Coreference Resolution through a seq2seq Transition-Based System

• URL: http://arxiv.org/abs/2211.12142v1
• Date: Tue, 22 Nov 2022 10:17:50 GMT
• Title: Coreference Resolution through a seq2seq Transition-Based System
• Authors: Bernd Bohnet, Chris Alberti, Michael Collins
• Abstract summary: We present a coreference resolution system that uses a text-to-text paradigm to predict mentions and links jointly. We obtain state-of-the-art accuracy on the CoNLL-2012 datasets with 83.3 F1-score for English. We get substantially higher zero-shot F1-scores for 3 out of 4 languages than previous approaches.
• Score: 10.187353923159613
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Most recent coreference resolution systems use search algorithms over possible spans to identify mentions and resolve coreference. We instead present a coreference resolution system that uses a text-to-text (seq2seq) paradigm to predict mentions and links jointly. We implement the coreference system as a transition system and use multilingual T5 as an underlying language model. We obtain state-of-the-art accuracy on the CoNLL-2012 datasets with 83.3 F1-score for English (a 2.3 higher F1-score than previous work (Dobrovolskii, 2021)) using only CoNLL data for training, 68.5 F1-score for Arabic (+4.1 higher than previous work) and 74.3 F1-score for Chinese (+5.3). In addition we use the SemEval-2010 data sets for experiments in the zero-shot setting, a few-shot setting, and supervised setting using all available training data. We get substantially higher zero-shot F1-scores for 3 out of 4 languages than previous approaches and significantly exceed previous supervised state-of-the-art results for all five tested languages.

Related papers

• DeMuX: Data-efficient Multilingual Learning [57.37123046817781]
  DEMUX is a framework that prescribes exact data-points to label from vast amounts of unlabelled multilingual data. Our end-to-end framework is language-agnostic, accounts for model representations, and supports multilingual target configurations.
  arXiv  Detail & Related papers  (2023-11-10T20:09:08Z)
• An Open Dataset and Model for Language Identification [84.15194457400253]
  We present a LID model which achieves a macro-average F1 score of 0.93 and a false positive rate of 0.033 across 201 languages. We make both the model and the dataset available to the research community.
  arXiv  Detail & Related papers  (2023-05-23T08:43:42Z)
• GMNLP at SemEval-2023 Task 12: Sentiment Analysis with Phylogeny-Based Adapters [35.36372251094268]
  This report describes GMU's sentiment analysis system for the SemEval-2023 shared task AfriSenti-SemEval. Our approach uses models with AfroXLMR-large, a pre-trained multilingual language model trained on African languages. Our system achieves the best F1-score on track 5: Amharic, with 6.2 points higher F1-score than the second-best performing system on this track.
  arXiv  Detail & Related papers  (2023-04-25T16:39:51Z)
• Ensemble Transfer Learning for Multilingual Coreference Resolution [60.409789753164944]
  A problem that frequently occurs when working with a non-English language is the scarcity of annotated training data. We design a simple but effective ensemble-based framework that combines various transfer learning techniques. We also propose a low-cost TL method that bootstraps coreference resolution models by utilizing Wikipedia anchor texts.
  arXiv  Detail & Related papers  (2023-01-22T18:22:55Z)
• T5Score: Discriminative Fine-tuning of Generative Evaluation Metrics [94.69907794006826]
  We present a framework that combines the best of both worlds, using both supervised and unsupervised signals from whatever data we have available. We operationalize this idea by training T5Score, a metric that uses these training signals with mT5 as the backbone. T5Score achieves the best performance on all datasets against existing top-scoring metrics at the segment level.
  arXiv  Detail & Related papers  (2022-12-12T06:29:04Z)
• AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages [75.08199398141744]
  We present AmericasNLI, an extension of XNLI (Conneau et al.), to 10 indigenous languages of the Americas. We conduct experiments with XLM-R, testing multiple zero-shot and translation-based approaches. We find that XLM-R's zero-shot performance is poor for all 10 languages, with an average performance of 38.62%.
  arXiv  Detail & Related papers  (2021-04-18T05:32:28Z)
• Explicit Alignment Objectives for Multilingual Bidirectional Encoders [111.65322283420805]
  We present a new method for learning multilingual encoders, AMBER (Aligned Multilingual Bi-directional EncodeR) AMBER is trained on additional parallel data using two explicit alignment objectives that align the multilingual representations at different granularities. Experimental results show that AMBER obtains gains of up to 1.1 average F1 score on sequence tagging and up to 27.3 average accuracy on retrieval over the XLMR-large model.
  arXiv  Detail & Related papers  (2020-10-15T18:34:13Z)
• Phonemer at WNUT-2020 Task 2: Sequence Classification Using COVID Twitter BERT and Bagging Ensemble Technique based on Plurality Voting [0.0]
  We develop a system that automatically identifies whether an English Tweet related to the novel coronavirus (COVID-19) is informative or not. Our final approach achieved an F1-score of 0.9037 and we were ranked sixth overall with F1-score as the evaluation criteria.
  arXiv  Detail & Related papers  (2020-10-01T10:54:54Z)
• NAYEL at SemEval-2020 Task 12: TF/IDF-Based Approach for Automatic Offensive Language Detection in Arabic Tweets [0.0]
  The proposed system aims to automatically identify the Offensive Language in Arabic Tweets. A machine learning based approach has been used to design our system. The best performed system and the system in the last rank reported 90.17% and 44.51% f1-score on test set respectively.
  arXiv  Detail & Related papers  (2020-07-27T07:44:00Z)
• Tha3aroon at NSURL-2019 Task 8: Semantic Question Similarity in Arabic [5.214494546503266]
  We describe our team's effort on the semantic text question similarity task of NSURL 2019. Our top performing system utilizes several innovative data augmentation techniques to enlarge the training data. It takes ELMo pre-trained contextual embeddings of the data and feeds them into an ON-LSTM network with self-attention.
  arXiv  Detail & Related papers  (2019-12-28T20:11:33Z)

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.