Related papers: Entailment Relation Aware Paraphrase Generation
Recently, large language models such as GPT-2 have shown themselves to be extremely adept at text generation and have also been able to achieve high-quality results in many downstream NLP tasks such as text classification, sentiment…
In recent years, the generation of conversation content based on deep neural networks has attracted many researchers. However, traditional neural language models tend to generate general replies, lacking logical and emotional factors. This…
Understanding inferences and answering questions from text requires more than merely recovering surface arguments, adjuncts, or strings associated with the query terms. As humans, we interpret sentences as contextualized components of a…
Embodied Everyday Task is a popular task in the embodied AI community, requiring agents to make a sequence of actions based on natural language instructions and visual observations. Traditional learning-based approaches face two challenges.…
Program synthesis is the task of automatically generating a program consistent with a specification. Recent years have seen proposal of a number of neural approaches for program synthesis, many of which adopt a sequence generation paradigm…
Paraphrases are important linguistic resources for a wide variety of NLP applications. Many techniques for automatic paraphrase mining from general corpora have been proposed. While these techniques are successful at discovering generic…
In reinforcement learning (RL), the ability to utilize prior knowledge from previously solved tasks can allow agents to quickly solve new problems. In some cases, these new problems may be approximately solved by composing the solutions of…
We propose syntactically controlled paraphrase networks (SCPNs) and use them to generate adversarial examples. Given a sentence and a target syntactic form (e.g., a constituency parse), SCPNs are trained to produce a paraphrase of the…
In this paper, we study the technical problem of developing conversational agents that can quickly adapt to unseen tasks, learn task-specific communication tactics, and help listeners finish complex, temporally extended tasks. We find that…
Most NLP datasets are manually labeled, so suffer from inconsistent labeling or limited size. We propose methods for automatically improving datasets by viewing them as graphs with expected semantic properties. We construct a paraphrase…
In the era of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) architectures are gaining significant attention for their ability to ground language generation in reliable knowledge sources. Despite their effectiveness, RAG…
We consider the problem of learning general-purpose, paraphrastic sentence embeddings in the setting of Wieting et al. (2016b). We use neural machine translation to generate sentential paraphrases via back-translation of bilingual sentence…
Expository documents are vital resources for conveying complex information to readers. Despite their usefulness, writing expository text by hand is a challenging process that requires careful content planning, obtaining facts from multiple…
This work studies comparatively two typical sentence matching tasks: textual entailment (TE) and answer selection (AS), observing that weaker phrase alignments are more critical in TE, while stronger phrase alignments deserve more attention…
Customer support via chat requires agents to resolve customer queries with minimum wait time and maximum customer satisfaction. Given that the agents as well as the customers can have varying levels of literacy, the overall quality of…
High-quality paraphrases are easy to produce using instruction-tuned language models or specialized paraphrasing models. Although this capability has a variety of benign applications, paraphrasing attacks$\unicode{x2013}$paraphrases applied…
Our goal, in the context of open-domain textual question-answering (QA), is to explain answers by showing the line of reasoning from what is known to the answer, rather than simply showing a fragment of textual evidence (a "rationale'"). If…
Reinforcement learning plays a crucial role in generative re-ranking scenarios due to its exploration-exploitation capabilities, but existing generative methods mostly fail to adapt to the dynamic entropy changes in model difficulty during…
Current pre-training works in natural language generation pay little attention to the problem of exposure bias on downstream tasks. To address this issue, we propose an enhanced multi-flow sequence to sequence pre-training and fine-tuning…
The transferability of adversarial examples is a crucial aspect of evaluating the robustness of deep learning systems, particularly in black-box scenarios. Although several methods have been proposed to enhance cross-model transferability,…