paper-with-me

홈 › Papers

Unsupervised Modeling of Topical Relevance in L2 Learner Text

2016-06-01 · WS 2016 6 · Ronan Cummins, Helen Yannakoudakis, Ted Briscoe
📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Information Retrieval

Similar Papers 제목 키워드 기반

An Information Theoretic Measurement of Topical Relevance in Learner Essays

2021-11-16 · ACL ARR November 2021 11 · Anonymous

We present a new approach to assess topical relevance in learner essays, leveraging recent advances in pretrained language models. Our approach is to generate features by calculating the normalized pointwise mutual infor…

Sentence Similarity Measures for Fine-Grained Estimation of Topical Relevance in Learner Essays

2016-06-09 · WS 2016 6 · Marek Rei, Ronan Cummins

We investigate the task of assessing sentence-level prompt relevance in learner essays. Various systems using word overlap, neural embeddings and neural compositional models are evaluated on two datasets of learner writi…

SentenceSentence SimilarityWord Embeddings

Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoring

2021-06-12 · SIGDIAL (ACL) 2021 7 · Linzi Xing, Giuseppe Carenini

Dialogue topic segmentation is critical in several dialogue modeling problems. However, popular unsupervised approaches only exploit surface features in assessing topical coherence among utterances. In this work, we addr…

Segmentation

Effective FAQ Retrieval and Question Matching With Unsupervised Knowledge Injection

2020-10-27 · Wen-Ting Tseng, Tien-Hong Lo, Yung-Chang Hsu, Berlin Chen

Frequently asked question (FAQ) retrieval, with the purpose of providing information on frequent questions or concerns, has far-reaching applications in many areas, where a collection of question-answer (Q-A) pairs compi…

Language ModellingRetrievalSentence

Modeling Topical Relevance for Multi-Turn Dialogue Generation

2020-09-27 · Hainan Zhang, Yanyan Lan, Liang Pang, Hongshen Chen 외

Topic drift is a common phenomenon in multi-turn dialogue. Therefore, an ideal dialogue generation models should be able to capture the topic information of each context, detect the relevant context, and produce appropri…

Dialogue GenerationSentence