Related papers: Entailment Relation Aware Paraphrase Generation
Paraphrase generation has been widely used in various downstream tasks. Most tasks benefit mainly from high quality paraphrases, namely those that are semantically similar to, yet linguistically diverse from, the original sentence.…
Current approaches in paraphrase generation and detection heavily rely on a single general similarity score, ignoring the intricate linguistic properties of language. This paper introduces two new tasks to address this shortcoming by…
Entailment has been recognized as an important metric for evaluating natural language understanding (NLU) models, and recent studies have found that entailment pretraining benefits weakly supervised fine-tuning. In this work, we design a…
Learning from a real-world data stream and continuously updating the model without explicit supervision is a new challenge for NLP applications with machine learning components. In this work, we have developed an adaptive learning system…
How to identify, extract, and use phrasal knowledge is a crucial problem for the task of Recognizing Textual Entailment (RTE). To solve this problem, we propose a method for detecting paraphrases via natural deduction proofs of semantic…
Associative thinking--the ability to connect seemingly unrelated ideas--is a foundational element of human creativity and problem-solving. This paper explores whether reinforcement learning (RL) guided by associative thinking principles can…
If two sentences have the same meaning, it should follow that they are equivalent in their inferential properties, i.e., each sentence should textually entail the other. However, many paraphrase datasets currently in widespread use rely on…
In this paper, we propose a novel neural approach for paraphrase generation. Conventional para- phrase generation methods either leverage hand-written rules and thesauri-based alignments, or use statistical machine learning principles. To…
Paraphrasing natural language sentences is a multifaceted process: it might involve replacing individual words or short phrases, local rearrangement of content, or high-level restructuring like topicalization or passivization. Past…
We use reinforcement learning to learn tree-structured neural networks for computing representations of natural language sentences. In contrast with prior work on tree-structured models in which the trees are either provided as input or…
Exemplar-Guided Paraphrase Generation (EGPG) aims to generate a target sentence which conforms to the style of the given exemplar while encapsulating the content information of the source sentence. In this paper, we propose a new method…
Empathetic response generation, aiming to understand the user's situation and feelings and respond empathically, is crucial in building human-like dialogue systems. Traditional approaches typically employ maximum likelihood estimation as…
The generation of explanation graphs is a significant task that aims to produce explanation graphs in response to user input, revealing the internal reasoning process. This task is challenging due to the significant discrepancy between…
Natural Language Inference (NLI) or Recognizing Textual Entailment (RTE) is the task of predicting the entailment relation between a pair of sentences (premise and hypothesis). This task has been described as a valuable testing ground for…
Paraphrase generation is an important task in natural language processing. Previous works focus on sentence-level paraphrase generation, while ignoring document-level paraphrase generation, which is a more challenging and valuable task. In…
Conversational AI assistants are becoming popular and question-answering is an important part of any conversational assistant. Using relevant utterances as features in question-answering has shown to improve both the precision and recall…
Explainable natural language inference aims to provide a mechanism to produce explanatory (abductive) inference chains which ground claims to their supporting premises. A recent corpus called EntailmentBank strives to advance this task by…
A long-standing issue with paraphrase generation is how to obtain reliable supervision signals. In this paper, we propose an unsupervised paradigm for paraphrase generation based on the assumption that the probabilities of generating two…
Recent work has shown that a multilingual neural machine translation (NMT) model can be used to judge how well a sentence paraphrases another sentence in the same language (Thompson and Post, 2020); however, attempting to generate…
Building explainable systems is a critical problem in the field of Natural Language Processing (NLP), since most machine learning models provide no explanations for the predictions. Existing approaches for explainable machine learning…