paper-with-me

Papers

Active Learning and Multi-label Classification for Ellipsis and Coreference Detection in Conversational Question-Answering

2022-07-07 · Quentin Brabant, Lina Maria Rojas-Barahona, Claire Gardent

In human conversations, ellipsis and coreference are commonly occurring linguistic phenomena. Although these phenomena are a mean of making human-machine conversations more fluent and natural, only few dialogue corpora contain explicit indications on which turns contain ellipses and/or coreferences. In this paper we address the task of automatically detecting ellipsis and coreferences in conversational question answering. We propose to use a multi-label classifier based on DistilBERT. Multi-label classification and active learning are employed to compensate the limited amount of labeled data. We show that these methods greatly enhance the performance of the classifier for detecting these phenomena on a manually labeled dataset.

📄 PDF Abstract BibTeX arXiv:2207.03145

Code (0)

등록된 구현이 없습니다.

Tasks

Active LearningConversational Question AnsweringMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONQuestion Answering

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Adam 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Weight Decay 설명 없음

Similar Papers 제목 키워드 기반

RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling

2020-10-17 · EMNLP 2020 11 · Jun Quan, Shian Zhang, Qian Cao, Zizhong Li 외

In order to alleviate the shortage of multi-domain data and to capture discourse phenomena for task-oriented dialogue modeling, we propose RiSAWOZ, a large-scale multi-domain Chinese Wizard-of-Oz dataset with Rich Semant…

Dialogue State TrackingIntent DetectionNatural Language Understandingslot-filling+2

Ellipsis Resolution as Question Answering: An Evaluation

2019-08-29 · EACL 2021 2 · Rahul Aralikatte, Matthew Lamm, Daniel Hardt, Anders Søgaard

Most, if not all forms of ellipsis (e.g., so does Mary) are similar to reading comprehension questions (what does Mary do), in that in order to resolve them, we need to identify an appropriate text span in the preceding …

coreference-resolutionCoreference ResolutionMachine Reading ComprehensionQuestion Answering+1

Adapting Coreference Resolution Models through Active Learning

2021-04-15 · ACL 2022 5 · Michelle Yuan, Patrick Xia, Chandler May, Benjamin Van Durme 외

Neural coreference resolution models trained on one dataset may not transfer to new, low-resource domains. Active learning mitigates this problem by sampling a small subset of data for annotators to label. While active l…

Active LearningClusteringcoreference-resolutionCoreference Resolution

Spoken Conversational Search for General Knowledge

2019-09-26 · WS 2019 9 · Lina M. Rojas-Barahona, Pascal Bellec, Benoit Besset, Martinho Dos-Santos 외

We present a spoken conversational question answering proof of concept that is able to answer questions about general knowledge from Wikidata. The dialogue component does not only orchestrate various components but also …

Conversational Question AnsweringConversational SearchGeneral KnowledgeQuestion Answering

DialogSum: A Real-Life Scenario Dialogue Summarization Dataset

2021-05-14 · Findings (ACL) 2021 8 · Yulong Chen, Yang Liu, Liang Chen, Yue Zhang

Proposal of large-scale datasets has facilitated research on deep neural models for news summarization. Deep learning can also be potentially useful for spoken dialogue summarization, which can benefit a range of real-li…

Abstractive Dialogue SummarizationCommon Sense ReasoningManagementRepresentation Learning+1