CorPipe at CRAC 2024: Predicting Zero Mentions from Raw Text

• URL: http://arxiv.org/abs/2410.02756v2
• Date: Sat, 09 Nov 2024 23:24:14 GMT
• Title: CorPipe at CRAC 2024: Predicting Zero Mentions from Raw Text
• Abstract summary: We present CorPipe 24, the winning entry to the CRAC 2024 Shared Task on Multilingual Coreference Resolution. In this third iteration of the task, a novel objective is to also predict empty nodes needed for zero coreference mentions. In both settings, CorPipe surpasses other participants by a large margin of 3.9 and 2.8 percent points, respectively.
• Score: 1.2772632966631616
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present CorPipe 24, the winning entry to the CRAC 2024 Shared Task on Multilingual Coreference Resolution. In this third iteration of the shared task, a novel objective is to also predict empty nodes needed for zero coreference mentions (while the empty nodes were given on input in previous years). This way, coreference resolution can be performed on raw text. We evaluate two model variants: a~two-stage approach (where the empty nodes are predicted first using a pretrained encoder model and then processed together with sentence words by another pretrained model) and a single-stage approach (where a single pretrained encoder model generates empty nodes, coreference mentions, and coreference links jointly). In both settings, CorPipe surpasses other participants by a large margin of 3.9 and 2.8 percent points, respectively. The source code and the trained model are available at https://github.com/ufal/crac2024-corpipe.

