paper-with-me

Papers

Linguistically-Informed Specificity and Semantic Plausibility for Dialogue Generation

2019-06-01 · NAACL 2019 6 · Wei-Jen Ko, Greg Durrett, Junyi Jessy Li

Sequence-to-sequence models for open-domain dialogue generation tend to favor generic, uninformative responses. Past work has focused on word frequency-based approaches to improving specificity, such as penalizing responses with only common words. In this work, we examine whether specificity is solely a frequency-related notion and find that more linguistically-driven specificity measures are better suited to improving response informativeness. However, we find that forcing a sequence-to-sequence model to be more specific can expose a host of other problems in the responses, including flawed discourse and implausible semantics. We rerank our model{'}s outputs using externally-trained classifiers targeting each of these identified factors. Experiments show that our final model using linguistically motivated specificity and plausibility reranking improves the informativeness, reasonableness, and grammatically of responses.

📄 PDF Abstract BibTeX

Code (1)

wjko2/Linguistically-Informed-Specificity-and-Semantic-Plausibility-for-Dialogue-Generation 공식 구현 pytorch

Tasks

Dialogue GenerationInformativenessRerankingSpecificity

Similar Papers 제목 키워드 기반

Challenging Neural Dialogue Models with Natural Data: Memory Networks Fail on Incremental Phenomena

2017-09-22 · Igor Shalyminov, Arash Eshghi, Oliver Lemon

Natural, spontaneous dialogue proceeds incrementally on a word-by-word basis; and it contains many sorts of disfluency such as mid-utterance/sentence hesitations, interruptions, and self-corrections. But training data fo…

RetrievalSentence

LinguaGame: A Linguistically Grounded Game-Theoretic Paradigm for Multi-Agent Dialogue Generation

2026-01-08 · Yuxiao Ye, Yiming Zhang, Yiran Ma, Huiyuan Xie 외 arxiv

Large Language Models (LLMs) have enabled Multi-Agent Systems (MASs) where agents interact through natural language to solve complex tasks or simulate multi-party dialogues. Recent work on LLM-based MASs has mainly focus…

Dialogue Generation

CONFIT: Toward Faithful Dialogue Summarization with Linguistically-Informed Contrastive Fine-tuning

2021-12-16 · NAACL 2022 7 · Xiangru Tang, Arjun Nair, Borui Wang, Bingyao Wang 외

Factual inconsistencies in generated summaries severely limit the practical applications of abstractive dialogue summarization. Although significant progress has been achieved by using pre-trained models, substantial amo…

Abstractive Dialogue SummarizationMeeting SummarizationText Summarization

Semantic Specificity in Spoken Dialogue Requests

2012-07-01 · WS 2012 7 · Ben Hixon, Rebecca J. Passonneau, Susan L. Epstein
Specificity

LIEDER: Linguistically-Informed Evaluation for Discourse Entity Recognition

2024-03-10 · Xiaomeng Zhu, Robert Frank

Discourse Entity (DE) recognition is the task of identifying novel and known entities introduced within a text. While previous work has found that large language models have basic, if imperfect, DE recognition abilities …