Machine Translation Evaluation using Bi-directional Entailment

Khobragade, Rakesh; Patel, Heaven; Namdev, Anand; Mishra, Anish; Bhattacharyya, Pushpak

doi:10.48550/arxiv.1911.00681

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides the simple cosine similarity to measure the distance, Natural Language Inference (NLI) models also serve as an effective measure of semantic similarity [15]. We trained a BERT-based NLI model on the SNLI dataset [2] with 91.1% dev accuracy, the linear layer has three output neurons for labels of contradiction, entailment and neutral.…”

Section: B Comparison Of Different Selection Methodsmentioning

confidence: 99%

Multi-turn Dialogue Reading Comprehension with Pivot Turns and Knowledge

Zhang

Zhao

2021

Preprint

View full text Add to dashboard Cite

Multi-turn dialogue reading comprehension aims to teach machines to read dialogue contexts and solve tasks such as response selection and answering questions. The major challenges involve noisy history contexts and especial prerequisites of commonsense knowledge that is unseen in the given material. Existing works mainly focus on context and response matching approaches. This work thus makes the first attempt to tackle the above two challenges by extracting substantially important turns as pivot utterances and utilizing external knowledge to enhance the representation of context. We propose a pivotoriented deep selection model (PoDS) on top of the Transformerbased language models for dialogue comprehension. In detail, our model first picks out the pivot utterances from the conversation history according to the semantic matching with the candidate response or question, if any. Besides, knowledge items related to the dialogue context are extracted from a knowledge graph as external knowledge. Then, the pivot utterances and the external knowledge are combined with a well-designed mechanism for refining predictions. Experimental results on four dialogue comprehension benchmark tasks show that our proposed model achieves great improvements on baselines. A series of empirical comparisons are conducted to show how our selection strategies and the extra knowledge injection influence the results.

show abstract

Section: B Comparison Of Different Selection Methodsmentioning

confidence: 99%