Unsupervised Modeling of Topical Relevance in L2 Learner Text
Code (0)
등록된 구현이 없습니다.
Tasks
Information RetrievalSimilar Papers 제목 키워드 기반
An Information Theoretic Measurement of Topical Relevance in Learner Essays
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
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 EmbeddingsImproving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoring
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…
SegmentationEffective FAQ Retrieval and Question Matching With Unsupervised Knowledge Injection
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 ModellingRetrievalSentenceModeling Topical Relevance for Multi-Turn Dialogue Generation
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