Related papers

• Language Models Can Control Their Own Attention [42.07765767561011]
  We introduce Declarative Attention (DA), a protocol that elicits the model to declare where it needs to attend within its chain-of-thought.<n>DA significantly reduces total attended tokens during decoding (52.0%, 31.1%) with modest accuracy drops (1.27pp, 2.75pp) that shrink with model scale.
  arXiv  Detail & Related papers  (2026-09-02T15:43:38Z)
• CorPipe at CRAC 2026: Empty Nodes and Cross-Lingual Transfer in Multilingual Coreference Resolution [0.6671865055671308]
  CorPipe 26 is an improved version of CorPipe 25, with a new variant predicting empty nodes together with mentions and coreference links in a single model.<n>Our system outperforms all other submissions in the LLM track by 2.8 percent points and all submissions in the unconstrained track by 9.5 percent points.
  arXiv  Detail & Related papers  (2026-05-28T16:01:03Z)
• CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution [0.6671865055671308]
  CorPipe 25 is the winning entry in the CRAC 2025 Shared Task on Multilingual Coreference Resolution.<n>Our system significantly outperforms all other submissions in both the LLM and unconstrained tracks by a substantial margin of 8 percentage points.
  arXiv  Detail & Related papers  (2025-09-22T14:51:37Z)
• Self-Consistent Decoding for More Factual Open Responses [28.184313177333642]
  "Sample & Select" improves factuality by a 30% relative margin against decoders of DoLA, P-CRR, and S-CRR. We collect human verifications of the generated summaries, confirming the factual superiority of our method.
  arXiv  Detail & Related papers  (2024-03-01T17:31:09Z)
• Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models [121.0693322732454]
  This paper proposes a textbfCraFT' approach for fine-tuning black-box vision-language models to downstream tasks. CraFT comprises two modules, a prompt generation module for learning text prompts and a prediction refinement module for enhancing output predictions in residual style. Experiments on few-shot classification over 15 datasets demonstrate the superiority of CraFT.
  arXiv  Detail & Related papers  (2024-02-06T14:53:19Z)
• CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution [36.30158138035512]
  We present a benchmark consisting of 800 Python functions (3-13 lines) Each function comes with an input-output pair, leading to two natural tasks: input prediction and output prediction. We show that simple CoT and fine-tuning schemes can improve performance on our benchmark but remain far from solving it.
  arXiv  Detail & Related papers  (2024-01-05T20:53:51Z)
• Object Recognition as Next Token Prediction [99.40793702627396]
  We present an approach to pose object recognition as next token prediction. The idea is to apply a language decoder that auto-regressively predicts the text tokens from image embeddings to form labels.
  arXiv  Detail & Related papers  (2023-12-04T18:58:40Z)
• ÚFAL CorPipe at CRAC 2023: Larger Context Improves Multilingual Coreference Resolution [1.2772632966631616]
  We present CorPipe, the winning entry in the CRAC 2023 Shared Task on Multilingual Coreference Resolution. Our system is an improved version of our earlier multilingual coreference pipeline, and it surpasses other participants by a large margin of 4.5 percent points.
  arXiv  Detail & Related papers  (2023-11-24T10:15:34Z)
• 1st Place Solution of The Robust Vision Challenge (RVC) 2022 Semantic Segmentation Track [67.56316745239629]
  This report describes the winning solution to the semantic segmentation task of the Robust Vision Challenge on ECCV 2022. Our method adopts the FAN-B-Hybrid model as the encoder and uses Segformer as the segmentation framework. The proposed method could serve as a strong baseline for the multi-domain segmentation task and benefit future works.
  arXiv  Detail & Related papers  (2022-10-23T20:52:22Z)
• Conformal Predictor for Improving Zero-shot Text Classification Efficiency [37.745518881553416]
  We reduce the average inference time for NLI- and NSP-based models by 25.6% and 22.2% respectively. With a suitable CP for each dataset, we reduce the average inference time for NLI- and NSP-based models by 25.6% and 22.2% respectively.
  arXiv  Detail & Related papers  (2022-10-23T05:19:50Z)
• Unsupervised and Few-shot Parsing from Pretrained Language Models [56.33247845224995]
  We propose an Unsupervised constituent Parsing model that calculates an Out Association score solely based on the self-attention weight matrix learned in a pretrained language model. We extend the unsupervised models to few-shot parsing models that use a few annotated trees to learn better linear projection matrices for parsing. Our few-shot parsing model FPIO trained with only 20 annotated trees outperforms a previous few-shot parsing method trained with 50 annotated trees.
  arXiv  Detail & Related papers  (2022-06-10T10:29:15Z)
• Progressive End-to-End Object Detection in Crowded Scenes [96.92416613336096]
  Previous query-based detectors suffer from two drawbacks: first, multiple predictions will be inferred for a single object, typically in crowded scenes; second, the performance saturates as the depth of the decoding stage increases. We propose a progressive predicting method to address the above issues. Specifically, we first select accepted queries to generate true positive predictions, then refine the rest noisy queries according to the previously accepted predictions. Experiments show that our method can significantly boost the performance of query-based detectors in crowded scenes.
  arXiv  Detail & Related papers  (2022-03-15T06:12:00Z)
• Tag and Correct: Question aware Open Information Extraction with Two-stage Decoding [73.24783466100686]
  Question Open IE takes question and passage as inputs, outputting an answer which contains a subject, a predicate, and one or more arguments. The semistructured answer has two advantages which are more readable and falsifiable compared to span answer. One is an extractive method which extracts candidate answers from the passage with the Open IE model, and ranks them by matching with questions. The other is the generative method which uses a sequence to sequence model to generate answers directly.
  arXiv  Detail & Related papers  (2020-09-16T00:58:13Z)
• Pre-training for Abstractive Document Summarization by Reinstating Source Text [105.77348528847337]
  This paper presents three pre-training objectives which allow us to pre-train a Seq2Seq based abstractive summarization model on unlabeled text. Experiments on two benchmark summarization datasets show that all three objectives can improve performance upon baselines.
  arXiv  Detail & Related papers  (2020-04-04T05:06:26Z)
• Parallel sequence tagging for concept recognition [0.0]
  Named Entity Recognition (NER) and Normalisation (NEN) are core components of any text-mining system for biomedical texts. In a traditional concept-recognition pipeline, these tasks are combined in a serial way, which is inherently prone to error propagation from NER to NEN. We propose a parallel architecture, where both NER and NEN are modeled as a sequence-labeling task, operating directly on the source text.
  arXiv  Detail & Related papers  (2020-03-16T19:41:07Z)

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.