Unsupervised Paraphrasing via Deep Reinforcement Learning

Siddique, A.B.; Oymak, Samet; Hristidis, Vagelis

doi:10.1145/3394486.3403231

Cited by 41 publications

(24 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rather than minimizing loss (the conventional approach), first utilized RL to maximize the reward given by an evaluator which outputs a real value to represent the matching degree between two sentences as paraphrases of each other. Other reward functions have been explored by researchers, including ROUGE score, perplexity score and language fluency (Siddique et al, 2020;.…”

Section: A Model-focusedmentioning

confidence: 99%

Paraphrase Generation: A Survey of the State of the Art

Zhou¹,

Bhat²

2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

This paper focuses on paraphrase generation, which is a widely studied natural language generation task in NLP. With the development of neural models, paraphrase generation research has exhibited a gradual shift to neural methods in the recent years. This has provided architectures for contextualized representation of an input text and generating fluent, diverse and human-like paraphrases. This paper surveys various approaches to paraphrase generation with a main focus on neural methods.

show abstract

Section: A Model-focusedmentioning

confidence: 99%

Paraphrase Generation: A Survey of the State of the Art

Zhou¹,

Bhat²

2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…Deep neural networks have proved highly effective for many critical NLP tasks [3,10,17,35,54,55,65,70] including slot filling. We organize the related work on slot filling into three categories: (i) supervised slot filling, (ii) few-shot slot filling, and (iii) zero-shot slot filling.…”

Section: Related Workmentioning

confidence: 99%

Linguistically-Enriched and Context-AwareZero-shot Slot Filling

Siddique

Jamour

Hristidis

2021

Proceedings of the Web Conference 2021

Self Cite

View full text Add to dashboard Cite

Slot filling is identifying contiguous spans of words in an utterance that correspond to certain parameters (i.e., slots) of a user request/query. Slot filling is one of the most important challenges in modern task-oriented dialog systems. Supervised approaches have proven effective at tackling this challenge, but they need a significant amount of labeled training data in a given domain. However, new domains (i.e., unseen in training) may emerge after deployment. Thus, it is imperative that these models seamlessly adapt and fill slots from both seen and unseen domains -unseen domains contain unseen slot types with no training data, and even seen slots in unseen domains are typically presented in different contexts. This setting is commonly referred to as zero-shot slot filling. Little work has focused on this setting, with limited experimental evaluation. Existing models that mainly rely on contextindependent embedding-based similarity measures fail to detect slot values in unseen domains or do so only partially. We propose a new zero-shot slot filling neural model, LEONA, which works in three steps.Step one acquires domain-oblivious, context-aware representations of utterance words by exploiting (a) linguistic features such as part-of-speech tags; (b) named entity recognition cues; and (c) contextual embeddings from pre-trained language models.Step two fine-tunes these rich representations and produces slotindependent tags for each word.Step three exploits generalizable context-aware utterance-slot similarity features at the word level, uses slot-independent tags, and contextualizes them to produce slot-specific predictions for each word. Our thorough evaluation on four diverse public datasets demonstrates that our approach consistently outperforms state-of-the-art models by 17.52%, 22.15%, 17.42%, and 17.95% on average for unseen domains on SNIPS, ATIS, MultiWOZ, and SGD datasets, respectively.

show abstract

“…The deep neural networks have proved highly effective for many critical NLP tasks [9,15,20,23,28,30,35,43] including intent detection. Supervised intent detection works [17,20,26,39,43] assume the availability of a large amount of labeled training data for all intents to learn discriminative features.…”

Section: Related Workmentioning

confidence: 99%

Generalized Zero-shot Intent Detection via Commonsense Knowledge

Siddique

Jamour

et al. 2021

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

Self Cite

View full text Add to dashboard Cite

Identifying user intents from natural language utterances is a crucial step in conversational systems that has been extensively studied as a supervised classification problem. However, in practice, new intents emerge after deploying an intent detection model. Thus, these models should seamlessly adapt and classify utterances with both seen and unseen intents -unseen intents emerge after deployment and they do not have training data. The few existing models that target this setting rely heavily on the training data of seen intents and consequently overfit to these intents, resulting in a bias to misclassify utterances with unseen intents into seen ones. We propose RIDE: an intent detection model that leverages commonsense knowledge in an unsupervised fashion to overcome the issue of training data scarcity. RIDE computes robust and generalizable relationship meta-features that capture deep semantic relationships between utterances and intent labels; these features are computed by considering how the concepts in an utterance are linked to those in an intent label via commonsense knowledge. Our extensive experimental analysis on three widely-used intent detection benchmarks shows that relationship meta-features significantly improve the detection of both seen and unseen intents and that RIDE outperforms the state-of-the-art models.

show abstract

Unsupervised Paraphrasing via Deep Reinforcement Learning

Cited by 41 publications

References 37 publications

Paraphrase Generation: A Survey of the State of the Art

Paraphrase Generation: A Survey of the State of the Art

Linguistically-Enriched and Context-AwareZero-shot Slot Filling

Generalized Zero-shot Intent Detection via Commonsense Knowledge

Contact Info

Product

Resources

About