Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userThink Before You Speak: Learning to Generate Implicit Knowledge for Response Generation by Self-Talk
فكر قبل أن تتحدث: تعلم توليد معرفة ضمنية لجيل الاستجابة عن طريق الحديث الذاتي
233
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يقدم البشر ردود مناسبة لا يستند فقط إلى كلام الحوار السابق ولكن أيضا على المعرفة الخلفية الضمنية مثل الحس السليم. على الرغم من أن نماذج توليد الاستجابة العصبية تنتج ردود تشبه الإنسان، إلا أنها في الغالب من طرفا ولا تولد أسباب وسيطة بين تاريخ الحوار والردود. يهدف هذا العمل إلى الدراسة إذا وكيف يمكننا تدريب نموذج RG الذي يتحدث عن نفسه لتوليد معرفة ضمنية قبل تقديم ردود. نحن نحقق مزيد من التحقيق في هذه النماذج عندما تولد معرفة خلفية ضمنية وعندما لا يكون ذلك ضروريا. تظهر النتائج التجريبية مقارنة بالنماذج التي تولد الردود مباشرة بالنظر إلى تاريخ الحوار، وتنتج نماذج الحديث الذاتي استجابات أفضل بجودة وفقا للتقييم البشري على الحكم النحوي والتماسك والعمل. والنماذج التي يتم تدريبها على تحديد متى يتحدث التحدث الذاتي إلى تحسين جودة الاستجابة. تبين تحليل المعرفة الضمنية الناتجة أن الطرز تستخدم معظمها المعرفة بشكل مناسب في الردود.
Humans make appropriate responses not only based on previous dialogue utterances but also on implicit background knowledge such as common sense. Although neural response generation models seem to produce human-like responses, they are mostly end-to-end and not generating intermediate grounds between a dialogue history and responses. This work aims to study if and how we can train an RG model that talks with itself to generate implicit knowledge before making responses. We further investigate can such models identify when to generate implicit background knowledge and when it is not necessary. Experimental results show that compared with models that directly generate responses given a dialogue history, self-talk models produce better-quality responses according to human evaluation on grammaticality, coherence, and engagingness. And models that are trained to identify when to self-talk further improves the response quality. Analysis on generated implicit knowledge shows that models mostly use the knowledge appropriately in the responses.
References used
https://aclanthology.org/
rate research
Read More
Evaluating the quality of responses generated by open-domain conversation systems is a challenging task. This is partly because there can be multiple appropriate responses to a given dialogue history. Reference-based metrics that rely on comparisons
to a set of known correct responses often fail to account for this variety, and consequently correlate poorly with human judgment. To address this problem, researchers have investigated the possibility of assessing response quality without using a set of known correct responses. RUBER demonstrated that an automatic response evaluation model could be made using unsupervised learning for the next-utterance prediction (NUP) task. For the unsupervised learning of such model, we propose a method of manipulating a golden response to create a new negative response that is designed to be inappropriate within the context while maintaining high similarity with the original golden response. We find, from our experiments on English datasets, that using the negative samples generated by our method alongside random negative samples can increase the model's correlation with human evaluations. The process of generating such negative samples is automated and does not rely on human annotation.
Keyphrases, that concisely summarize the high-level topics discussed in a document, can be categorized into present keyphrase which explicitly appears in the source text and absent keyphrase which does not match any contiguous subsequence but is high
ly semantically related to the source. Most existing keyphrase generation approaches synchronously generate present and absent keyphrases without explicitly distinguishing these two categories. In this paper, a Select-Guide-Generate (SGG) approach is proposed to deal with present and absent keyphrases generation separately with different mechanisms. Specifically, SGG is a hierarchical neural network which consists of a pointing-based selector at low layer concentrated on present keyphrase generation, a selection-guided generator at high layer dedicated to absent keyphrase generation, and a guider in the middle to transfer information from selector to generator. Experimental results on four keyphrase generation benchmarks demonstrate the effectiveness of our model, which significantly outperforms the strong baselines for both present and absent keyphrases generation. Furthermore, we extend SGG to a title generation task which indicates its extensibility in natural language generation tasks.
Personalized response generation is essential for more human-like conversations. However, how to model user personalization information with no explicit user persona descriptions or demographics still remains under-investigated. To tackle the data sp
arsity problem and the huge number of users, we utilize tensor factorization to model users' personalization information with their posting histories. Specifically, we introduce the personalized response embedding for all question-user pairs and form them into a three-mode tensor, decomposed by Tucker decomposition. The personalized response embedding is fed to either the decoder of an LSTM-based Seq2Seq model or a transformer language model to help generate more personalized responses. To evaluate how personalized the generated responses are, we further propose a novel ranking-based metric called Per-Hits@k which measures how likely are the generated responses come from the corresponding users. Results on a large-scale conversation dataset show that our proposed tensor factorization based models generate more personalized and higher quality responses compared to baselines.
Motivated by suggested question generation in conversational news recommendation systems, we propose a model for generating question-answer pairs (QA pairs) with self-contained, summary-centric questions and length-constrained, article-summarizing an
swers. We begin by collecting a new dataset of news articles with questions as titles and pairing them with summaries of varying length. This dataset is used to learn a QA pair generation model producing summaries as answers that balance brevity with sufficiency jointly with their corresponding questions. We then reinforce the QA pair generation process with a differentiable reward function to mitigate exposure bias, a common problem in natural language generation. Both automatic metrics and human evaluation demonstrate these QA pairs successfully capture the central gists of the articles and achieve high answer accuracy.
We propose to tackle data-to-text generation tasks by directly splicing together retrieved segments of text from neighbor'' source-target pairs. Unlike recent work that conditions on retrieved neighbors but generates text token-by-token, left-to-righ
t, we learn a policy that directly manipulates segments of neighbor text, by inserting or replacing them in partially constructed generations. Standard techniques for training such a policy require an oracle derivation for each generation, and we prove that finding the shortest such derivation can be reduced to parsing under a particular weighted context-free grammar. We find that policies learned in this way perform on par with strong baselines in terms of automatic and human evaluation, but allow for more interpretable and controllable generation.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
