Bridging Anaphora Resolution as Question Answering

• URL: http://arxiv.org/abs/2004.07898v3
• Date: Wed, 24 Jun 2020 22:28:10 GMT
• Title: Bridging Anaphora Resolution as Question Answering
• Authors: Yufang Hou
• Abstract summary: We cast bridging anaphora resolution as question answering based on context. We present a question answering framework (BARQA) for this task. We propose a novel method to generate a large amount of "quasi-bridging" training data.
• Score: 10.81197069967052
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most previous studies on bridging anaphora resolution (Poesio et al., 2004; Hou et al., 2013b; Hou, 2018a) use the pairwise model to tackle the problem and assume that the gold mention information is given. In this paper, we cast bridging anaphora resolution as question answering based on context. This allows us to find the antecedent for a given anaphor without knowing any gold mention information (except the anaphor itself). We present a question answering framework (BARQA) for this task, which leverages the power of transfer learning. Furthermore, we propose a novel method to generate a large amount of "quasi-bridging" training data. We show that our model pre-trained on this dataset and fine-tuned on a small amount of in-domain dataset achieves new state-of-the-art results for bridging anaphora resolution on two bridging corpora (ISNotes (Markert et al., 2012) and BASHI (Roesiger, 2018)).

Related papers

• Large Language Models Meet Knowledge Graphs to Answer Factoid Questions [57.47634017738877]
  We propose a method for exploring pre-trained Text-to-Text Language Models enriched with additional information from Knowledge Graphs. We procure easily interpreted information with Transformer-based models through the linearization of the extracted subgraphs. Final re-ranking of the answer candidates with the extracted information boosts Hits@1 scores of the pre-trained text-to-text language models by 4-6%.
  arXiv  Detail & Related papers  (2023-10-03T15:57:00Z)
• Conjunct Resolution in the Face of Verbal Omissions [51.220650412095665]
  We propose a conjunct resolution task that operates directly on the text and makes use of a split-and-rephrase paradigm in order to recover the missing elements in the coordination structure. We curate a large dataset, containing over 10K examples of naturally-occurring verbal omissions with crowd-sourced annotations. We train various neural baselines for this task, and show that while our best method obtains decent performance, it leaves ample space for improvement.
  arXiv  Detail & Related papers  (2023-05-26T08:44:02Z)
• TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack [93.50174324435321]
  We present Twin Answer Sentences Attack (TASA), an adversarial attack method for question answering (QA) models. TASA produces fluent and grammatical adversarial contexts while maintaining gold answers.
  arXiv  Detail & Related papers  (2022-10-27T07:16:30Z)
• Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge [82.5582220249183]
  We propose a novel open-domain question answering (ODQA) framework for answering single/multi-hop questions across heterogeneous knowledge sources. Unlike previous methods that solely rely on the retriever for gathering all evidence in isolation, our intermediary performs a chain of reasoning over the retrieved set. Our system achieves competitive performance on two ODQA datasets, OTT-QA and NQ, against tables and passages from Wikipedia.
  arXiv  Detail & Related papers  (2022-10-22T03:21:32Z)
• End-to-end Neural Information Status Classification [17.976752792350933]
  We propose an end-to-end neural approach for information status classification. During the inference time, our system takes a raw text as the input and generates mentions together with their information status. Our system achieves competitive results on bridging anaphora recognition compared to the previous state-of-the-art system.
  arXiv  Detail & Related papers  (2021-09-06T21:44:11Z)
• Reference-based Weak Supervision for Answer Sentence Selection using Web Data [87.18646699292293]
  We introduce Reference-based Weak Supervision (RWS), a fully automatic large-scale data pipeline. RWS harvests high-quality weakly-supervised answers from abundant Web data. Our experiments indicate that the produced data consistently bolsters TANDA.
  arXiv  Detail & Related papers  (2021-04-18T19:41:17Z)
• Adaptive Active Learning for Coreference Resolution [37.261220564076964]
  Recent developments in incremental coreference resolution allow for a novel approach to active learning in this setting. By lowering the data barrier for coreference, coreference resolvers can rapidly adapt to a series of previously unconsidered domains.
  arXiv  Detail & Related papers  (2021-04-15T17:21:51Z)
• Stay Together: A System for Single and Split-antecedent Anaphora Resolution [19.98823717287972]
  Split-antecedent anaphora is rarer and more complex to resolve than single-antecedent anaphora. We introduce a system that resolves both single and split-antecedent anaphors, and evaluate it in a more realistic setting.
  arXiv  Detail & Related papers  (2021-04-12T10:01:08Z)
• Free the Plural: Unrestricted Split-Antecedent Anaphora Resolution [23.843305521306227]
  We introduce the first model for unrestricted resolution of split-antecedent anaphors. We show that we can substantially improve its performance by addressing the sparsity issue. Evaluation on the gold annotated ARRAU corpus shows that the out best model uses a combination of three auxiliary corpora.
  arXiv  Detail & Related papers  (2020-10-31T11:21:39Z)
• ClarQ: A large-scale and diverse dataset for Clarification Question Generation [67.1162903046619]
  We devise a novel bootstrapping framework that assists in the creation of a diverse, large-scale dataset of clarification questions based on postcomments extracted from stackexchange. We quantitatively demonstrate the utility of the newly created dataset by applying it to the downstream task of question-answering. We release this dataset in order to foster research into the field of clarification question generation with the larger goal of enhancing dialog and question answering systems.
  arXiv  Detail & Related papers  (2020-06-10T17:56:50Z)

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.