearly expressed in the probing task performance.
arXiv Detail & Related papers (2020-04-17T09:17:40Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.